EP1656650A1 - Method and system for detecting a body in a zone located proximate an interface - Google Patents

Method and system for detecting a body in a zone located proximate an interface

Info

Publication number
EP1656650A1
EP1656650A1 EP04767924A EP04767924A EP1656650A1 EP 1656650 A1 EP1656650 A1 EP 1656650A1 EP 04767924 A EP04767924 A EP 04767924A EP 04767924 A EP04767924 A EP 04767924A EP 1656650 A1 EP1656650 A1 EP 1656650A1
Authority
EP
European Patent Office
Prior art keywords
data
interface
representative
bodies
green
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
EP04767924A
Other languages
German (de)
French (fr)
Other versions
EP1656650B1 (en
Inventor
Thierry Cohignac
Frédéric Guichard
Christophe Migliorini
Fanny Rousson
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
MG International SA
Original Assignee
Vision IQ
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Vision IQ filed Critical Vision IQ
Publication of EP1656650A1 publication Critical patent/EP1656650A1/en
Application granted granted Critical
Publication of EP1656650B1 publication Critical patent/EP1656650B1/en
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G08B21/08—Alarms for ensuring the safety of persons responsive to the presence of persons in a body of water, e.g. a swimming pool; responsive to an abnormal condition of a body of water
    • G08B21/082—Alarms for ensuring the safety of persons responsive to the presence of persons in a body of water, e.g. a swimming pool; responsive to an abnormal condition of a body of water by monitoring electrical characteristics of the water

Definitions

  • the present invention relates to a method, a system and devices for detecting a body in an area located near an interface between two liquid and / or gaseous media, in particular of the water / air type.
  • “near” also means “at the interface”.
  • Problem posed The problem concerns the detection of the presence of bodies in the vicinity of a water / air interface.
  • the invention sets out more particularly to solve these various problems in the case, among others, of the following four applications: - alarm if a stationary body is located under the interface.
  • the device written in this patent uses principles of detection and localization of bodies relative to the interface different from those which are the subject of the present application.
  • Solution The present invention solves the problem of detecting bodies located in the vicinity of a water / air type interface by proposing a method and a system making it possible to evaluate the position of a body relative to an interface, particularly of water type. / air, to discriminate moving bodies from stationary bodies, to generate alerts, to compile statistics, to give elements of trajectography and to allow the detection of entries or exits of bodies in the monitored area.
  • the invention relates to a method for detecting a body in an area located near an interface between two liquid and / or gaseous media, especially of the water / air type.
  • the body is lit by electromagnetic radiation comprising at least two different wavelengths, in particular situated in ranges corresponding to the near infrared on the one hand and to green-blue on the other hand.
  • the media have different absorption coefficients depending on the wavelengths of the electromagnetic radiation.
  • the method comprises the following steps: - (a) the step of choosing from the wavelengths of the electromagnetic radiation, at least two wavelengths or two wavelength ranges, - (b) the step of perform, for each wavelength or wavelength range, an image of the interface and of the area, - (c) the step of producing electrical signals representative of each image, - (d) the step of digitizing the electrical signals so as to produce data corresponding to each image, - (e) the step of extracting data corresponding to each image two groups of data respectively representative of at least one part of the body in the range near infrared and in the green-blue range, - (f) the step of comparing the groups of data. Steps (c) to (f) are hereinafter referred to as the process of deducing the presence of a body.
  • the method further comprises the step of integrating over time the results of the step of comparing the groups of data.
  • the method further comprises the step of triggering an alarm if a human-sized body is detected under the interface for a time greater than a determined threshold.
  • the method is such that to extract data corresponding to each image two groups of data respectively representative of at least one part of the body in the near infrared range and in the green-blue range, we generates caps (within the meaning of the present invention).
  • the method further comprises the following steps: the step of associating characteristics with each cap, - the step of deducing the presence of a group of data representative of at least part of the body if the characteristics exceed a predetermined SC threshold.
  • the method is such that to compare the groups of data, one searches for the data representative of at least one part of the body in the green-blue range for which there is not, in a neighborhood determined geometric, corresponding data representative of at least one part of the body in the near infrared range. So in case of a positive search, we can conclude that the body is located under the interface.
  • the method is such that to compare the groups of data, one searches for the data representative of at least one part of the body in the green-blue range for which there is, in a determined geometric neighborhood, corresponding data representative of at least one part of the body in the infrared range.
  • the method is more particularly intended to discriminate between a stationary body and a moving body.
  • the method in order to integrate the results of the comparison of the groups of data over time, the method further comprises the following steps: the step of iterating at specific time intervals the process of deduction of the presence of the body,
  • the invention also relates to a system for detecting a body in an area located near an interface between two liquid and / or gaseous media, in particular of the water / air type.
  • the body is lit by electromagnetic radiation comprising at least two different wavelengths, in particular situated in ranges corresponding to the near infrared on the one hand and to green-blue on the other hand.
  • the media have different absorption coefficients depending on the wavelengths of the electromagnetic radiation.
  • the system includes: - (a) selection means for choosing from the wavelengths of the electromagnetic radiation, at least two wavelengths or two wavelength ranges, - (b) means for taking pictures to produce, for each of the wavelengths or wavelength ranges, an image of the interface and of the area, (c) conversion means for producing electrical signals representative of each image, - (d) digitization means for digitizing the electrical signals so as to produce data corresponding to each image, (e) computer processing means for extracting data corresponding to each image two groups of data respectively representative of at least one part of the body in the near range infrared and in the green-blue range, - (f) means of calculation for comparing the groups of data.
  • the means of conversion, the means of digitization, the means of computer processing, the means of calculation are hereinafter called the means of deducing the presence of a body.
  • the system further comprises integration means for integrating over time the results of the means of calculating the data groups.
  • the system further comprises activation means for activating an alarm if a body of human size is detected under the interface for a time greater than a determined threshold.
  • the system is such that the computer processing means make it possible to generate caps (within the meaning of the present invention).
  • the system is such that the computer processing means make it possible: - to associate characteristics with each cap, - to deduce the presence of a group of data representative of at least one part of the body if the characteristics exceed a predetermined threshold SC.
  • the system is such that the calculation means make it possible to search for data representative of at least one part of the body in the green-blue range for which there is not, in a determined geometric neighborhood , corresponding data representative of at least one part of the body in the near infrared range. It results from the combination of technical features that in the event of a positive search, we can conclude that the body is located under the interface.
  • the system is such that the calculation means make it possible to search for the data representative of at least one part of said body in the green-blue range for which there is, in a determined geometric neighborhood, data corresponding representative of at least part of said body in the near infrared range. It results from the combination of technical features that in the event of a positive search, it can be concluded that said body is located at least partially above the interface.
  • the system is more particularly intended to discriminate between a stationary body and a moving body.
  • the system is such that the integration means for integrating over time the results of the calculation means make it possible: - to iterate at determined time intervals the implementation means for deducing the presence of said body;
  • FIG. 7 which represents a flowchart of the computer processing means
  • - Figure 8 shows a general schematic view of the system according to the invention.
  • Pixel, Pixel value Pixel is called: an elementary area of an image obtained by creating a tiling, generally regular, of said image.
  • a sensor such as a video camera, or a thermal or acoustic camera
  • FIG. 1a represents an image 101 (symbolized by a man, swimming on the surface of a swimming pool, the contours of which are not perfectly visible).
  • FIG. 1b a tiling 102 of pixels 103 has been superimposed on this image.
  • a tiling has been shown in the figure on which the values of the pixels have been indicated.
  • Adjacent pixels Two pixels of the tiling are said to be adjacent if their edges or corners touch.
  • Path on tiling A path on tiling is an ordered and finite set of pixels where each pixel is adjacent to its next (in the sense of the ordering). The size of a path is given by the number of pixels making it up.
  • FIG. 2a represents a tiling 202 of 16 pixels 203, among which we have highlighted 3 pixels, called A, B and C. It can be noted that the pixels A and B are adjacent and that the pixels B and C are adjacent. There is therefore a path (A->B-> C) which connects these pixels. The set of pixels ⁇ A, B, C ⁇ is therefore connected. In FIG. 2b, a tiling has also been shown.
  • Each pair of pixels in the set is linked by a path of pixels belonging to the set, the set of pixels ⁇ A, B, C , E, F, 1 ⁇ is therefore connected.
  • FIG. 2c the same tiling 202 has been shown as in FIG. 2b, by selecting the set of pixels ⁇ A, C, F, N, P ⁇ .
  • A->C-> F which connects the pixels A, C and F, but there is no path of pixels belonging to the set connecting N and P, or else N to A.
  • L ' set of pixels ⁇ A, C, F, N, P ⁇ is not connected.
  • the set ⁇ A, C, F ⁇ is connected.
  • Pixel adjacent to a set A pixel which does not belong to a set is said to be adjacent to said set when it is joined to at least one pixel belonging to said set.
  • Level of a cap We call level of a top cap. or inf. said predetermined value.
  • FIG. 3a, 3b, 4a, and 4b represent images composed of tilings 302 (resp. 402) of pixels 303 (resp. 403) on which their values have been indicated.
  • FIG. 3a represents (inside 304 of the strong line 305) a set of 4 pixels. This set has the following properties: - it is connected in the sense of the definition given, - the values of all the pixels of the set are greater than 1, - the (twelve) pixels adjacent to the set have for some a value greater than 1. The set of pixels considered is therefore not an upper cap. level 1.
  • this set of pixels has the following properties: - it is connected in the sense of the definition given, - the values of all the pixels in the set are greater than 2, - the (twelve) contiguous pixels to the set all have a value less than or equal to 2.
  • This set of pixels is therefore an upper cap. level 2.
  • FIG. 3b represents a set 306 of eight pixels having the following properties: - it is connected in the sense of the definition given, - the values of all the pixels of the set are greater than 1, - the (eighteen) pixels contiguous to the set all have a value less than or equal to 1.
  • the set of pixels considered is therefore an upper cap. of level 1.
  • FIG. 4a represents a tiling 402 of pixels 403.
  • a strong line 405 has isolated a set 404 of ten pixels distributed in two zones 404 a and 404b.
  • This set of pixels 404 has the following properties: - it is not connected within the meaning of the definition given, - the values of all the pixels are greater than 1 - the (twenty-five) pixels joined to the set all have a value less than or equal to 1. The ten pixels of this unrelated set therefore do not constitute an upper cap. of level 1.
  • FIG. 4b represents a set 406 of twelve pixels having the following properties: - it is connected in the sense of the definition given, - the values of the pixels are not all greater than 1, - the (twenty- four) pixels joined to the set all have a value less than or equal to 1.
  • Characteristic (s) associated with a skullcap We call characteristic (s) associated (s) with a skullcap: one or more values obtained by arithmetic and / or logical operations predefined from the pixel values of the cap, and / or the positions of the pixels in the tiling, and / or the level of the cap. For example, an arithmetic operation could consist in using the sum of the differences between the value of each pixel of the cap and the level of the cap, or even the size (number of pixels) of said cap.
  • Figure 5 represents a schematic view of the system allowing the detection of bodies located in the vicinity of a water type interface /air. Since the green-blue 501 and near infrared 502 images are not necessarily taken from the same observation point, the data or the images can advantageously be replaced in a virtual common reference frame 503.
