WO2009008733A1 - Means and method for average weight determination and appetite feeding - Google Patents
Means and method for average weight determination and appetite feeding Download PDFInfo
- Publication number
- WO2009008733A1 WO2009008733A1 PCT/NO2008/000254 NO2008000254W WO2009008733A1 WO 2009008733 A1 WO2009008733 A1 WO 2009008733A1 NO 2008000254 W NO2008000254 W NO 2008000254W WO 2009008733 A1 WO2009008733 A1 WO 2009008733A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- fish
- images
- objects
- pattern
- netpen
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 235000019789 appetite Nutrition 0.000 title claims description 6
- 230000036528 appetite Effects 0.000 title claims description 6
- 241000251468 Actinopterygii Species 0.000 claims abstract description 149
- 239000008188 pellet Substances 0.000 claims abstract description 30
- 238000004458 analytical method Methods 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 18
- 210000003608 fece Anatomy 0.000 claims abstract description 15
- 235000021407 appetite control Nutrition 0.000 claims description 7
- 230000009182 swimming Effects 0.000 claims description 7
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 5
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 239000000725 suspension Substances 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 description 7
- 238000012546 transfer Methods 0.000 description 6
- 238000012423 maintenance Methods 0.000 description 5
- RZVAJINKPMORJF-UHFFFAOYSA-N Acetaminophen Chemical group CC(=O)NC1=CC=C(O)C=C1 RZVAJINKPMORJF-UHFFFAOYSA-N 0.000 description 3
- 239000002028 Biomass Substances 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 241000894006 Bacteria Species 0.000 description 1
- 241000233866 Fungi Species 0.000 description 1
- 241001674048 Phthiraptera Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000010794 food waste Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 244000045947 parasite Species 0.000 description 1
- 238000009372 pisciculture Methods 0.000 description 1
- 244000062645 predators Species 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000000699 topical effect Effects 0.000 description 1
- 230000003612 virological effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K61/00—Culture of aquatic animals
- A01K61/80—Feeding devices
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K61/00—Culture of aquatic animals
- A01K61/90—Sorting, grading, counting or marking live aquatic animals, e.g. sex determination
- A01K61/95—Sorting, grading, counting or marking live aquatic animals, e.g. sex determination specially adapted for fish
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
- Y02A40/81—Aquaculture, e.g. of fish
Definitions
- the present invention relates to a method and a system as described in the preamble of the respective independent claims and is especially concerned with registration of predominately freely moving objects in a netpen of a fish farm.
- the fish farming industry still has a number of imperfect and labour intensive technical challenges with regard to a more efficient operation.
- the average weight determiner from Vaki and Storvik advertised in the magazine Norsk Fiskeoppdrett consists of a frame which the fish must swim through.
- the problem is that the largest fish refuse to swim through the measuring frame with the result being that the average weight which is measured is too small, i.e. the population has too many small fish in relation to large fish. The measurements can thereby be in doubt.
- These frames are also manual and often require calibrations which make them not very effective as a stationary device.
- None of the above mentioned units are either constructed or suited as a tool for pellet counting and, at the same time, be used for appetite control of the feeding.
- Akva Group has a Doppler sensor with a camera as a feed sensor for appetite feeding. This can also not count the fish in the feeding zone which is an important tool for the appetite feeding and will give an incorrect registration when the fish are found deep in the sea. In addition, it appears that the amount of pellets is influenced by the fish and faeces near the sensor. This was solved by encapsulating the sensor in a cage of net. The result was increased maintenance and cleaning.
- Neither the Poro camera nor the Doppler can measure the average weight of the fish or count the fish in the measuring zone.
- Known from NO20050517 is a method and device where a number of cameras are used, preferably CCD cameras, to register images of fish which move past the camera in a transfer channel.
- the signals from said camera are processed in a computer to calculate the volume of each fish.
- the fish is illuminated by at least two light sources and is registered by at least two cameras placed around the transfer channel, such that reflected light or silhouettes of the fish from opposite sides of the fish is registered, to form a complete photographic recording of the transverse dimension of the fish over the length of the fish. This is used as the basis to calculate the weight of the fish.
- said transfer channel is necessary so that one fish shall be pumped or shall swim past and also that it is necessary to estimate the speed of the fish so that the area of average profiles of the fish can be calculated for determining the part volume of fish. These volume parts are later added to give a total volume of the fish.
- GB 2 2001 772 A describes a method and device to determine the length measurements of the quality of farmed fish.
- the fish is forced to swim through a transparent channel or pipe where it is subjected to radiation from at least one radiation source.
- the radiation is registered by the photo detector in a number of cameras arranged in a row along the channel.
- the length of the fish can then be calculated in a computer according to the degree of masking in the photo detectors.
- GB 2 203 540 A is a method and apparatus for measuring, counting and classifying fish.
- the fish is forced along a curved track with detectors and associated transmitters. On its journey through the track the fish breaks the beam from a first light sensor and thereafter the beam from a second light sensor, and from the time between the break in the beams and the distance to the sensors one can determine the speed and the length of the fish. This is thereafter used to estimate the total size of the fish.
- NO168151 describes a method and apparatus for counting fish.
- the fish is forced through a channel where a number of CCD line cameras are arranged, and with an associated light source on the opposite side.
- Fish which passes the light source form an area of shadow which the camera registers.
- the cross sectional area of the fish can be calculated, for example, in a computer, and built on the area registration the number of fish which has passed can be calculated by adding together all the registered areas and dividing the total area by the last calculated average area.
- EP 0984391 A1 shows a counting device which, with the help of two simultaneously activated cameras, determines the number and size of fish which pass in a channel. The number of fish is counted with the help of size and direction which are estimated from images which are taken by the cameras.
- light sources and cameras or other irradiation sources assembled opposite each other in a transfer channel are not used. Correspondingly it is also unnecessary to force the fish individually through the channel.
- the apparatus and the systems partly are large, expensive and not easy to handle. Furthermore it shall also be pointed out that the above mentioned documents only describe the technological background.
- the object is to solve the problems of biomass measuring and appetite control/feeding in one and the same device in the netpen in a simple, completely automated, maintenance friendly and efficient way.
- the above mentioned object is achieved with a method for registration of predominately freely moving objects in a fish farm netpen as described in the independent claim 1 , in that a camera housing with a number of underwater cameras are submerged in the netpen, suspended from a cable. Each camera takes individual images, at respective angles, of objects which freely pass the camera housing and sends said images to a computer processing unit.
- the computer processing unit analyses the images taken from different angles to determine the main pattern of the object, by grouping each pattern element from the relationship between shape, size, contrast and/or colour and by determining the mutual distance between given pattern elements for identification of a main pattern and, to determine, based on the main pattern, whether the objects are fish, pellets, faeces or other unknown elements.
- Alternative embodiments of the method are characterised in that an object which has been defined as a fish based on approved placing of said main pattern is analysed with respect to be able to determine the volume of the object.
- the analysis can determine the contour of the fish in each of the images from the cameras, based on the displacement of the contour in each of the images from the cameras, to estimate the distance along the contour of the fish whereupon a surface orientated in space with a known area is provided, and to look for pattern groups beyond said main pattern that can be identified and be positioned in all the images, and to estimate the distance to all identifiable pattern groups.
- the analysis can comprise the steps: to provide a surface in space with the shape of the fish independent of position or orientation, and based on positioning of dorsal fins, mouth, eye, ventral fins and tail, to estimate the volume on a vertical section of the fish which will be identical to the volume of half of the fish, and thereafter estimate the volume of the fish and thereby the weight.
- the characteristic pattern on the fish is decided such as spots and variations in the fish scales and the mutual distance between these where these patterns are unique to each fish, and to apply the characteristic features to identify individual objects.
- the analysis can be used to count the number of fish in the area of the netpen, in that the number of fish in the image area is counted, the mutual distance between the fish is estimated, and the swimming speed is estimated, whereupon the number of fish per volume is calculated.
- the counting of pellets can be activated as a parameter for appetite control for the appetite of the fish and a signal can be sent to a control unit for the control of a feed distributor.
- the main pattern can be used to determine the amount of pellets and faeces in an area of the netpen.