  • the virtual reference frame may correspond to the surface of water 504, so that a point on the surface of water 505, seen by the green-blue camera 506 and seen by the near infrared camera 507, will be in the same place 508 in the common coordinate system virtual. In this way, two points close to real space will correspond to close points in this virtual common landmark.
  • FIG. 6 represents, in the case of a swimming pool, a general view of the system allowing the detection of bodies located in the vicinity of a water / air type interface, in particular the detection and monitoring of swimmers.
  • the system according to the invention comprises means, hereinafter described, for detecting a body 601 in a zone 603 located near an interface 602 between two liquid media 604 and / or gaseous 605 in particular of the water / air type; said body being illuminated by electromagnetic radiation comprising at least two different wavelengths, in particular situated in ranges corresponding to the near infrared on the one hand and to green-blue on the other hand; said media having different absorption coefficients as a function of the wavelengths of the electromagnetic radiation.
  • “near” also means "at the interface”.
  • the system further comprises the means: A video camera 606a, equipped with a filter making it possible to produce at least one video image in the wavelength range of 300 to 700 nm (range called green-blue below).
  • a video camera 606b equipped with a filter making it possible to produce at least one video image in the wavelength range from 780 to 1100 nm (range termed near infrared thereafter). These cameras make it possible to produce video images of said interface 602 and of said zone 603, from at least two observation points 607a and 607b. These images are represented by electrical signals 608a and 608b.
  • Each of the observation points 607a and 607b is located on one side of said interface 602. In this case, the observation points 607a and 607b are located above the swimming pool.
  • the video cameras 606a and 606b and their housings are aerial, they are in the open air.
  • the system further includes digital conversion means 609 for producing digital data from electrical signals 608a and 608b representative of the green-blue and near infrared video images.
  • digital conversion means 609 for producing digital data from electrical signals 608a and 608b representative of the green-blue and near infrared video images.
  • the cameras 606a and 606b are equipped with polarizing filters 611a and 611b at least partially eliminating the reflections of light on said interface in said images.
  • This variant embodiment is particularly suitable in the case of a swimming pool reflecting the rays of the sun or those of an artificial lighting.
  • Said system further comprises computer processing means 700 described below.
  • FIG. 7 represents a flow diagram of the computer processing means 700.
  • the computer processing means 700 make it possible to discriminate the data corresponding to the green-blue video images of a part of a real body (FIG. 1a) from those corresponding to the video images apparent blue-green (FIG. 1b) generated by said interface 602.
  • the computer processing means 700 also make it possible to discriminate the data corresponding to near infrared video images of a part of a real body (FIG. 1a) from those corresponding to near infrared video images apparent (FIG. 1b) generated by said interface 602.
  • Said computer processing means 700 comprise calculation means, in particular a processor 701, and a memory 702.
  • Computer processing means 700 comprise means of 712 to extract a group of data representative of at least one part of the body in the near infrared range uge.
  • the computer processing means 700 further comprise extraction means 713 making it possible to extract a group of data representative of at least one part of the body in the green-blue range.
  • the extraction means 712 and 713 to extract groups of data representative of at least one part of the body in the near infrared range and in the green-blue range, the extraction means 712 and 713 - generate caps, - associate characteristics with each cap, - deduce the presence of a group of data representative of at least one part of the body if the characteristics exceed a predetermined threshold SC.
  • An example of a characteristic associated with a cap may be its area defined by the number of pixels constituting it.
  • Another characteristic associated with a cap can be its contrast defined as the sum of the differences between the value of each pixel of the cap and the level of the cap.
  • a data group representative of a part of a body could then be a cap having a contrast greater than a threshold SC and an area between a ThinMin threshold and a MaxMax threshold representative of the minimum and maximum dimensions of the body parts wanted.
  • the computer means 700 make it possible to select from the groups of extracted data, those which do not correspond to a part of the swimmer.
  • the system includes means making it possible to eliminate the caps corresponding to reflections, water lines, carpets as well as any object potentially present in a swimming pool and not corresponding to a part of the swimmer.
  • Examples of selection may be made by calculating the level of the caps, which must be below a threshold SR corresponding to the average gray level of the reflections, by calculating the alignment of the caps, corresponding to the usual position of the water lines. , by estimating the shape of the caps which should not be rectangular in order to eliminate the carpets.
  • the extraction means 712 and 713 may proceed other than by means of the extraction of caps.
  • the extraction means 712 and 713 can extract groups of pixels sharing one or more predetermined properties, and then associate characteristics with each group of pixels, and deduce the presence of a group of data representative of at least a body part if the characteristics exceed a predetermined SC threshold.
  • the predetermined property or properties may for example be chosen so as to exclude the appearance of the water / air interface in the image.
  • Said computer processing means 700 also comprise comparison means 714, for comparing said groups of data.
  • said comparison means 714 search for data representative of at least part of said body in the green-blue range for which there is not, in a geometrical comparison neighborhood, corresponding representative data at least a part of said body in the near infrared range. So that in the event of a positive search, it can be concluded that said body is located under the interface.
  • a geometric comparison neighborhood for example a circular neighborhood with a radius of 50 cm, centered on the center of gravity of the extracted caps in the green-blue image, caps extracted in the near infrared image. If the search is negative, the swimmer is considered to be below the surface of the water.
  • one searches for data representative of at least one part of said body in the green-blue range for which there is, in a geometric comparison neighborhood, corresponding data representative of at least one part of said body in the near infrared range. So that in the event of a positive search, it can be concluded that said body is located at least in part above the interface.
  • a geometric comparison neighborhood for example a circular neighborhood with a radius of 50 cm, centered on the center of gravity of the extracted caps in the green-blue image, caps extracted in the near infrared image. If the search is positive, the swimmer is considered to be at least partly above the surface of the water.
  • the caps extracted in the green-blue image and those extracted in the near infrared image are matched if the distance the shortest (between the two closest pixels) is less than 30 cm.
  • the unpaired green-blue image caps will then be considered to be a swimmer below the surface of the water.
  • the paired caps of the green-blue image will be considered as swimmers partly above the surface of the water.
  • the geometric comparison neighborhood is not necessarily determined.
  • the geometric comparison neighborhood relating to the infrared and green-blue caps respectively, as a function of geometric considerations relating to the positions of said caps and possibly also as a function of geometric considerations specific to the environment in particular the orientation of the cameras relative to the interface or the orientation in the images of the normal to the interface.
  • the caps from the infrared cameras being relative to the body parts located above the interface, we will look for the corresponding green-blue caps in a geometric comparison neighborhood calculated according to the orientation of the normal to the interface.
  • the system described in the present invention can be used in complement of a system based on stereovision such as that described in patent n ° FR 00/15803.
  • the system described in patent n ° FR 00/15803 detects a body under the surface of the water and, - if there is, in a determined geometrical neighborhood, corresponding data representative of at least one part of said body in the near infrared range, it can be concluded that said body is located at least partly above the interface, - if there is not, in a determined geometrical neighborhood, corresponding data representative of at least a part of said body in the near infrared range, it can be concluded that said body is located below one interface.
  • the system described in the present invention can advantageously use stereovision principles such as those described in patent No. FR 00/15803.
  • said system includes integration over time 703, associated with a clock 704, to iterate at determined time intervals said process for deducing the presence of a body described above.
  • the video images are taken at time intervals determined from said observation point.
  • said computer processing means 700 include totalizers 705 for calculating the number of times the body is detected during a determined period of time T1.
  • Said computer processing means 700 further comprise discriminators 706 for discriminating, at a point in said zone, between the bodies which are present a number of times greater than a determined threshold SI and the bodies which are present a number of times lower than said determined threshold SI.
  • said bodies are hereinafter designated the stationary bodies
  • said bodies are hereinafter designated the moving bodies.
  • said computer processing means 700 further comprises means for calculating the number of times a body is detected as being stationary and new during a determined period of time T2. Said time period T2 is chosen to be greater than the duration of the phenomena that are observed, and in particular greater than T1.
  • Said computer processing means 700 furthermore comprise transmission means 716 for transmitting an alert signal 711 according to the detection criteria described above.
  • an additional step of integration over time may advantageously be carried out by accumulation of images from the same green-blue and / or near infrared camera.
  • the accumulated image is calculated for example by averaging the gray levels of the pixels of the successive images taken over a determined time interval.
  • An accumulated image obtained by accumulation of images from a green-blue camera will be called green-blue accumulated image.
  • an accumulated image obtained by accumulation of images from a near infrared camera will be called an accumulated near infrared image.
  • the extraction means 712 and 713 can then also use the accumulated green-blue and / or near infrared images.
  • the extraction means 712 may extract only the caps of the green-blue image for which there is not, in the accumulated green-blue image, a similar cap located in a neighborhood.
  • Extraction means 712 and 713 can then also use composite images consisting of accumulated green-blue images and green-blue images as well as composite images consisting of accumulated near infrared and near infrared images.
  • the extraction means 712 could use the difference between the green-blue image and the accumulated green-blue image.
  • FIG. 8 represents a general schematic view of the system according to the invention.
  • the system makes it possible to detect a body 801 in a zone 802 located near an interface 803 between two liquid 812 and / or gaseous 813 media, in particular of the water / air type.
  • the body 801 is illuminated by electromagnetic radiation 804 comprising at least two different wavelengths, in particular situated in ranges corresponding to the near infrared on the one hand and to green-blue on the other hand.
  • the media 812 and 813 have different absorption coefficients as a function of the wavelengths of the electromagnetic radiation.
  • the system comprises: - (a) selection means 814 for choosing from the wavelengths of electromagnetic radiation 804, at least two wavelengths or two wavelength ranges, - (b) pick-up means views 815 to produce, for each wavelength or wavelength range, an image 805 of the interface and of the area, - (c) conversion means 816 for producing electrical signals 6 representative of each image 805, - (d) digitization means 817 for digitizing the electrical signals 806 so as to produce data 807 corresponding to each image, - (e) computer processing means 818 for extracting data 807 corresponding to each image 805 two groups of data 807 respectively representative of at least one part of the body 801 in the near infrared range and in the green-blue range, (f) calculation means 819 for comparing the groups of data 807.
  • the conversion means 816, the digitization means 817, the computer processing means 818, the calculation means 819 are hereinafter called the deduction means from the presence of a body 801. It is thus possible to detect the presence of a body 801 and / or to determine the position of the detected body with respect to the interface 803, by discriminating between a body 801 located under the interface 803 and a body 801 located at least in part above the interface 803.
  • the system further comprises integration means 820 for integrating over time the results of the calculation means 819 of the data groups 807.
  • the system further comprises activation means 821 for activating an alarm 808 if a body of human size is st detected under the interface for a time greater than a determined threshold.