- the above mentioned object is also achieved with a system as given in the independent claim 10.
- the system is characterised in that at least three of said underwater cameras in the camera housing are all fixed mounted in the form of a triangle, mainly pointing in the same direction where each camera is arranged to take individual images at respective angles of objects which freely pass the camera housing and to send said images to a computer processing unit, with the computer processing unit being arranged to analyse the images taken from different angles to determine the main pattern of the objects by grouping each pattern element based on the relationship between shape, size, contrast and/or colour, and by determining the mutual distance between given pattern elements for identification of a main pattern and to decide, based on the main pattern, whether the objects are fish, pellets, faeces or other unknown elements.
- Alternative embodiments are characterised in that said underwater camera is orientated in a fixed frame or plate with an individual fixed distance, forming a rigid and fixed unit, and is arranged in a protruding and outer eccentric housing part in a ball formed housing.
- the outer housing part can be arranged to an in-between lying housing part which in turn can be arranged to a stationary housing.
- the housing can be connected to a ballast body via a stay.
- the housing can be equipped with an electronic compass so that position in relation to a given fixed point in the suspension system itself can be estimated with the help of the computer processing unit.
- Figure 1a shows a netpen with a device according to the invention
- Figure 1b shows the device in more detail
- Figure 2 shows the positioning of the cameras in the device according to the invention
- Figures 3a and 3b show the positioning of the cameras in the device in relation to an object
- Figures 4a, 4b, 4c show images taken by the device according to the invention
- Figure 5a shows an object in a coordinate system
- Figures 5b and 5c show converted images.
- Fig.1a shows a netpen 15 in which is placed a closed unit 2, shown in detail in fig. 1b, containing three underwater cameras 1a, 1b and 1c in a rigid frame 16 with mutual fixed distance and angle pointing in the same direction towards a feeding area 26 with fish 10.
- the frame 16 with the cameras 1a, 1b and 1c form a triangle 1 which is preferably surrounded by one or more watertight and preferably ball-shaped housing 2, which in turn can be divided into a moveable, doubly-connected housing 2a, 2b and a stationary part 2c, where the housing part 2a is eccentrically orientated as a protruding eye in relation to the parts 2b, 2c.
- the triangle housing 2 is shown designed as a closed housing for the protection of the electronics.
- a cable 17a, 17b and 17c is attached, collected in a common cable 19 via a junction box 18 to which, according to the invention, other sensors 24 for temperature, oxygen, compass etc., can also be connected and which distribute signals and electricity transfer via a common cable 20, where this again also can contain signals and electricity supply to means for power transfer, for example, a gear motor 23 for rotation of the ball housing 2a, 2b.
- the number of cables can, in this way, be minimised and it becomes a simpler installation with less maintenance.
- the cable 20 is led up to a control centre, processor or computer unit 8 via an underwater connection 21 , and placed on a feeding automat/distributor 9 or netpen floating collar 10 which in turn has a wireless communication to a central PC 5.
- the computer processing unit does not need to be arranged as shown in the figures, but can, for example, be the mentioned PC 5.
- the unit 8 will in this case also be a communication unit.
- the processing unit 8 or the feeding automat/distributor 9 is connected to transport pipes for the feeding and can, as shown in fig.
- the triangle housing 2 can be used for average weight measurements, counting the fish and counting feed pellets in one and same compact unit, in that images from the cameras 1a, 1b and 1c in the frame send images, such as three dimensional images, to the processor 8 and/or the PC 5, and where the fish is not damaged, stressed or alarmed by physical geometrical barriers in the netpen, at the same time as there is not an unnecessary number of criss-crossing cables causing problems for operational safety and maintenance of the net case, such as, for example, cleaning of net bags 15 and sorting the fish, etc.
- the triangular ball housing 2 is programmed via the computer unit 8 to have a given position for the counting of the pellets and appetite control and another position covering the correct measurement area for average weight measurements or be positioned in relation to environmental conditions controlled by the processor or the computer unit 8 or the PC 5.
- ballast body 25 is shown, for example, a ball connected to the lower part of the triangle housing 2c via a fixed stay 26.
- Fig. 2 shows the cameras 1a, 1b and 1c orientated in relation to each other in the frame 16 and figs. 3a and 3b show the individual visual angles 27a, 27b and 27c of the three cameras covering one and the same fish 10 in arbitrary swimming position in relation to the fixed visual angles of the cameras seen from two sides.
- Figs. 4a, 4b and 4c show how the cameras 1a, 1b and 1c individually show images of the coordinate position of the fish 10 on the screen so that the algorithm of the software can recognise the same fish 10 and identify the objects as fish 10, pellets 11 and faeces 12. As images are taken at the same time, the distance to, for example, the fish 10 is determined, and in addition the software can pick out the coordinates of the contour of, for example, the fish 10 in an arbitrary position swimming sidewise or up or down in relation to the cameras 1a, 1b and 1c.
- the figures 5a, 5b and 5c show how the arbitrary position in space of the objects 10, 11 and 12 can be converted for all images of fish 10, pellets 11 and faeces 12 to a two-dimensional coordinate system and from the estimated polar coordinates of a side outline and a breadth outline easily identify and estimate the weight of the fish 10, count the fish 10, and count feed pellets 11 by separation of faeces 12.
- pellets 11 can be separated out from the faeces 12 more easily such that the number of pellets measured in the feeding area can control the feed amounts from automated feed machines, feed buoys or feed distributers 9, and that one can, by counting the number of fish 10 in the area, be sure to have the fish in eating mode before one connects up an automated appetite control unit.
- This will in turn be an important premise for trusting an appetite control unit.
- the system identifies all objects in front of the camera. Based on learning, the camera will be able to identify the position and orientation in space of any object in relation to the camera. By analysing two or more images and identifying the arbitrary positioning on a unique object in these images, the system will be able to estimate the speed and direction of the individual objects.
- Every change in contrast and colour is analysed to form the basis for outline of the pattern.
- Each pattern element is grouped based on, for example, shape, size, contrast and colour.
- a mutual distance between given pattern elements gives identification of a main pattern, which is part of recognising the fish.
- Recognition of the main pattern on a fish can be related to such features as: - eye gill lid mouth dorsal fins ventral fins - tail fin
- An object which has been identified as a fish from approved position of the above mentioned main pattern is analysed with regard to being able to determine the volume of the object.
- the analysis determines the contour of the fish in each of the images from the cameras. From the displacement of the contours in each of the images from the cameras, the distance along the contour of the fish is calculated. This gives a surface orientated in space with an area which is now known. The analysis continues by searching for pattern groups beyond the above mentioned main pattern that can be identified and be placed in all the images, and the distance to all identifiable pattern groups is estimated. After this analysis, the system will have a surface in space with the shape of the fish independent of position or orientation. Based on the positioning of, for example, dorsal fins, mouth, eye, ventral fins and tail, the system is capable of calculating the volume of a vertical section of the fish which will be identical to the volume of half the fish. As the fish is symmetrical about the vertical section, the volume of the fish is calculated and thus the weight (displaced water).
- the system When one has identified a fish and its position, the system will find characteristic patterns on the fish, such as dots and variations in the fish scales and mutual distance between these. These patterns are unique to each fish and are used to identify individual fish. This ensures that the system will recognise if a fish is still in the image. This identity will prevent the average weight determinations being influenced by the same individual being average weight determined several times.
- the system is capable of estimating the density of fish per volume in relation to the depth.
- the number of fish in the image area is counted.
- the mutual distance between the fish is estimated.
- the speed of swimming is estimated. This provides an estimation of the number of fish per volume. Changes in the position, vertical position (in the depth) of the camera will give a measure of the fish density through the water column.
- the system From analysis of fish density, the system will be able to give an indication to feeding systems about the location of the fish in relation to the surface. Where the fish density increases in the uppermost part of the netpen before or during feeding there be will interest from the fish to get hold of some feed. When the fish density decreases in the uppermost layers of the netpen, the fish is satiated and the fish density will increase deeper in the netpen. Then the camera will also be able to count the increasing number of pellets in the netpen.
- the speed of these objects can be estimated in relation to the camera, as the system estimates distance between each series of images and as the time between the image series is known, the speed and direction of the particles are estimated.