Landscapes

  • Emergency Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Image Processing (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Geophysics And Detection Of Objects (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Radar Systems Or Details Thereof (AREA)
  • Optical Radar Systems And Details Thereof (AREA)
  • Image Analysis (AREA)
  • Emergency Alarm Devices (AREA)
  • Studio Devices (AREA)

Abstract

The invention concerns a method and a system for detecting a body (801) in a zone (802) located proximate an interface (803). The body is illuminated by an electromagnetic radiation (804) comprising at least two different wavelengths, located in ranges corresponding to near infrared and to green-blue. The method comprises the following steps: selecting two wavelengths; providing, for each of said wavelengths, an image (805) of the interface and of the zone; extracting from said data of each image two sets of data (807) respectively representing at least one part of the body in the near infrared range and in the green-blue range; comparing said data sets (807). It is thus possible to detect the presence of a body by discriminating between a body entirely located beneath the interface and a body located at least partly above the interface.

Description

PROCEDE ET SYSTEME POUR DETECTER UN CORPS DANS UNE ZONE SITUEE A PROXIMITE D'UNE INTERFACEMETHOD AND SYSTEM FOR DETECTING A BODY IN A ZONE LOCATED NEAR AN INTERFACE
Préambule de la description Domaine concerné La présente invention concerne un procédé, un système et des dispositifs pour détecter un corps dans une zone située à proximité d'une interface entre deux milieux liquides et/ou gazeux notamment du type eau/air. Au sens de la présente invention "à proximité" désigne également "à l'interface". Problème posé Le problème concerne la détection de présence de corps dans le voisinage d'une interface de type eau/air. En plus de ce problème principal, viennent s'ajouter la discrimination entre les corps situés d'un côté ou de l'autre de l'interface et la détection de corps stationnaires . L'invention s'attache plus particulièrement à résoudre ces différents problèmes dans le cas, entre autres, des quatre applications suivantes : - alarme si un corps stationnaire est situé sous l'interface. Par exemple, alarme dans le cas d'un corps immergé dans l'eau depuis un temps jugé trop long, - estimation statistique du temps d'occupation d'une zone surveillée. Cette application permet d'effectuer des analyses statistiques sur notamment l'occupation d'une piscine, - estimation de trajectoire des corps, - mise en évidence de la disparition d'un corps de la zone surveillée. Cette application peut être exploitée notamment dans le cas de la surveillance des nageurs en bord de mer. Art antérieur Il existe différentes méthodes de détection de présence de corps dans une certaine zone. Elles utilisent en général plusieurs capteurs vidéo installés sous le niveau de l'interface. Bien qu'efficaces ces techniques ne sont pas toujours commodes à mettre en œuvre. Elles peuvent également soulever des problèmes de maintenance, notamment dans des piscines ne comportant pas de galeries techniques. Par ailleurs, pour résoudre ces problèmes, le déposant, a déposé le 6 décembre 2000 le brevet n° FR 00/15803 intitulé « procédé, système et dispositif pour détecter un corps à proximité d'une interface eau/air ». Le dispositif écrit dans ce brevet utilise des principes de détection et de localisation des corps par rapport à l'interface différents de ceux faisant l'objet de la présente demande. Solution La présente invention résout le problème de la détection de corps situés au voisinage d'une interface de type eau/air en proposant un procédé et un système permettant d'évaluer la position d'un corps par rapport à une interface notamment de type eau/air, de discriminer les corps en mouvement des corps stationnaires, de générer des alertes, d'élaborer des statistiques, de donner des éléments de trajectographie et de permettre la détection d'entrées ou de sorties de corps dans la zone surveillée. Procédé L'invention concerne un procédé pour détecter un corps dans une zone située à proximité d'une interface entre deux milieux liquides et/ou gazeux, notamment du type eau/air. Le corps est éclairé par un rayonnement électromagnétique comprenant au moins deux longueurs d'onde différentes, notamment situées dans des plages correspondant au proche infra-rouge d'une part et au vert-bleu d'autre part. Les milieux ont des coefficients d'absorption différents en fonction des longueurs d'onde du rayonnement électromagnétique. Le procédé comprend les étapes suivantes : - (a) l'étape de choisir parmi les longueurs d'onde du rayonnement électromagnétique, au moins deux longueurs d'onde ou deux plages de longueurs d'onde, - (b) l'étape de réaliser, pour chacune des longueurs d'onde ou plages de longueur d'onde une image de l'interface et de la zone, - (c) l'étape de produire des signaux électriques représentatifs de chaque image, - (d) l'étape de numériser les signaux électriques de manière à produire des données correspondant à chaque image, - (e) l'étape d'extraire des données correspondant à chaque image deux groupes de données respectivement représentatifs d'au moins une partie du corps dans la plage proche infra-rouge et dans la plage vert-bleu, - (f) l'étape de comparer les groupes de données. Les étapes (c) à (f) sont ci-après dénommées le processus de déduction de la présence d'un corps.Preamble to the description Field concerned The present invention relates to a method, a system and devices for detecting a body in an area located near an interface between two liquid and / or gaseous media, in particular of the water / air type. In the sense of the present invention "near" also means "at the interface". Problem posed The problem concerns the detection of the presence of bodies in the vicinity of a water / air interface. In addition to this main problem, there is also the discrimination between the bodies located on one side or the other of the interface and the detection of stationary bodies. The invention sets out more particularly to solve these various problems in the case, among others, of the following four applications: - alarm if a stationary body is located under the interface. For example, alarm in the case of a body submerged in water for a time considered too long, - statistical estimate of the occupation time of a monitored area. This application makes it possible to perform statistical analyzes on in particular the occupation of a swimming pool, - estimation of the trajectory of bodies, - highlighting the disappearance of a body from the monitored area. This application can be used in particular in the case of monitoring swimmers by the sea. Prior art There are different methods of detecting the presence of bodies in a certain area. They generally use several video sensors installed below the interface level. Although effective, these techniques are not always easy to use. They can also raise maintenance problems, especially in swimming pools without technical galleries. Furthermore, to resolve these problems, the applicant filed on December 6, 2000 patent No. FR 00/15803 entitled "method, system and device for detecting a body near a water / air interface". The device written in this patent uses principles of detection and localization of bodies relative to the interface different from those which are the subject of the present application. Solution The present invention solves the problem of detecting bodies located in the vicinity of a water / air type interface by proposing a method and a system making it possible to evaluate the position of a body relative to an interface, particularly of water type. / air, to discriminate moving bodies from stationary bodies, to generate alerts, to compile statistics, to give elements of trajectography and to allow the detection of entries or exits of bodies in the monitored area. Method The invention relates to a method for detecting a body in an area located near an interface between two liquid and / or gaseous media, especially of the water / air type. The body is lit by electromagnetic radiation comprising at least two different wavelengths, in particular situated in ranges corresponding to the near infrared on the one hand and to green-blue on the other hand. The media have different absorption coefficients depending on the wavelengths of the electromagnetic radiation. The method comprises the following steps: - (a) the step of choosing from the wavelengths of the electromagnetic radiation, at least two wavelengths or two wavelength ranges, - (b) the step of perform, for each wavelength or wavelength range, an image of the interface and of the area, - (c) the step of producing electrical signals representative of each image, - (d) the step of digitizing the electrical signals so as to produce data corresponding to each image, - (e) the step of extracting data corresponding to each image two groups of data respectively representative of at least one part of the body in the range near infrared and in the green-blue range, - (f) the step of comparing the groups of data. Steps (c) to (f) are hereinafter referred to as the process of deducing the presence of a body.
Il résulte de la combinaison des traits techniques qu'il est ainsi possible de détecter la présence d'un corps et/ou de déterminer la position du corps détecté par rapport à l'interface, en discriminant entre un corps situé entièrement sous l'interface et un corps situé au moins en partie au-dessus de l'interface. De préférence selon l'invention, le procédé comprend en outre l'étape d'intégrer dans le temps les résultats de l'étape de comparaison des groupes de données. De préférence selon l'invention, le procédé comprend en outre l'étape de déclencher une alarme si un corps de taille humaine est détecté sous l'interface pendant un temps supérieur à un seuil déterminé. De préférence selon l'invention, le procédé est tel que pour extraire des données correspondant à chaque image deux groupes de données respectivement représentatifs d'au moins une partie du corps dans la plage proche infra-rouge et dans la plage vert-bleu, on génère des calottes (au sens de la présente invention) . De préférence selon l'invention, le procédé comprend en outre les étapes suivantes : l'étape d'associer à chaque calotte des caractéristiques, - l'étape de déduire la présence d'un groupe de données représentatif d'au moins une partie du corps si les caractéristiques dépassent un seuil SC prédéterminé. De préférence selon l'invention, le procédé est tel que pour comparer les groupes de données, on recherche les données représentatives d'au moins une partie du corps dans la plage vert-bleu pour lesquelles il n'y a pas, dans un voisinage géométrique déterminé, de données correspondantes représentatives d'au moins une partie du corps dans la plage proche infra-rouge. Ainsi en cas de recherche positive, on peut conclure que le corps est situé sous l'interface. De préférence selon l'invention, le procédé est tel que pour comparer les groupes de données, on recherche les données représentatives d'au moins une partie du corps dans la plage vert-bleu pour lesquelles il y a, dans un voisinage géométrique déterminé, des données correspondantes représentatives d'au moins une partie du corps dans la plage infra-rouge. Ainsi en cas de recherche positive, on peut conclure que le corps est situé au moins en partie au-dessus de l'interface. Selon une variante de réalisation de l'invention, le procédé est plus particulièrement destiné à discriminer entre un corps stationnaire et un corps en mouvement. De préférence dans le cas de cette variante de réalisation, pour intégrer dans le temps les résultats de la comparaison des groupes de données, le procédé comprend en outre les étapes suivantes : - l'étape d'itérer à intervalles de temps déterminés le processus de déduction de la présence du corps,It results from the combination of technical features that it is thus possible to detect the presence of a body and / or to determine the position of the detected body with respect to the interface, by discriminating between a body located entirely under the interface. and a body located at least partially above the interface. Preferably according to the invention, the method further comprises the step of integrating over time the results of the step of comparing the groups of data. Preferably according to the invention, the method further comprises the step of triggering an alarm if a human-sized body is detected under the interface for a time greater than a determined threshold. Preferably according to the invention, the method is such that to extract data corresponding to each image two groups of data respectively representative of at least one part of the body in the near infrared range and in the green-blue range, we generates caps (within the meaning of the present invention). Preferably according to the invention, the method further comprises the following steps: the step of associating characteristics with each cap, - the step of deducing the presence of a group of data representative of at least part of the body if the characteristics exceed a predetermined SC threshold. Preferably according to the invention, the method is such that to compare the groups of data, one searches for the data representative of at least one part of the body in the green-blue range for which there is not, in a neighborhood determined geometric, corresponding data representative of at least one part of the body in the near infrared range. So in case of a positive search, we can conclude that the body is located under the interface. Preferably according to the invention, the method is such that to compare the groups of data, one searches for the data representative of at least one part of the body in the green-blue range for which there is, in a determined geometric neighborhood, corresponding data representative of at least one part of the body in the infrared range. Thus in the event of a positive search, we can conclude that the body is located at least in part above the interface. According to an alternative embodiment of the invention, the method is more particularly intended to discriminate between a stationary body and a moving body. Preferably in the case of this alternative embodiment, in order to integrate the results of the comparison of the groups of data over time, the method further comprises the following steps: the step of iterating at specific time intervals the process of deduction of the presence of the body,
- l'étape de calculer le nombre de fois où le corps est détecté pendant une période de temps déterminée Tl, - l'étape de discriminer, en un point de la zone, entre les corps qui sont présents un nombre de fois supérieur à un seuil déterminé SI (ces corps sont ci-après désignés les corps stationnaires) et les corps qui sont présents un nombre de fois inférieur au seuil déterminé SI (ces corps sont ci-après désignés les corps en mouvement) . II est ainsi possible de détecter la présence d'un corps stationnaire situé entièrement sous l'interface et de déclencher en conséquence une alarme. Système L'invention concerne également un système pour détecter un corps dans une zone située à proximité d'une interface entre deux milieux liquides et/ou gazeux, notamment du type eau/air. Le corps est éclairé par un rayonnement électromagnétique comprenant au moins deux longueurs d'onde différentes, notamment situées dans des plages correspondant au proche infra-rouge d'une part et au vert-bleu d'autre part. Les milieux ont des coefficients d'absorption différents en fonction des longueurs d'onde du rayonnement électromagnétique. Le système comprend : - (a) des moyens de sélection pour choisir parmi les longueurs d'onde du rayonnement électromagnétique, au moins deux longueurs d'onde ou deux plages de longueurs d'onde, - (b) des moyens de prise de vues pour réaliser, pour chacune des longueurs d'onde ou plages de longueur d'onde, une image de l'interface et de la zone, (c) des moyens de conversion pour produire des signaux électriques représentatifs de chaque image, - (d) des moyens de numérisation pour numériser les signaux électriques de manière à produire des données correspondant à chaque image, (e) des moyens de traitement informatique pour extraire des données correspondant à chaque image deux groupes de données respectivement représentatifs d'au moins une partie du corps dans la plage proche infra-rouge et dans la plage vert- bleu, - (f) des moyens de calcul pour comparer les groupes de données. Les moyens de conversion, les moyens de numérisation, les moyens de traitement informatique, les moyens de calcul sont ci-après dénommés les moyens de déduction de la présence d'un corps.- the step of calculating the number of times the body is detected during a determined period of time T1, - the step of discriminating, at a point in the zone, between the bodies which are present a number of times greater than one determined threshold SI (these bodies are hereinafter designated the stationary bodies) and the bodies which are present a number of times less than the determined threshold SI (these bodies are hereinafter designated the bodies in movement). It is thus possible to detect the presence of a stationary body located entirely under the interface and to consequently trigger an alarm. System The invention also relates to a system for detecting a body in an area located near an interface between two liquid and / or gaseous media, in particular of the water / air type. The body is lit by electromagnetic radiation comprising at least two different wavelengths, in particular situated in ranges corresponding to the near infrared on the one hand and to green-blue on the other hand. The media have different absorption coefficients depending on the wavelengths of the electromagnetic radiation. The system includes: - (a) selection means for choosing from the wavelengths of the electromagnetic radiation, at least two wavelengths or two wavelength ranges, - (b) means for taking pictures to produce, for each of the wavelengths or wavelength ranges, an image of the interface and of the area, (c) conversion means for producing electrical signals representative of each image, - (d) digitization means for digitizing the electrical signals so as to produce data corresponding to each image, (e) computer processing means for extracting data corresponding to each image two groups of data respectively representative of at least one part of the body in the near range infrared and in the green-blue range, - (f) means of calculation for comparing the groups of data. The means of conversion, the means of digitization, the means of computer processing, the means of calculation are hereinafter called the means of deducing the presence of a body.
Il résulte de la combinaison des traits techniques qu'il est ainsi possible de détecter la présence d'un corps et/ou de déterminer la position du corps détecté par rapport à l'interface, en discriminant entre un corps situé sous l'interface et un corps situé au moins en partie au-dessus de l'interface. De préférence selon l'invention, le système comprend en outre des moyens d'intégration pour intégrer dans le temps les résultats des moyens de calcul des groupes de données. De préférence selon l'invention, le système comprend en outre des moyens d'activation pour actionner une alarme si un corps de taille humaine est détecté sous l'interface pendant un temps supérieur à un seuil déterminé. De préférence selon l'invention, le système est tel que les moyens de traitement informatique permettent de générer des calottes (au sens de la présente invention) . De préférence selon l'invention, le système est tel que les moyens de traitement informatique permettent : - d'associer à chaque calotte des caractéristiques, - de déduire la présence d'un groupe de données représentatif d' au moins une partie du corps si les caractéristiques dépassent un seuil SC prédéterminé. De préférence selon l'invention, le système est tel que les moyens de calcul permettent de rechercher les données représentatives d' u moins une partie du corps dans la plage vert-bleu pour lesquelles il n'y a pas, dans un voisinage géométrique déterminé, de données correspondantes représentatives d'au moins une partie du corps dans la plage proche infra-rouge. Il résulte de la combinaison des traits techniques qu'en cas de recherche positive, on peut conclure que le corps est situé sous l'interface. De préférence selon l'invention, le système est tel que les moyens de calcul permettent de rechercher les données représentatives d'au moins une partie dudit corps dans la plage vert-bleu pour lesquelles il y a, dans un voisinage géométrique déterminé, des données correspondantes représentatives d'au moins une partie dudit corps dans la plage proche infra-rouge. Il résulte de la combinaison des traits techniques qu'en cas de recherche positive, on peut conclure que ledit corps est situé au moins en partie au-dessus de l'interface. Dans le cas d'une variante de réalisation de l'invention, le système est plus particulièrement destiné à discriminer entre un corps stationnaire et un corps en mouvement. De préférence dans le cas de cette variante de réalisation, le système est tel que les moyens d'intégration pour intégrer dans le temps les résultats des moyens de calcul permettent : - d'itérer à intervalles de temps déterminés la mise en œuvre des moyens de déduction de la présence dudit corps ;It results from the combination of technical features that it is thus possible to detect the presence of a body and / or to determine the position of the detected body with respect to the interface, by discriminating between a body located under the interface and a body located at least partially above the interface. Preferably according to the invention, the system further comprises integration means for integrating over time the results of the means of calculating the data groups. Preferably according to the invention, the system further comprises activation means for activating an alarm if a body of human size is detected under the interface for a time greater than a determined threshold. Preferably according to the invention, the system is such that the computer processing means make it possible to generate caps (within the meaning of the present invention). Preferably according to the invention, the system is such that the computer processing means make it possible: - to associate characteristics with each cap, - to deduce the presence of a group of data representative of at least one part of the body if the characteristics exceed a predetermined threshold SC. Preferably according to the invention, the system is such that the calculation means make it possible to search for data representative of at least one part of the body in the green-blue range for which there is not, in a determined geometric neighborhood , corresponding data representative of at least one part of the body in the near infrared range. It results from the combination of technical features that in the event of a positive search, we can conclude that the body is located under the interface. Preferably according to the invention, the system is such that the calculation means make it possible to search for the data representative of at least one part of said body in the green-blue range for which there is, in a determined geometric neighborhood, data corresponding representative of at least part of said body in the near infrared range. It results from the combination of technical features that in the event of a positive search, it can be concluded that said body is located at least partially above the interface. In the case of an alternative embodiment of the invention, the system is more particularly intended to discriminate between a stationary body and a moving body. Preferably in the case of this variant embodiment, the system is such that the integration means for integrating over time the results of the calculation means make it possible: - to iterate at determined time intervals the implementation means for deducing the presence of said body;
- de calculer le nombre de fois où le corps est détecté pendant une période de temps déterminée Tl ;- calculate the number of times the body is detected during a determined period of time T1;
- de discriminer, en un point de ladite zone, entre les corps qui sont présents un nombre de fois supérieur à un seuil déterminé SI (ces corps sont ci-après désignés les corps stationnaires) et les corps qui sont présents un nombre de fois inférieur au seuil déterminé SI (ces corps sont ci-après désignés les corps en mouvement) . II est ainsi possible de détecter la présence d'un corps stationnaire situé entièrement sous l'interface. Par conséquent, il est ainsi possible de déclencher une alarme. Description détaillée D'autres caractéristiques et avantages de l'invention apparaîtront à la lecture de la description de variantes de réalisation de l'invention données à titre d'exemple indicatif et non limitatif, et des figures ci-après : - figures la, 1b, le qui représentent dans l'ordre une image, une image superposée d'un pavage, une image composée d'un pavage de pixel sur lesquels on a indiqué leur valeur, de manière à illustrer la notion de pavage de pixels, - figures 2a, 2b, 2c qui représentent une image composée d'un pavage de pixels sur lesquels on a indiqué leur valeur, de manière à illustrer la notion d'ensemble connexe de pixels, - figures 3a, 3b, 4a, 4b qui représentent une image composée d'un pavage de pixels sur lesquels on a indiqué leur valeur, de manière à illustrer la notion de niveau d'une calotte, - figures 5 et β qui représentent, dans le cas d'une piscine, une vue générale du système permettant la détection de corps situés au voisinage d'une interface de type eau/air, notamment la détection et la surveillance des nageurs, - figure 7 qui représente un organigramme des moyens de traitement informatique, - figure 8 représente une vue générale schématique du système selon l'invention. Avant de décrire le système et les différentes parties qui le composent en se référant aux figures 5, 6, 7 et 8, on explicitera certains termes techniques en se référant aux figures la à . Définitions Les définitions ci-après explicitent les termes techniques employés dans la présente invention. Pixel, Valeur de pixel On appelle pixel : une zone élémentaire d'une image obtenue en créant un pavage, généralement régulier, de ladite image. Lorsque l'image provient d'un capteur tel qu'une caméra vidéo, ou une caméra thermique ou acoustique, on peut générale- ment associer une valeur à ce pixel : la couleur ou le niveau de gris pour une image vidéo. Exemple : On a représenté sur la figure la une image 101 (symbolisée par un homme, nageant à la surface d'une piscine, dont les contours ne sont pas parfaitement visibles) . Sur la figure lb, on a superposé à cette image un pavage 102 de pixels 103. On a représenté sur la figure le un pavage sur lequel on a indiqué les valeurs des pixels. Pixels adjacents Deux pixels du pavage sont dits adjacents si leurs bords ou leurs coins se touchent. Chemin sur pavage Un chemin sur le pavage est un ensemble ordonné et fini de pixels où chaque pixel est adjacent à son suivant (au sens de l'ordonnancement) . La taille d'un chemin est donnée par le nombre de pixels le constituant. Pixels jointifs Deux pixels sont dits jointifs lorsque le chemin le plus court débutant à l'un et finissant à l'autre est de taille inférieure à un nombre déterminé de pixels. Ensemble connexe de pixels Un ensemble de pixels est dit connexe si pour chaque paire de pixels de l'ensemble, il existe un chemin débutant à l'un et finissant à l'autre, ce chemin étant constitué de pixels de l'ensemble. Exemple : La figure 2a représente un pavage 202 de 16 pixels 203, parmi lesquels on a mis en évidence 3 pixels, dénommés A, B et C. On peut remarquer que les pixels A et B sont adjacents et que les pixels B et C sont adjacents. Il existe donc un chemin (A->B->C) qui relie ces pixels. L'ensemble de pixels {A, B, C} est donc connexe. Sur la figure 2b, on a également représenté un pavage- to discriminate, at a point in said zone, between the bodies which are present a number of times greater than a determined threshold SI (these bodies are hereinafter designated the stationary bodies) and the bodies which are present a number of times less at the determined threshold SI (these bodies are hereafter designated the bodies in movement). It is thus possible to detect the presence of a stationary body located entirely under the interface. Therefore, it is thus possible to trigger an alarm. Detailed description Other characteristics and advantages of the invention will appear on reading the description of alternative embodiments of the invention given by way of indicative and non-limiting example, and the figures below: - Figures la, 1b , the which represent in order an image, an image superimposed by a tiling, an image composed of a tiling of pixels on which their value has been indicated, so as to illustrate the concept of tiling of pixels, - Figures 2a , 2b, 2c which represent an image composed of a tiling of pixels on which their value has been indicated, so as to illustrate the concept of connected set of pixels, - Figures 3a, 3b, 4a, 4b which represent a composite image a tiling of pixels on which their value has been indicated, so as to illustrate the concept of level of a cap, - Figures 5 and β which represent, in the case of a swimming pool, a general view of the system allowing the detection of bodies located in the vo drawing of a water / air type interface, in particular the detection and monitoring of swimmers, - FIG. 7 which represents a flowchart of the computer processing means, - Figure 8 shows a general schematic view of the system according to the invention. Before describing the system and the various parts which compose it with reference to FIGS. 5, 6, 7 and 8, some technical terms will be explained with reference to FIGS. Definitions The definitions below explain the technical terms used in the present invention. Pixel, Pixel value Pixel is called: an elementary area of an image obtained by creating a tiling, generally regular, of said image. When the image comes from a sensor such as a video camera, or a thermal or acoustic camera, it is generally possible to associate a value with this pixel: the color or the gray level for a video image. Example: FIG. 1a represents an image 101 (symbolized by a man, swimming on the surface of a swimming pool, the contours of which are not perfectly visible). In FIG. 1b, a tiling 102 of pixels 103 has been superimposed on this image. A tiling has been shown in the figure on which the values of the pixels have been indicated. Adjacent pixels Two pixels of the tiling are said to be adjacent if their edges or corners touch. Path on tiling A path on tiling is an ordered and finite set of pixels where each pixel is adjacent to its next (in the sense of the ordering). The size of a path is given by the number of pixels making it up. Joining pixels Two pixels are said to be contiguous when the shortest path starting at one and ending at the other is less than a determined number of pixels. Connected set of pixels A set of pixels is said to be connected if for each pair of pixels in the set, there is a path starting at one and ending at the other, this path being made up of pixels of the set. Example: FIG. 2a represents a tiling 202 of 16 pixels 203, among which we have highlighted 3 pixels, called A, B and C. It can be noted that the pixels A and B are adjacent and that the pixels B and C are adjacent. There is therefore a path (A->B-> C) which connects these pixels. The set of pixels {A, B, C} is therefore connected. In FIG. 2b, a tiling has also been shown.
202 de 16 pixels 203, désignés par les lettres A à P. Si on sélectionne l'ensemble de pixels {A, B, C, E, F, I}, on peut constater que les pixels A et B sont adjacents, que les pixels B et C sont adjacents, etc Il existe donc des chemins : A -> B202 of 16 pixels 203, designated by the letters A to P. If we select the set of pixels {A, B, C, E, F, I}, we can see that the pixels A and B are adjacent, that the pixels B and C are adjacent, etc. There are therefore paths: A -> B
-> C et C-> B -> F -> E -> I. Chaque couple de pixels de l'ensemble est relié par un chemin de pixels appartenant à l'ensemble, l'ensemble de pixels {A, B, C, E, F, 1} est par conséquent connexe. Sur la figure 2c, on a représenté le même pavage 202 que sur la figure 2b, en sélectionnant l'ensemble de pixels {A, C, F, N, P} . Il existe un chemin : A->C->F qui relie les pixels A, C et F, mais il n'existe pas de chemin de pixels appartenant à l'ensemble reliant N et P, ou bien N à A. L'ensemble de pixels {A, C, F, N, P} n'est pas connexe. Par contre, l'ensemble {A, C, F} est connexe. Pixel adjacent à un ensemble Un pixel n'appartenant pas à un ensemble est dit adjacent audit ensemble lorsqu'il est jointif à au moins un pixel appartenant audit ensemble Calotte On appelle calotte sup. (resp. inf) : un ensemble connexe de pixels dont les valeurs sont supérieures (resp. infé- rieures) à une valeur prédéterminée et vérifiant la condition suivante : les valeurs des pixels adjacents à l'ensemble (non compris dans l'ensemble) sont inférieures ou égales (respective- ment, supérieures ou égales) à ladite valeur prédéterminée, de sorte que les valeurs des pixels situés dans ledit ensemble sont supérieures (respectivement inférieures) aux valeurs des pixels adjacents à l'ensemble. Niveau d 'une calotte On appelle niveau d'une calotte sup. ou inf. ladite valeur prédéterminée. Exemple : Les figures 3a, 3b, 4a, et 4b représentent des images composées de pavages 302 (resp. 402) de pixels 303 (resp. 403) sur lesquels on a indiqué leurs valeurs. La figure 3a représente (à l'intérieur 304 du trait fort 305) un ensemble de 4 pixels. Cet ensemble a les propriétés suivantes : - il est connexe au sens de la définition donnée, - les valeurs de tous les pixels de l'ensemble sont supérieures à 1, - les (douze) pixels adjacents à l'ensemble ont pour certains une valeur supérieure à 1. L'ensemble de pixels considéré n'est donc pas une calotte sup. de niveau 1. Par contre, cet ensemble de pixels a les propriétés suivantes : - il est connexe au sens de la définition donnée, - les valeurs de tous les pixels de l'ensemble sont supérieures à 2, - les (douze) pixels jointifs à l'ensemble ont tous une valeur inférieure ou égale à 2. Cet ensemble de pixels est donc une calotte sup. de niveau 2. La figure 3b représente un ensemble 306 de huit pixels présentant les propriétés suivantes : - il est connexe au sens de la définition donnée, - les valeurs de tous les pixels de l'ensemble sont supérieures à 1, - les (dix-huit) pixels jointifs à l'ensemble ont tous une valeur inférieure ou égale à 1. L'ensemble de pixels considéré est donc une calotte sup. de niveau 1. La figure 4a représente un pavage 402 de pixels 403.-> C and C-> B -> F -> E -> I. Each pair of pixels in the set is linked by a path of pixels belonging to the set, the set of pixels {A, B, C , E, F, 1} is therefore connected. In FIG. 2c, the same tiling 202 has been shown as in FIG. 2b, by selecting the set of pixels {A, C, F, N, P}. There is a path: A->C-> F which connects the pixels A, C and F, but there is no path of pixels belonging to the set connecting N and P, or else N to A. L ' set of pixels {A, C, F, N, P} is not connected. On the other hand, the set {A, C, F} is connected. Pixel adjacent to a set A pixel which does not belong to a set is said to be adjacent to said set when it is joined to at least one pixel belonging to said set. (resp. inf): a connected set of pixels whose values are higher (resp. inf- ) to a predetermined value and satisfying the following condition: the values of the pixels adjacent to the set (not included in the set) are less than or equal (respectively, greater than or equal) to the said predetermined value, so that the values of the pixels located in said set are greater (respectively lower) than the values of the pixels adjacent to the set. Level of a cap We call level of a top cap. or inf. said predetermined value. Example: FIGS. 3a, 3b, 4a, and 4b represent images composed of tilings 302 (resp. 402) of pixels 303 (resp. 403) on which their values have been indicated. FIG. 3a represents (inside 304 of the strong line 305) a set of 4 pixels. This set has the following properties: - it is connected in the sense of the definition given, - the values of all the pixels of the set are greater than 1, - the (twelve) pixels adjacent to the set have for some a value greater than 1. The set of pixels considered is therefore not an upper cap. level 1. However, this set of pixels has the following properties: - it is connected in the sense of the definition given, - the values of all the pixels in the set are greater than 2, - the (twelve) contiguous pixels to the set all have a value less than or equal to 2. This set of pixels is therefore an upper cap. level 2. FIG. 3b represents a set 306 of eight pixels having the following properties: - it is connected in the sense of the definition given, - the values of all the pixels of the set are greater than 1, - the (eighteen) pixels contiguous to the set all have a value less than or equal to 1. The set of pixels considered is therefore an upper cap. of level 1. FIG. 4a represents a tiling 402 of pixels 403.
Dans ce pavage 402 on a isolé par un trait fort 405 un ensemble 404 de dix pixels répartis en deux zones 404 a et 404b. Cet ensemble de pixels 404 présente les propriétés suivantes : - il n'est pas connexe au sens de la définition don- née, - les valeurs de tous les pixels sont supérieures à 1 - les (vingt-cinq) pixels jointifs à l'ensemble ont tous une valeur inférieure ou égale à 1. Les dix pixels de cet ensemble non connexe ne consti- tuent donc pas une calotte sup. de niveau 1. La figure 4b représente un ensemble 406 de douze pixels présentant les propriétés suivantes : - il est connexe au sens de la définition donnée, - les valeurs des pixels ne sont pas toutes supérieu- res à 1, - les (vingt-quatre) pixels jointifs à l'ensemble ont tous une valeur inférieure ou égale à 1. L'ensemble de pixels considéré n'est donc pas une calotte sup. de niveau 1. Caractéristique (s) associée (s) à une calotte On appelle caractéristique (s) associée (s) à une calotte : une ou des valeurs obtenues par des opérations arithmétiques et/ou logiques prédéfinies à partir des valeurs des pixels de la calotte, et/ou des positions des pixels dans le pavage, et/ou du niveau de la calotte. Par exemple, une opération arithmétique pourrait consister à utiliser la somme des écarts entre la valeur de chaque pixel de la calotte et le niveau de la calotte, ou encore la taille (nombre de pixels) de ladite calotte. Calotte réalisée On appelle calotte sup. réalisée (resp. calotte inf. réalisée) : une calotte sup. (resp. inf.) dont les caractéristiques associées sont dans une plage de valeur déterminée. Voisinage géométrique On va maintenant décrire le système et les différentes parties qui le composent en se référant aux figures 5,6 et 7. La figure 5 représente une vue schématique du système permettant la détection de corps situés au voisinage d'une interface de type eau/air. Les images vert-bleu 501 et proche infra-rouge 502 n'étant pas forcément prises depuis le même point d'observation, avantageusement les données ou les images pourront être replacées dans un repère commun virtuel 503. Le repère virtuel pourra correspondre à la surface de l'eau 504, de telle sorte qu'un point de la surface de l'eau 505, vu par la caméra vert- bleu 506 et vu par la caméra proche infra-rouge 507, sera au même endroit 508 dans le repère commun virtuel. De cette façon, à deux points proches de l'espace réel, correspondront des points proches dans ce repère commun virtuel. La notion de repère géométrique correspondra à la notion de proximité dans le repère commun virtuel . La figure 6 représente, dans le cas d'une piscine, une vue générale du système permettant la détection de corps situés au voisinage d'une interface de type eau/air, notamment la détection et la surveillance des nageurs. Le système selon l'invention comprend des moyens, ci- après décrits, pour détecter un corps 601 dans une zone 603 située à proximité d'une interface 602 entre deux milieux liquides 604 et/ou gazeux 605 notamment du type eau/air ; ledit corps étant éclairé par un rayonnement électromagnétique comprenant au moins deux longueurs d'onde différentes, notamment situées dans des plages correspondant au proche infra-rouge d'une part et au vert-bleu d'autre part ; lesdits milieux ayant des coefficients d'absorption différents en fonction des longueurs d'onde du rayonnement électromagnétique. Au sens de la présente invention "à proximité" désigne également "à l'interface ". Le système comprend en outre les moyens : Une caméra vidéo 606a, équipée d'un filtre permettant de réaliser au moins une image vidéo dans la plage de longueur d'onde de 300 à 700 nm (plage dénommée vert-bleu par la suite) . Une caméra vidéo 606b, équipée d'un filtre permettant de réaliser au moins une image vidéo dans la plage de longueur d'onde de 780 à 1100 nm (plage dénommée proche infra-rouge par la suite) . Ces caméras permettent de réaliser des images vidéo de ladite interface 602 et de ladite zone 603, à partir d'au moins deux points d'observation 607a et 607b. Ces images sont représentées par des signaux électriques 608a et 608b. Chacun des points d'observation 607a et 607b est situé d'un côté de ladite interface 602. En l'espèce, les points d'observation 607a et 607b sont situés au-dessus de la piscine.In this tiling 402, a strong line 405 has isolated a set 404 of ten pixels distributed in two zones 404 a and 404b. This set of pixels 404 has the following properties: - it is not connected within the meaning of the definition given, - the values of all the pixels are greater than 1 - the (twenty-five) pixels joined to the set all have a value less than or equal to 1. The ten pixels of this unrelated set therefore do not constitute an upper cap. of level 1. FIG. 4b represents a set 406 of twelve pixels having the following properties: - it is connected in the sense of the definition given, - the values of the pixels are not all greater than 1, - the (twenty- four) pixels joined to the set all have a value less than or equal to 1. The set of pixels considered is therefore not an upper cap. of level 1. Characteristic (s) associated with a skullcap We call characteristic (s) associated (s) with a skullcap: one or more values obtained by arithmetic and / or logical operations predefined from the pixel values of the cap, and / or the positions of the pixels in the tiling, and / or the level of the cap. For example, an arithmetic operation could consist in using the sum of the differences between the value of each pixel of the cap and the level of the cap, or even the size (number of pixels) of said cap. Shell made We call shell upper. completed (resp. lower cap completed): an upper cap. (resp. inf.) whose associated characteristics are within a determined value range. Geometric neighborhood We will now describe the system and the different parts that make it up with reference to Figures 5,6 and 7. Figure 5 represents a schematic view of the system allowing the detection of bodies located in the vicinity of a water type interface /air. Since the green-blue 501 and near infrared 502 images are not necessarily taken from the same observation point, the data or the images can advantageously be replaced in a virtual common reference frame 503. The virtual reference frame may correspond to the surface of water 504, so that a point on the surface of water 505, seen by the green-blue camera 506 and seen by the near infrared camera 507, will be in the same place 508 in the common coordinate system virtual. In this way, two points close to real space will correspond to close points in this virtual common landmark. The notion of geometric coordinate system will correspond to the concept of proximity in the virtual common coordinate system. FIG. 6 represents, in the case of a swimming pool, a general view of the system allowing the detection of bodies located in the vicinity of a water / air type interface, in particular the detection and monitoring of swimmers. The system according to the invention comprises means, hereinafter described, for detecting a body 601 in a zone 603 located near an interface 602 between two liquid media 604 and / or gaseous 605 in particular of the water / air type; said body being illuminated by electromagnetic radiation comprising at least two different wavelengths, in particular situated in ranges corresponding to the near infrared on the one hand and to green-blue on the other hand; said media having different absorption coefficients as a function of the wavelengths of the electromagnetic radiation. In the sense of the present invention "near" also means "at the interface". The system further comprises the means: A video camera 606a, equipped with a filter making it possible to produce at least one video image in the wavelength range of 300 to 700 nm (range called green-blue below). A video camera 606b, equipped with a filter making it possible to produce at least one video image in the wavelength range from 780 to 1100 nm (range termed near infrared thereafter). These cameras make it possible to produce video images of said interface 602 and of said zone 603, from at least two observation points 607a and 607b. These images are represented by electrical signals 608a and 608b. Each of the observation points 607a and 607b is located on one side of said interface 602. In this case, the observation points 607a and 607b are located above the swimming pool.
Les caméras vidéo 606a et 606b et leurs boîtiers sont aériens, ils sont à l'air libre. Ledit système comprend en outre des moyens de conversion numérique 609 pour produire des données numériques à partir des signaux électriques 608a et 608b représentatifs des images vidéo vert-bleu et proche infra-rouge. Avantageusement, lorsque ledit corps 601 est éclairé par de la lumière produisant des reflets sur ladite interface, les caméras 606a et 606b sont équipées de filtres polarisant 611a et 611b éliminant au moins en partie les reflets de la lumière sur ladite interface dans lesdites images . Cette variante de réalisation est particulièrement adaptée dans le cas d'une piscine reflétant les rayons du soleil ou ceux d'un éclairage artificiel. Ledit système comprend en outre des moyens de traitement informatique 700 décrits ci-dessous. La figure 7 représente un organigramme des moyens de traitement informatique 700. Les moyens de traitement informatique 700 permettent de discriminer les données correspondant aux images vidéo vert- bleu d'une partie d'un corps réel (figure la) de celles correspondant aux images vidéo vert-bleu apparentes (figure lb) générée par ladite interface 602. Les moyens de traitement informatique 700 permettent également de discriminer les données correspondant aux images vidéo proche infra-rouge d'une partie d'un corps réel (figure la) de celles correspondant aux images vidéo proche infra-rouge apparentes (figure lb) générée par ladite interface 602. Lesdits moyens de traitement informatique 700 comprennent des moyens de calcul, notamment un processeur 701, et une mémoire 702. Les moyens de traitement informatique 700 comprennent des moyens d'extraction 712 permettant d'extraire un groupe de données représentatives d'au moins une partie du corps dans la plage proche infra-rouge. Les moyens de traitement informatique 700 comprennent, en outre, des moyens d'extraction 713 permettant d'extraire un groupe de données représentatives d'au moins une partie du corps dans la plage vert-bleu. Dans une variante de réalisation, pour extraire des groupes de données représentatifs d'au moins une partie du corps dans la plage proche infra-rouge et dans la plage vert-bleu, les moyens d'extraction 712 et 713 - génèrent des calottes, - associent à chaque calotte des caractéristiques, - déduisent la présence d'un groupe de données représentatif d'au moins une partie du corps si les caractéristiques dépassent un seuil SC prédéterminé. Un exemple de caractéristique associée à une calotte pourra être son aire définie par le nombre de pixels la constituant. Une autre caractéristique associée à une calotte peut être son contraste défini comme étant la somme des écarts entre la valeur de chaque pixel de la calotte et le niveau de la calotte. Un exemple de groupe de données représentatif d'une partie d'un corps pourra alors être une calotte ayant un contraste supérieur à un seuil SC et une aire comprise entre un seuil TailleMin et un seuil TailleMax représentatifs des dimensions minimales et maximales des parties du corps recherchées . Dans une variante de réalisation concernant les piscines, les moyens informatiques 700 permettent de sélectionner parmi les groupes de données extraits, ceux ne correspondant pas à une partie de nageur. Avantageusement le système comprend des moyens permettant d'éliminer les calottes correspondant aux reflets, aux lignes d'eau, aux tapis ainsi qu'à tout objet potentiellement présent dans une piscine et ne correspondant pas à une partie de nageur. Des exemples de sélection pourront se faire par calcul du niveau des calottes, qui doivent être inférieurs à un seuil SR correspondant au niveau de gris moyen des reflets, par calcul de l'alignement des calottes, correspondant à la position habituelle des lignes d'eau, par estimation de la forme des calottes qui ne doit pas être rectangulaire afin d'éliminer les tapis. Pour extraire des groupes de données représentatifs d' au moins une partie du corps dans la plage proche infra-rouge et dans la plage vert-bleu, les moyens d'extraction 712 et 713 pourront procéder autrement qu'au moyen de l'extraction de calottes. Par exemple, les moyens d'extraction 712 et 713 pourront extraire des groupes de pixels partageant une ou plusieurs propriétés prédéterminées, et ensuite associer à chaque groupes de pixels des caractéristiques, et déduire la présence d'un groupe de données représentatif d'au moins une partie du corps si les caractéristiques dépassent un seuil SC prédéterminé. La ou les propriétés prédéterminées pourront par exemple être choisies de manière à exclure l'apparence de l'interface eau/air dans l'image. Par exemple, dans le cas des images infra-rouge, on pourra extraire les groupes de pixels dont la luminosité est bien supérieure à la luminosité moyenne de l'image de l'interface et dont la taille est relative à celle d'un corps humain. Lesdits moyens de traitement informatique 700 comprennent en outre des moyens de comparaison 714, pour comparer lesdits groupes de données. Dans une variante de réalisation, lesdits moyens de comparaison 714, recherchent les données représentatives d'au moins une partie dudit corps dans la plage vert-bleu pour lesquelles il n'y a pas, dans un voisinage de comparaison géométrique, de données correspondantes représentatives d'au moins une partie dudit corps dans la plage proche infra-rouge. De sorte qu'en cas de recherche positive, on peut conclure que ledit corps est situé sous l'interface. Dans le cas particulier de la localisation d'un nageur par rapport à la surface de l'eau, on recherche, dans un voisinage de comparaison géométrique, par exemple un voisinage circulaire de rayon 50 cm, centré sur le centre de gravité des calottes extraites dans l'image vert-bleu, des calottes extraites dans l'image proche infra-rouge. Si la recherche est négative, le nageur est considéré comme étant sous la surface de l'eau. Pour comparer lesdits groupes de données, on recherche, les données représentatives d'au moins une partie dudit corps dans la plage vert-bleu pour lesquelles il y a, dans un voisinage de comparaison géométrique, des données correspondantes représentatives d'au moins une partie dudit corps dans la plage proche infra-rouge. De sorte qu'en cas de recherche positive, on peut conclure que ledit corps est situé au moins en partie au-dessus de l'interface. Dans le cas particulier de la localisation d'un nageur par rapport à la surface de l'eau, on recherche, dans un voisinage de comparaison géométrique, par exemple un voisinage circulaire de rayon 50 cm, centré sur le centre de gravité des calottes extraites dans l'image vert-bleu, des calottes extraites dans l'image proche infra-rouge. Si la recherche est positive, le nageur est considéré comme étant au moins en partie au-dessus de la surface de l'eau. Dans une variante de réalisation, toujours pour la localisation d'un nageur par rapport à l'interface eau/air, on apparie les calottes extraites dans l'image vert-bleu et celles extraites dans l'image proche infra-rouge si la distance la plus courte (entre les deux pixels les plus proches) est inférieure à 30 cm. Les calottes de l'image vert-bleu non appariées seront alors considérées comme étant un nageur sous la surface de l'eau. Les calottes de l'image vert-bleu appariées seront considérées comme des nageurs en partie au-dessus de la surface de l'eau. Le voisinage de comparaison géométrique n' est pas nécessairement déterminé. Dans une variante de réalisation, on peut définir le voisinage de comparaison géométrique relatif aux calottes respectivement infra-rouge et vert-bleu, en fonction de considérations géométriques relatives aux positions desdites calottes et éventuellement aussi en fonction de considérations géométriques propres à l'environnement notamment l'orientation des caméras par rapport à l'interface ou l'orientation dans les images de la normale à l'interface. Les calottes issues des caméras infra-rouge étant relatives aux parties de corps situées au-dessus de l'interface, on cherchera les calottes vert-bleu correspondantes dans un voisinage de comparaison géométrique calculé en fonction de l'orientation de la normale à l'interface. Dans une autre variante de réalisation, le système décrit dans la présente invention peut être utilisé en complément d'un système basé sur la stéréovision tel que celui décrit dans le brevet n° FR 00/15803. Dans le cas où le système décrit dans le brevet n° FR 00/15803 détecte un corps sous la surface de l'eau et, - s'il y a, dans un voisinage géométrique déterminé, des données correspondantes représentatives d'au moins une partie dudit corps dans la plage proche infra-rouge, on peut conclure que ledit corps est situé au moins en partie au-dessus de l'interface, - s'il n'y a pas, dans un voisinage géométrique déterminé, des données correspondantes représentatives d'au moins une partie dudit corps dans la plage proche infra-rouge, on peut conclure que ledit corps est situé en dessous de 1' interface. Dans une autre variante de réalisation, le système décrit dans la présente invention peut avantageusement utiliser des principes de stéréovision tels que ceux décrits dans le brevet n° FR 00/15803. Dans le cas particulier de l'utilisation de plusieurs caméras vert-bleu et/ou de plusieurs caméras proche infra-rouge. Celles-ci pourront travailler en stéréovision. Dans le cas où ledit système est plus particulièrement destiné à discriminer entre un corps stationnaire (un nageur en difficulté) et un corps en mouvement (un nageur s'ébattant dans un bassin) , ledit système comprend une intégration dans le temps 703, associés à une horloge 704, pour itérer à intervalles de temps déterminés ledit processus de déduction de la présence d'un corps ci-dessus décrit. A cet effet, les images vidéo sont prises à intervalles de temps déterminés à partir dudit point d'observation. Dans ce cas, lesdits moyens de traitement informatique 700 comprennent des totalisateurs 705 pour calculer le nombre de fois où le corps est détecté pendant une période de temps déterminée Tl . Lesdits moyens de traitement informatique 700 comprennent en outre des discriminateurs 706 pour discriminer, en un point de ladite zone, entre les corps qui sont présents un nombre de fois supérieur à un seuil déterminé SI et les corps qui sont présents un nombre de fois inférieur audit seuil déterminé SI. Dans le premier cas, lesdits corps sont ci-après désignés les corps stationnaires, dans le deuxième cas lesdits corps sont ci-après désignés les corps en mouvement. Dans une variante de réalisation, lesdits moyens de traitement informatique 700 comprennent en outre des moyens pour calculer le nombre de fois où un corps est détecté comme étant stationnaire et nouveau pendant une période de temps déterminée T2. Ladite période de temps T2 est choisie supérieure à la durée des phénomènes que l'on observe, et notamment supérieure à Tl. Lesdits moyens de traitement informatique 700 comprennent en outre des moyens d'émission 716 pour émettre un signal d'alerte 711 selon les critères de détection décrits ci- dessus. Notamment, dans une variante de réalisation plus particulièrement adaptée à la surveillance des nageurs dans une piscine, le système émet un signal d'alerte 711, en présence d'un corps de taille humaine, stationnaire et situé sous l'interface. Dans une variante de réalisation dudit système, une étape supplémentaire d'intégration dans le temps pourra être avantageusement réalisée par accumulation d'images provenant d'une même caméra vert-bleu et/ou proche infra-rouge. L'image accumulée se calcule par exemple en moyennant les niveaux de gris des pixels des images successives prises sur un intervalle de temps déterminé. Une image accumulée obtenue par accumulation des images provenant d'une caméra vert-bleu sera dite image accumulée vert-bleu. De la même façon, une image accumulée obtenue par accumulation des images provenant d'une caméra proche infra-rouge sera dite image accumulée proche infra-rouge. Les moyens d'extraction 712 et 713 pourront alors également utiliser les images accumulées vert-bleu et/ou proche infrarouge. Par exemple, les moyens d'extraction 712 pourront n'extraire que les calottes de l'image vert-bleu pour lesquelles il n'y a pas, dans l'image accumulée vert-bleu, de calotte similaire située dans un voisinage. Les moyens d'extraction 712 et 713 pourront alors aussi utiliser des images composites constituées des images accumulées vert-bleu et des images vert- bleu ainsi que des images composites constituées des images accumulées proche infra-rouge et proche infra-rouge. Par exemple, les moyens d'extraction 712 pourront utiliser la différence entre l'image vert-bleu et l'image vert-bleu accumulée. On va maintenant décrire la figure 8 qui représente une vue générale schématique du système selon l'invention. Le système permet de détecter un corps 801 dans une zone 802 située à proximité d'une interface 803 entre deux milieux liquides 812 et/ou gazeux 813, notamment du type eau/air. Le corps 801 est éclairé par un rayonnement électromagnétique 804 comprenant au moins deux longueurs d'onde différentes, notamment situées dans des plages correspondant au proche infra-rouge d' une part et au vert-bleu d' autre part. Les milieux 812 et 813 ont des coefficients d'absorption différents en fonction des longueurs d'onde du rayonnement électromagnétique. Le système comprend : - (a) des moyens de sélection 814 pour choisir parmi les longueurs d'onde du rayonnement électromagnétique 804, au moins deux longueurs d'onde ou deux plages de longueur d'onde, - (b) des moyens de prise de vues 815 pour réaliser, pour chacune des longueurs d'onde ou plages de longueur d'onde, une image 805 de l'interface et de la zone, - (c) des moyens de conversion 816 pour produire des signaux électriques 6 représentatifs de chaque image 805, - (d) des moyens de numérisation 817 pour numériser les signaux électriques 806 de manière à produire des données 807 correspondant à chaque image, - (e) des moyens de traitement informatique 818 pour extraire des données 807 correspondant à chaque image 805 deux groupes de données 807 respectivement représentatifs d'au moins une partie du corps 801 dans la plage proche infra-rouge et dans la plage vert-bleu, (f) des moyens de calcul 819 pour comparer les groupes de données 807. Les moyens de conversion 816, les moyens de numérisation 817, les moyens de traitement informatique 818, les moyens de calcul 819 sont ci-après dénommés les moyens de déduction de la présence d'un corps 801. Il est ainsi possible de détecter la présence d'un corps 801 et/ou de déterminer la position du corps détecté par rapport à l'interface 803, en discriminant entre un corps 801 situé sous l'interface 803 et un corps 801 situé au moins en partie au- dessus de l'interface 803. Dans le cas de la variante de réalisation représentée sur la figure 809, le système comprend en outre des moyens d'intégration 820 pour intégrer dans le temps les résultats des moyens de calcul 819 des groupes de données 807. Dans le cas de la variante de réalisation représentée sur la figure 809, le système comprend en outre des moyens d' activâtion 821 pour actionner une alarme 808 si un corps de taille humaine est détecté sous l'interface pendant un temps supérieur à un seuil déterminé. The video cameras 606a and 606b and their housings are aerial, they are in the open air. The system further includes digital conversion means 609 for producing digital data from electrical signals 608a and 608b representative of the green-blue and near infrared video images. Advantageously, when said body 601 is illuminated by light producing reflections on said interface, the cameras 606a and 606b are equipped with polarizing filters 611a and 611b at least partially eliminating the reflections of light on said interface in said images. This variant embodiment is particularly suitable in the case of a swimming pool reflecting the rays of the sun or those of an artificial lighting. Said system further comprises computer processing means 700 described below. FIG. 7 represents a flow diagram of the computer processing means 700. The computer processing means 700 make it possible to discriminate the data corresponding to the green-blue video images of a part of a real body (FIG. 1a) from those corresponding to the video images apparent blue-green (FIG. 1b) generated by said interface 602. The computer processing means 700 also make it possible to discriminate the data corresponding to near infrared video images of a part of a real body (FIG. 1a) from those corresponding to near infrared video images apparent (FIG. 1b) generated by said interface 602. Said computer processing means 700 comprise calculation means, in particular a processor 701, and a memory 702. Computer processing means 700 comprise means of 712 to extract a group of data representative of at least one part of the body in the near infrared range uge. The computer processing means 700 further comprise extraction means 713 making it possible to extract a group of data representative of at least one part of the body in the green-blue range. In an alternative embodiment, to extract groups of data representative of at least one part of the body in the near infrared range and in the green-blue range, the extraction means 712 and 713 - generate caps, - associate characteristics with each cap, - deduce the presence of a group of data representative of at least one part of the body if the characteristics exceed a predetermined threshold SC. An example of a characteristic associated with a cap may be its area defined by the number of pixels constituting it. Another characteristic associated with a cap can be its contrast defined as the sum of the differences between the value of each pixel of the cap and the level of the cap. An example of a data group representative of a part of a body could then be a cap having a contrast greater than a threshold SC and an area between a ThinMin threshold and a MaxMax threshold representative of the minimum and maximum dimensions of the body parts wanted. In an alternative embodiment concerning swimming pools, the computer means 700 make it possible to select from the groups of extracted data, those which do not correspond to a part of the swimmer. Advantageously, the system includes means making it possible to eliminate the caps corresponding to reflections, water lines, carpets as well as any object potentially present in a swimming pool and not corresponding to a part of the swimmer. Examples of selection may be made by calculating the level of the caps, which must be below a threshold SR corresponding to the average gray level of the reflections, by calculating the alignment of the caps, corresponding to the usual position of the water lines. , by estimating the shape of the caps which should not be rectangular in order to eliminate the carpets. To extract groups of data representative of at least one part of the body in the near infrared range and in the green-blue range, the extraction means 712 and 713 may proceed other than by means of the extraction of caps. For example, the extraction means 712 and 713 can extract groups of pixels sharing one or more predetermined properties, and then associate characteristics with each group of pixels, and deduce the presence of a group of data representative of at least a body part if the characteristics exceed a predetermined SC threshold. The predetermined property or properties may for example be chosen so as to exclude the appearance of the water / air interface in the image. For example, in the case of infrared images, we can extract groups of pixels whose brightness is much higher than the average brightness of the interface image and whose size is relative to that of a human body . Said computer processing means 700 also comprise comparison means 714, for comparing said groups of data. In an alternative embodiment, said comparison means 714 search for data representative of at least part of said body in the green-blue range for which there is not, in a geometrical comparison neighborhood, corresponding representative data at least a part of said body in the near infrared range. So that in the event of a positive search, it can be concluded that said body is located under the interface. In the particular case of the location of a swimmer relative to the surface of the water, one searches, in a geometric comparison neighborhood, for example a circular neighborhood with a radius of 50 cm, centered on the center of gravity of the extracted caps in the green-blue image, caps extracted in the near infrared image. If the search is negative, the swimmer is considered to be below the surface of the water. To compare said groups of data, one searches for data representative of at least one part of said body in the green-blue range for which there is, in a geometric comparison neighborhood, corresponding data representative of at least one part of said body in the near infrared range. So that in the event of a positive search, it can be concluded that said body is located at least in part above the interface. In the particular case of the location of a swimmer relative to the surface of the water, one searches, in a geometric comparison neighborhood, for example a circular neighborhood with a radius of 50 cm, centered on the center of gravity of the extracted caps in the green-blue image, caps extracted in the near infrared image. If the search is positive, the swimmer is considered to be at least partly above the surface of the water. In an alternative embodiment, still for the location of a swimmer relative to the water / air interface, the caps extracted in the green-blue image and those extracted in the near infrared image are matched if the distance the shortest (between the two closest pixels) is less than 30 cm. The unpaired green-blue image caps will then be considered to be a swimmer below the surface of the water. The paired caps of the green-blue image will be considered as swimmers partly above the surface of the water. The geometric comparison neighborhood is not necessarily determined. In an alternative embodiment, it is possible to define the geometric comparison neighborhood relating to the infrared and green-blue caps respectively, as a function of geometric considerations relating to the positions of said caps and possibly also as a function of geometric considerations specific to the environment in particular the orientation of the cameras relative to the interface or the orientation in the images of the normal to the interface. The caps from the infrared cameras being relative to the body parts located above the interface, we will look for the corresponding green-blue caps in a geometric comparison neighborhood calculated according to the orientation of the normal to the interface. In another alternative embodiment, the system described in the present invention can be used in complement of a system based on stereovision such as that described in patent n ° FR 00/15803. In the case where the system described in patent n ° FR 00/15803 detects a body under the surface of the water and, - if there is, in a determined geometrical neighborhood, corresponding data representative of at least one part of said body in the near infrared range, it can be concluded that said body is located at least partly above the interface, - if there is not, in a determined geometrical neighborhood, corresponding data representative of at least a part of said body in the near infrared range, it can be concluded that said body is located below one interface. In another alternative embodiment, the system described in the present invention can advantageously use stereovision principles such as those described in patent No. FR 00/15803. In the particular case of the use of several green-blue cameras and / or of several near infrared cameras. They will be able to work in stereovision. In the case where said system is more particularly intended to discriminate between a stationary body (a swimmer in difficulty) and a moving body (a swimmer struggling in a pool), said system includes integration over time 703, associated with a clock 704, to iterate at determined time intervals said process for deducing the presence of a body described above. To this end, the video images are taken at time intervals determined from said observation point. In this case, said computer processing means 700 include totalizers 705 for calculating the number of times the body is detected during a determined period of time T1. Said computer processing means 700 further comprise discriminators 706 for discriminating, at a point in said zone, between the bodies which are present a number of times greater than a determined threshold SI and the bodies which are present a number of times lower than said determined threshold SI. In the first case, said bodies are hereinafter designated the stationary bodies, in the second case said bodies are hereinafter designated the moving bodies. In an alternative embodiment, said computer processing means 700 further comprises means for calculating the number of times a body is detected as being stationary and new during a determined period of time T2. Said time period T2 is chosen to be greater than the duration of the phenomena that are observed, and in particular greater than T1. Said computer processing means 700 furthermore comprise transmission means 716 for transmitting an alert signal 711 according to the detection criteria described above. In particular, in an alternative embodiment more particularly suitable for monitoring swimmers in a swimming pool, the system emits an alert signal 711, in the presence of a human-sized body, stationary and located under the interface. In an alternative embodiment of said system, an additional step of integration over time may advantageously be carried out by accumulation of images from the same green-blue and / or near infrared camera. The accumulated image is calculated for example by averaging the gray levels of the pixels of the successive images taken over a determined time interval. An accumulated image obtained by accumulation of images from a green-blue camera will be called green-blue accumulated image. Likewise, an accumulated image obtained by accumulation of images from a near infrared camera will be called an accumulated near infrared image. The extraction means 712 and 713 can then also use the accumulated green-blue and / or near infrared images. For example, the extraction means 712 may extract only the caps of the green-blue image for which there is not, in the accumulated green-blue image, a similar cap located in a neighborhood. Extraction means 712 and 713 can then also use composite images consisting of accumulated green-blue images and green-blue images as well as composite images consisting of accumulated near infrared and near infrared images. For example, the extraction means 712 could use the difference between the green-blue image and the accumulated green-blue image. We will now describe FIG. 8 which represents a general schematic view of the system according to the invention. The system makes it possible to detect a body 801 in a zone 802 located near an interface 803 between two liquid 812 and / or gaseous 813 media, in particular of the water / air type. The body 801 is illuminated by electromagnetic radiation 804 comprising at least two different wavelengths, in particular situated in ranges corresponding to the near infrared on the one hand and to green-blue on the other hand. The media 812 and 813 have different absorption coefficients as a function of the wavelengths of the electromagnetic radiation. The system comprises: - (a) selection means 814 for choosing from the wavelengths of electromagnetic radiation 804, at least two wavelengths or two wavelength ranges, - (b) pick-up means views 815 to produce, for each wavelength or wavelength range, an image 805 of the interface and of the area, - (c) conversion means 816 for producing electrical signals 6 representative of each image 805, - (d) digitization means 817 for digitizing the electrical signals 806 so as to produce data 807 corresponding to each image, - (e) computer processing means 818 for extracting data 807 corresponding to each image 805 two groups of data 807 respectively representative of at least one part of the body 801 in the near infrared range and in the green-blue range, (f) calculation means 819 for comparing the groups of data 807. The conversion means 816, the digitization means 817, the computer processing means 818, the calculation means 819 are hereinafter called the deduction means from the presence of a body 801. It is thus possible to detect the presence of a body 801 and / or to determine the position of the detected body with respect to the interface 803, by discriminating between a body 801 located under the interface 803 and a body 801 located at least in part above the interface 803. In the case of the alternative embodiment shown in FIG. 809, the system further comprises integration means 820 for integrating over time the results of the calculation means 819 of the data groups 807. In the case of the variant embodiment shown in FIG. 809, the system further comprises activation means 821 for activating an alarm 808 if a body of human size is st detected under the interface for a time greater than a determined threshold.

Claims

REVENDICATIONS
Procédé 1. Procédé pour détecter un corps (1) dans une zone (2) située à proximité d'une interface (3) entre deux milieux liquides et/ou gazeux, notamment du type eau/air ; ledit corps (1) étant éclairé par un rayonnement électromagnétique (4) comprenant au moins deux longueurs d'onde différentes, notamment situées dans des plages correspondant au proche infra-rouge d'une part et au vert-bleu d'autre part ; lesdits milieux ayant des coefficients d'absorption différents en fonction des longueurs d'onde du rayonnement électromagnétique (4) ; ledit procédé comprenant les étapes suivantes : - (a) l'étape de choisir parmi les longueurs d'onde du rayonnement électromagnétique (4) , au moins deux longueurs d'onde ou deux plages de longueurs d'onde, - (b) l'étape de réaliser, pour chacune desdites longueurs d'onde ou plages de longueur d'onde une image (5) de ladite interface (3) et de ladite zone (2), - (c) l'étape de produire des signaux électriques (6) représentatifs de chaque image (5) , - (d) l'étape de numériser les signaux électriques (6) de manière à produire des données (7) correspondant à chaque image (5) , (e) l'étape d'extraire desdites données (7) correspondant à chaque image (5) deux groupes de données (7) respectivement représentatifs d'au moins une partie dudit corpsMethod 1. Method for detecting a body (1) in an area (2) located near an interface (3) between two liquid and / or gaseous media, in particular of the water / air type; said body (1) being lit by electromagnetic radiation (4) comprising at least two different wavelengths, in particular situated in ranges corresponding to the near infrared on the one hand and to green-blue on the other hand; said media having different absorption coefficients as a function of the wavelengths of the electromagnetic radiation (4); said method comprising the following steps: - (a) the step of choosing from the wavelengths of the electromagnetic radiation (4), at least two wavelengths or two wavelength ranges, - (b) l step of producing, for each of said wavelengths or wavelength ranges, an image (5) of said interface (3) and of said zone (2), - (c) the step of producing electrical signals (6) representative of each image (5), - (d) the step of digitizing the electrical signals (6) so as to produce data (7) corresponding to each image (5), (e) step d 'extracting from said data (7) corresponding to each image (5) two groups of data (7) respectively representative of at least part of said body
(1) dans la plage proche infra-rouge et dans la plage vert-bleu, - (f) l'étape de comparer lesdits groupes de données (7) ; les étapes (c) à (f) étant ci-après dénommées le processus de déduction de la présence d'un corps (1) ; de sorte qu' il est ainsi possible de détecter la présence d'un corps (1) et/ou de déterminer la position du corps (1) détecté par rapport à ladite interface (3) , en discriminant entre un corps (1) situé entièrement sous l'interface (3) et un corps (1) situé au moins en partie au-dessus de l'interface (3) . (1) in the near infrared range and in the green-blue range, - (f) the step of comparing said groups of data (7); steps (c) to (f) being hereinafter called the process of deducing the presence of a body (1); so that it is thus possible to detect the presence of a body (1) and / or to determine the position of the body (1) detected with respect to said interface (3), by discriminating between a body (1) located entirely under the interface (3) and a body (1) located at least partially above the interface (3).
2. Procédé selon la revendication 1 ; ledit procédé comprenant en outre : - l'étape d'intégrer dans le temps les résultats de l'étape de comparaison desdits groupes de données (7) . 2. Method according to claim 1; said method further comprising: the step of integrating over time the results of the step of comparing said groups of data (7).
3. Procédé selon la revendication 2 ; ledit procédé comprenant en outre : - l'étape de déclencher une alarme (8) si un corps (1) de taille humaine est détecté sous ladite interface (3) pendant un temps supérieur à un seuil déterminé. 3. Method according to claim 2; said method further comprising: - the step of triggering an alarm (8) if a body (1) of human size is detected under said interface (3) for a time greater than a determined threshold.
4. Procédé selon l'une quelconques des revendications 1 à 3 ; ledit procédé étant tel que pour extraire desdites données (7) correspondant à chaque image (5) deux groupes de données (7) respectivement représentatifs d'au moins une partie dudit corps (1) dans la plage proche infra-rouge et dans la plage vert-bleu, on génère des calottes (9) (au sens de la présente invention) . 4. Method according to any one of claims 1 to 3; said method being such as to extract from said data (7) corresponding to each image (5) two groups of data (7) respectively representative of at least part of said body (1) in the near infrared range and in the range green-blue, caps (9) are generated (within the meaning of the present invention).
5. Procédé selon la revendication 4 ; ledit procédé comprenant en outre les étapes suivantes : l'étape d'associer à chaque calotte (9) des caractéristiques (10) (au sens de la présente invention) , - l'étape de déduire la présence d'un groupe de données (7) représentatif d'au moins une partie dudit corps (1) si les caractéristiques (10) dépassent un seuil SC prédéterminé. 5. Method according to claim 4; said method further comprising the following steps: the step of associating with each cap (9) characteristics (10) (within the meaning of the present invention), - the step of deducing the presence of a group of data ( 7) representative of at least part of said body (1) if the characteristics (10) exceed a predetermined threshold SC.
6. Procédé selon l'une quelconque des revendications 1 à 5 ; ledit procédé étant tel que pour comparer lesdits groupes de données (7), on recherche les données (7) représentatives d'au moins une partie dudit corps (1) dans la plage vert-bleu pour lesquelles il n'y a pas, dans un voisinage géométrique (11) déterminé, de données (7) correspondantes représentatives d'au moins une partie dudit corps (1) dans la plage infra-rouge ; de sorte qu'en cas de recherche positive, on peut conclure que ledit corps (1) est situé sous l'interface (3) . 6. Method according to any one of claims 1 to 5; said method being such that to compare said groups of data (7), one searches for data (7) representative of at least one part of said body (1) in the green-blue range for which there is not, in a determined geometric neighborhood (11), of corresponding data (7) representative of at least a part of said body (1) in the infrared range; so that in the event of a positive search, it can be concluded that said body (1) is located under the interface (3).
7. Procédé selon l'une quelconque des revendications 1 à 5 ; ledit procédé étant tel que pour comparer lesdits groupes de données (7) , on recherche, les données (7) représentatives d'au moins une partie dudit corps (1) dans la plage vert-bleu pour lesquelles il y a, dans un voisinage géométrique (11) déterminée, des données (7) correspondantes représentatives d'au moins une partie dudit corps (1) dans la plage infra-rouge ; de sorte qu'en cas de recherche positive, on peut conclure que ledit corps (1) est situé au moins en partie au- dessus de l'interface (3) . 8. Procédé selon la revendication 2 prise ensemble avec l'une quelconques des revendications 1 à 7 ; plus particulièrement destiné à discriminer entre un corps (1) stationnaire et un corps (1) en mouvement ; pour intégrer dans le temps les résultats de l'étape de comparaison desdits groupes de données (7), ledit procédé comprenant en outre les étapes suivantes : - l'étape d'itérer à intervalles de temps déterminés ledit processus de déduction de la présence dudit corps (1) ; - l'étape de calculer le nombre de fois où ledit corps7. Method according to any one of claims 1 to 5; said method being such that to compare said groups of data (7), one searches, the data (7) representative of at least one part of said body (1) in the green-blue range for which there is, in a neighborhood geometrical (11) determined, corresponding data (7) representative of at least a part of said body (1) in the infrared range; so that in the event of a positive search, it can be concluded that said body (1) is located at least partly above the interface (3). 8. The method of claim 2 taken together with any one of claims 1 to 7; more particularly intended to discriminate between a stationary body (1) and a moving body (1); to integrate over time the results of the step of comparing said groups of data (7), said method further comprising the following steps: - the step of iterating at determined time intervals said process of deducing the presence of said body (1); - the step of calculating the number of times said body
(1) est détecté pendant une période de temps déterminée Tl ; - l'étape de discriminer, en un point de ladite zone (2) , entre lesdits corps (1) qui sont présents un nombre de fois supérieur à un seuil déterminé SI (lesdits corps (1) étant ci- après désignés les corps (1) stationnaires) et lesdits corps (1) qui sont présents un nombre de fois inférieur audit seuil déterminé SI (lesdits corps (1) étant ci-après désignés les corps (1) en mouvement) ; de sorte qu'il est ainsi possible de détecter la présence d'un corps (1) stationnaire situé entièrement sous l'interface (3) et ainsi de déclencher une alarme (8) . Système 9. Système pour détecter un corps (1) dans une zone(1) is detected for a determined period of time T1; the step of discriminating, at a point in said zone (2), between said bodies (1) which are present a number of times greater than a determined threshold SI (said bodies (1) being hereinafter designated the bodies ( 1) stationary) and said bodies (1) which are present a number of times lower than said determined threshold SI (said bodies (1) being hereinafter designated the bodies (1) in movement); so that it is thus possible to detect the presence of a stationary body (1) located entirely under the interface (3) and thus to trigger an alarm (8). System 9. System for detecting a body (1) in an area
(2) située à proximité d'une interface (3) entre deux milieux liquides (12) et/ou milieux gazeux (13), notamment du type eau/air ; ledit corps (1) étant éclairé par un rayonnement électromagnétique (4) comprenant au moins deux longueurs d'onde différentes, notamment situées dans des plages correspondant au proche infra-rouge d'une part et au vert-bleu d'autre part ; lesdits milieux ayant des coefficients d' absorption différents en fonction des longueurs d'onde du rayonnement électromagnétique (4) ; ledit système comprenant : - (a) des moyens de sélection (14) pour choisir parmi les longueurs d'onde du rayonnement électromagnétique (4), au moins deux longueurs d'onde ou deux plages de longueurs d'onde, - (b) des moyens de prise de vues (15) pour réaliser, pour chacune desdites longueurs d'onde ou plages de longueur d'onde, une image (5) de ladite interface (3) et de ladite zone (2), - (c) des moyens de conversion (16) pour produire des signaux électriques (6) représentatifs de chaque image (5) , - (d) des moyens de numérisation (17) pour numériser les signaux électriques (6) de manière à produire des données (7) correspondant à chaque image (5), - (e) des moyens de traitement informatique (18) pour extraire desdites données (7) correspondant à chaque image (5) deux groupes de données (7) respectivement représentatifs d'au moins une partie dudit corps (1) dans la plage proche infrarouge et dans la plage vert-bleu, - (f) des moyens de calcul (19) pour comparer lesdits groupes de données (7) ; les moyens de conversion (16) , les moyens de numérisation (17), les moyens de traitement informatique (18), les moyens de calcul (19) étant ci-après dénommés les moyens de déduction de la présence d'un corps (1) ; de sorte qu' il est ainsi possible de détecter la présence d'un corps (1) et/ou de déterminer la position du corps (1) détecté par rapport à ladite interface (3), en discriminant entre un corps (1) situé sous l'interface (3) et un corps (1) situé au moins en partie au-dessus de l'interface (3) . (2) located near an interface (3) between two liquid media (12) and / or gaseous media (13), in particular of the type water / air; said body (1) being lit by electromagnetic radiation (4) comprising at least two different wavelengths, in particular situated in ranges corresponding to the near infrared on the one hand and to green-blue on the other hand; said media having different absorption coefficients as a function of the wavelengths of the electromagnetic radiation (4); said system comprising: - (a) selection means (14) for choosing from the wavelengths of the electromagnetic radiation (4), at least two wavelengths or two ranges of wavelengths, - (b) taking means (15) for producing, for each of said wavelengths or wavelength ranges, an image (5) of said interface (3) and of said zone (2), - (c) conversion means (16) for producing electrical signals (6) representative of each image (5), - (d) digitizing means (17) for digitizing the electrical signals (6) so as to produce data (7 ) corresponding to each image (5), - (e) computer processing means (18) for extracting said data (7) corresponding to each image (5) two groups of data (7) respectively representative of at least part of said body (1) in the near infrared range and in the green-blue range, - (f) calculation means (19) for comparing lesd its data groups (7); the conversion means (16), the digitization means (17), the computer processing means (18), the calculation means (19) being hereinafter referred to as the means for deducing the presence of a body (1 ); so that it is thus possible to detect the presence of a body (1) and / or to determine the position of the detected body (1) relative to said interface (3), by discriminating between a body (1) located under the interface (3) and a body (1) located at least partially above the interface (3).
10. Système selon la revendication 9 ; ledit système comprenant en outre : - des moyens d'intégration (20) pour intégrer dans le temps les résultats des moyens de calcul (19) desdits groupes de données (7) . 10. The system of claim 9; said system further comprising: - integration means (20) for integrating over time the results of the calculation means (19) of said data groups (7).
11. Système selon la revendication 10 ; ledit système comprenant en outre : - des moyens d'activation (21) pour actionner une alarme (8) si un corps (1) de taille humaine est détecté sous ladite interface (3) pendant un temps supérieur à un seuil déterminé. 12 Système selon l'une quelconques des revendications 9 à 11 ; ledit système étant tel que lesdits moyens de traitement informatique (18) permettent de générer des calottes (9) (au sens de la présente invention) . 13. Système selon la revendication 12 ; ledit système étant tel que lesdits moyens de traitement informatique (18) permettent : - d'associer à chaque calotte (9) des caractéristiques (10) (au sens de la présente invention) , - de déduire la présence d'un groupe de données (7) représentatif d'au moins une partie dudit corps (1) si les caractéristiques (10) dépassent un seuil SC prédéterminé. 14. Système selon l'une quelconque des revendications 9 à 13 ; ledit système étant tel que lesdits moyens de calcul11. System according to claim 10; said system further comprising: - activation means (21) for activating an alarm (8) if a body (1) of human size is detected under said interface (3) for a time greater than a determined threshold. 12 System according to any one of claims 9 to 11; said system being such that said computer processing means (18) make it possible to generate caps (9) (within the meaning of the present invention). 13. The system of claim 12; said system being such that said computer processing means (18) allow: - to associate with each cap (9) characteristics (10) (within the meaning of the present invention), - to deduce the presence of a group of data (7) representative of at least part of said body (1) if the characteristics (10) exceed a predetermined threshold SC. 14. System according to any one of claims 9 to 13; said system being such that said calculation means
(19) permettent de rechercher les données (7) représentatives d'au moins une partie dudit corps (1) dans la plage vert-bleu pour lesquelles il n'y a pas, dans un voisinage géométrique (11) déterminé, de données (7) correspondantes représentatives d'au moins une partie dudit corps (1) dans la plage infra-rouge ; de sorte qu'en cas de recherche positive, on peut conclure que ledit corps (1) est situé sous l'interface (3) . 15. Système selon l'une quelconque des revendications 9 à 13 ; ledit système étant tel que lesdits moyens de calcul (19) permettent de rechercher les données (7) représentatives d'au moins une partie dudit corps (1) dans la plage vert-bleu pour lesquelles il y a, dans un voisinage géométrique (11) déterminé, des données (7) correspondantes représentatives d'au moins une partie dudit corps (1) dans la plage infra-rouge ; de sorte qu'en cas de recherche positive, on peut conclure que ledit corps (1) est situé au moins en partie au- dessus de l'interface (3) . 16. Système selon la revendication 10 prise ensemble avec l'une quelconques des revendications 9 à 15 ; plus particulièrement destiné à discriminer entre un corps (1) stationnaire et un corps (1) en mouvement ; lesdits moyens d'intégration (20) pour intégrer dans le temps les résultats des moyens de calcul (19) permettant : - d'itérer à intervalles de temps déterminés la mise en œuvre desdits moyens de déduction de la présence dudit corps (D ; - de calculer le nombre de fois où ledit corps (1) est détecté pendant une période de temps déterminée Tl ; - de discriminer, en un point de ladite zone (2), entre lesdits corps (1) qui sont présents un nombre de fois supérieur à un seuil déterminé SI (lesdits corps (1) étant ci- après désignés les corps (1) stationnaires) et lesdits corps (1) qui sont présents un nombre de fois inférieur audit seuil déterminé SI (lesdits corps (1) étant ci-après désignés les corps (1) en mouvement) ; de sorte qu' il est ainsi possible de détecter la présence d'un corps (1) stationnaire situé entièrement sous l'interface (3) ; de sorte qu'il est ainsi possible de déclencher une alarme (8) . (19) make it possible to search for the data (7) representative of at least part of said body (1) in the green-blue range for which there is no, in a determined geometrical neighborhood (11), data ( 7) corresponding representative of at least part of said body (1) in the infrared range; so that in the event of a positive search, it can be concluded that said body (1) is located under the interface (3). 15. System according to any one of claims 9 to 13; said system being such that said calculation means (19) make it possible to search for representative data (7) at least a part of said body (1) in the green-blue range for which there is, in a determined geometric neighborhood (11), corresponding data (7) representative of at least a part of said body (1) in the infrared range; so that in the event of a positive search, it can be concluded that said body (1) is located at least partly above the interface (3). 16. The system of claim 10 taken together with any one of claims 9 to 15; more particularly intended to discriminate between a stationary body (1) and a moving body (1); said integration means (20) for integrating over time the results of the calculation means (19) making it possible: - to iterate at determined time intervals the implementation of said means for deducing the presence of said body (D; - to calculate the number of times said body (1) is detected during a determined period of time T1; - to discriminate, at a point in said zone (2), between said bodies (1) which are present a greater number of times at a determined threshold SI (said bodies (1) being hereinafter designated the stationary bodies (1)) and said bodies (1) which are present a number of times lower than said determined threshold SI (said bodies (1) being below after designating the bodies (1) in movement); so that it is thus possible to detect the presence of a stationary body (1) situated entirely under the interface (3); so that it is thus possible to trigger an alarm (8).
EP04767924A 2003-07-28 2004-07-28 Method and system for detecting a body in a zone located proximate an interface Expired - Lifetime EP1656650B1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR0350378A FR2858450B1 (en) 2003-07-28 2003-07-28 METHOD AND SYSTEM FOR DETECTING A BODY IN A ZONE LOCATED NEAR AN INTERFACE
PCT/FR2004/050363 WO2005013226A1 (en) 2003-07-28 2004-07-28 Method and system for detecting a body in a zone located proximate an interface

Publications (2)

Publication Number Publication Date
EP1656650A1 true EP1656650A1 (en) 2006-05-17
EP1656650B1 EP1656650B1 (en) 2008-03-05

Family

ID=34043805

Family Applications (1)

Application Number Title Priority Date Filing Date
EP04767924A Expired - Lifetime EP1656650B1 (en) 2003-07-28 2004-07-28 Method and system for detecting a body in a zone located proximate an interface

Country Status (8)

Country Link
US (1) US7583196B2 (en)
EP (1) EP1656650B1 (en)
JP (1) JP4766492B2 (en)
AT (1) ATE388460T1 (en)
DE (1) DE602004012283D1 (en)
ES (1) ES2303092T3 (en)
FR (1) FR2858450B1 (en)
WO (1) WO2005013226A1 (en)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008066619A1 (en) * 2006-10-19 2008-06-05 Travis Sparks Pool light with safety alarm and sensor array
US7839291B1 (en) * 2007-10-02 2010-11-23 Flir Systems, Inc. Water safety monitor systems and methods
US8390685B2 (en) * 2008-02-06 2013-03-05 International Business Machines Corporation Virtual fence
US8345097B2 (en) * 2008-02-15 2013-01-01 Harris Corporation Hybrid remote digital recording and acquisition system
WO2012145800A1 (en) * 2011-04-29 2012-11-01 Preservation Solutions Pty Ltd Monitoring the water safety of at least one person in a body of water
US8544120B1 (en) * 2012-03-02 2013-10-01 Lockheed Martin Corporation Device for thermal signature reduction
CN103646511A (en) * 2013-11-25 2014-03-19 银川博聚工业产品设计有限公司 Swimming pool drowning dynamic monitoring device
US20170167151A1 (en) * 2015-12-10 2017-06-15 Elazar Segal Lifesaving system and method for swimming pool
US10329785B2 (en) 2016-04-08 2019-06-25 Robson Forensic, Inc. Lifeguard positioning system
JP7313811B2 (en) * 2018-10-26 2023-07-25 キヤノン株式会社 Image processing device, image processing method, and program
CN109584509B (en) * 2018-12-27 2020-08-11 太仓市小车东汽车服务有限公司 Swimming pool drowning monitoring method based on combination of infrared rays and visible light
CN115278119B (en) * 2022-09-30 2022-12-06 中国科学院长春光学精密机械与物理研究所 Infrared camera integral time automatic adjusting method for infrared radiation characteristic measurement

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0683451B2 (en) * 1986-08-01 1994-10-19 東芝エンジニアリング株式会社 Submersion detection system
US4779095A (en) * 1986-10-28 1988-10-18 H & G Systems, Inc. Image change detection system
GB8811355D0 (en) * 1988-05-13 1997-09-17 Secr Defence An electro-optical detection system
US4862257A (en) * 1988-07-07 1989-08-29 Kaman Aerospace Corporation Imaging lidar system
JPH0378577A (en) * 1989-08-19 1991-04-03 Mitsubishi Electric Corp Vacuum device
US5043705A (en) * 1989-11-13 1991-08-27 Elkana Rooz Method and system for detecting a motionless body in a pool
GB9115537D0 (en) * 1991-07-18 1991-09-04 Secr Defence An electro-optical detection system
US5959534A (en) * 1993-10-29 1999-09-28 Splash Industries, Inc. Swimming pool alarm
US5638048A (en) * 1995-02-09 1997-06-10 Curry; Robert C. Alarm system for swimming pools
FR2741370B1 (en) * 1995-11-16 1998-05-29 Poseidon SWIMMING POOL MONITORING SYSTEM FOR DROWNING PREVENTION
US6963354B1 (en) * 1997-08-07 2005-11-08 The United States Of America As Represented By The Secretary Of The Navy High resolution imaging lidar for detecting submerged objects
US6628835B1 (en) * 1998-08-31 2003-09-30 Texas Instruments Incorporated Method and system for defining and recognizing complex events in a video sequence
US6327220B1 (en) * 1999-09-15 2001-12-04 Johnson Engineering Corporation Sonar location monitor
FR2802653B1 (en) * 1999-12-21 2003-01-24 Poseidon METHOD AND SYSTEM FOR DETECTING AN OBJECT IN FRONT OF A BACKGROUND
JP2002077897A (en) * 2000-08-25 2002-03-15 Nippon Hoso Kyokai <Nhk> Object extraction type tv camera
WO2002046795A1 (en) * 2000-12-06 2002-06-13 Poseidon Method for detecting new objects in an illuminated scene
SG95652A1 (en) * 2001-05-25 2003-04-23 Univ Nanyang Drowning early warning system
US6642847B1 (en) * 2001-08-31 2003-11-04 Donald R. Sison Pool alarm device

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See references of WO2005013226A1 *

Also Published As

Publication number Publication date
US20070052697A1 (en) 2007-03-08
ES2303092T3 (en) 2008-08-01
ATE388460T1 (en) 2008-03-15
FR2858450B1 (en) 2005-11-11
WO2005013226A1 (en) 2005-02-10
US7583196B2 (en) 2009-09-01
DE602004012283D1 (en) 2008-04-17
JP4766492B2 (en) 2011-09-07
EP1656650B1 (en) 2008-03-05
FR2858450A1 (en) 2005-02-04
JP2007500892A (en) 2007-01-18

Similar Documents

Publication Publication Date Title
EP1656650B1 (en) Method and system for detecting a body in a zone located proximate an interface
FR3065307A1 (en) DEVICE FOR CAPTURING AN IMPRESSION OF A BODY PART.
FR2882160A1 (en) Video image capturing method for e.g. portable telephone, involves measuring local movements on edges of images and estimating parameters of global movement model in utilizing result of measurement of local movements
EP1240622B1 (en) Method and system for detecting an object in relation to a surface
EP2994901B1 (en) Compact human presence detector
FR2832528A1 (en) DETERMINING AN ILLUMINANT OF A DIGITAL COLOR IMAGE BY SEGMENTATION AND FILTERING
EP3388976B1 (en) Method for detecting fraud
EP1340104B1 (en) Method and device for detecting an object near a water/air interface
EP2307948A2 (en) Interactive device and method of use
EP0577491B1 (en) Process and device for monitoring a three-dimensional scene using imagery sensors
FR2717269A1 (en) Discriminating between targets which might represent ocean mines
WO2001081858A1 (en) Method for measuring a three-dimensional object, or assembly of objects
EP2756483B1 (en) Method and system for acquiring and processing images for the detection of motion
EP3770806A1 (en) Method for video monitoring of the crossing of a line by persons, corresponding device and computer program
FR2817624A1 (en) Method for detecting objects in an illuminated area, such as a person under water, uses digitized video images
EP3862980B1 (en) Method of generation of a virtual three-dimensional representation of breakwater surface layer
FR2911984A1 (en) Symbolic point identifying method for e.g. monitoring vigilance of e.g. adult, involves identifying pair of natural points having improved score as symbolic points of area of image of face
FR2817625A1 (en) Method for detecting objects in an illuminated area, such as a person under water, uses digitized video images
EP4254250A1 (en) Method and apparatus for detecting a mobile device spectator based on depth data
FR3135812A1 (en) Method for automatically monitoring people in a pool of water, computer program and associated device
FR3141788A1 (en) Volumetric space monitoring system and corresponding computer program.
EP2329474B1 (en) Scene surveillance method and system
FR3098962A1 (en) System for detecting a hyperspectral feature
FR3055997A1 (en) SYSTEM FOR DETERMINING AT LEAST ONE CHARACTERISTIC RELATING TO THE CONTOUR OF A SUBJECT CONTAINED IN AT LEAST ONE DIGITAL IMAGE
FR3037176A1 (en) DEVICE FOR DETECTING THE PRESENCE OF PERSON ON THE GROUND BY ANALYSIS OF A FLOW OF DEPTH MAPS

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20060228

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LI LU MC NL PL PT RO SE SI SK TR

17Q First examination report despatched

Effective date: 20060811

DAX Request for extension of the european patent (deleted)
GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: MG INTERNATIONAL

111Z Information provided on other rights and legal means of execution

Free format text: FR

Effective date: 20070919

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LI LU MC NL PL PT RO SE SI SK TR

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

Free format text: NOT ENGLISH

REG Reference to a national code

Ref country code: CH

Ref legal event code: EP

REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

Free format text: LANGUAGE OF EP DOCUMENT: FRENCH

REF Corresponds to:

Ref document number: 602004012283

Country of ref document: DE

Date of ref document: 20080417

Kind code of ref document: P

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: FI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080305

REG Reference to a national code

Ref country code: ES

Ref legal event code: FG2A

Ref document number: 2303092

Country of ref document: ES

Kind code of ref document: T3

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: AT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080305

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: PL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080305

Ref country code: SI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080305

REG Reference to a national code

Ref country code: IE

Ref legal event code: FD4D

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080605

Ref country code: CZ

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080305

Ref country code: SK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080305

Ref country code: PT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080805

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: RO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080305

PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080606

Ref country code: IE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080305

Ref country code: DK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080305

26N No opposition filed

Effective date: 20081208

REG Reference to a national code

Ref country code: CH

Ref legal event code: PL

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MC

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20080731

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: BG

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080605

Ref country code: EE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080305

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: CH

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20080731

Ref country code: LI

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20080731

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080305

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: CY

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080305

REG Reference to a national code

Ref country code: FR

Ref legal event code: GC

Ref country code: FR

Ref legal event code: AU

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: HU

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080906

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: TR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080305

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20080606

REG Reference to a national code

Ref country code: FR

Ref legal event code: PLFP

Year of fee payment: 13

REG Reference to a national code

Ref country code: FR

Ref legal event code: PLFP

Year of fee payment: 14

REG Reference to a national code

Ref country code: FR

Ref legal event code: PLFP

Year of fee payment: 15

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: NL

Payment date: 20230711

Year of fee payment: 20

Ref country code: LU

Payment date: 20230711

Year of fee payment: 20

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 20230831

Year of fee payment: 20

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: FR

Payment date: 20230710

Year of fee payment: 20

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: ES

Payment date: 20231103

Year of fee payment: 20

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: BE

Payment date: 20230929

Year of fee payment: 20