- the particles that are identified as pellets one can estimate the flow velocity along three axes, as the average sinking velocity for any type of pellet is known.
- the system will estimate the swimming speed of individual fish. This gives an indication of the stress level of the fish based on the swimming speed of the fish.
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Environmental Sciences (AREA)
- Engineering & Computer Science (AREA)
- Zoology (AREA)
- Animal Husbandry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Marine Sciences & Fisheries (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Farming Of Fish And Shellfish (AREA)
- Image Processing (AREA)
Abstract
A method and system for registration of predominately freely moving objects in a fish farm netpen are described, in which a camera housing (2) with a number of underwater cameras, is submerged in the netpen suspended from a cable (20). Each camera (1a, 1 b, 1c) takes individual images, at respective angles, of objects that freely pass the camera housing and sends said images to a computer processing unit (5) and the computer processing unit (5) analyses the images taken at different angles to determine the main pattern of the objects, by grouping each pattern element based on relations between shape, size, contrast and/or colour, and to determine mutual distance between given pattern elements for identification of the main pattern and determine, based on the main pattern, whether the objects are fish (10), pellets (11), faeces (12) or other unknown elements.
Description
Means and method for average weight determination and appetite feeding.
The present invention relates to a method and a system as described in the preamble of the respective independent claims and is especially concerned with registration of predominately freely moving objects in a netpen of a fish farm.
The fish farming industry still has a number of imperfect and labour intensive technical challenges with regard to a more efficient operation.
A need for good growth, low feeding factor, environment and more frequent reporting of average weights and biomass are also demands which in recent times have become more and more topical. These together constitute the important elements for increased profitability.
Here the use of an underwater camera has, in different ways, been a recognised tool used for average weight determination and control of feeding.
However no completely automated solution has been developed and introduced to the market to measure the average weight of fish and, at the same time function, as a tool for feeding of the fish as a simple and maintenance friendly combined solution.
From brochures from Akva Group ASA, Storvik A/S, Poro and Vaka As, a technique is known with regard to average biomass weight measuring in netpens and video analysis which counts feed pellets. Vicass, shown on a web page for Aquagroup ASA, is an average weight determiner which consists of two cameras in a frame. This has a great flaw in that it can only take two- dimensional images of fish, i.e. breadth and length and, in addition, it functions only when the fish swims perpendicularly to the direction of the camera, in addition it must be carried out manually and painstakingly to get reliable and sufficient images of the fish. This is therefore heavy going and time-consuming to use in a large netpen in a fish farm.
The average weight determiner from Vaki and Storvik advertised in the magazine Norsk Fiskeoppdrett consists of a frame which the fish must swim through. The problem is that the largest fish refuse to swim through the measuring frame with the result being that the average weight which is
measured is too small, i.e. the population has too many small fish in relation to large fish. The measurements can thereby be in doubt. These frames are also manual and often require calibrations which make them not very effective as a stationary device.
None of the above mentioned units are either constructed or suited as a tool for pellet counting and, at the same time, be used for appetite control of the feeding.
Some years ago in Norsk Fiskeoppdrett, Poro AB, Sweden introduced a pellet camera and a programme which counted pellets pointing downwards towards the bottom of the netpen. This did not function satisfactorily as the faeces (excrement) from the fish could not be distinguished from the feed pellets and therefore this measuring method was not greatly successful. In addition, there was no information that the pellet detection was carried out at the correct location in the netpen to thereby be able to rely upon the control of the feeding.
Akva Group has a Doppler sensor with a camera as a feed sensor for appetite feeding. This can also not count the fish in the feeding zone which is an important tool for the appetite feeding and will give an incorrect registration when the fish are found deep in the sea. In addition, it appears that the amount of pellets is influenced by the fish and faeces near the sensor. This was solved by encapsulating the sensor in a cage of net. The result was increased maintenance and cleaning.
Neither the Poro camera nor the Doppler can measure the average weight of the fish or count the fish in the measuring zone.
Known from NO20050517 is a method and device where a number of cameras are used, preferably CCD cameras, to register images of fish which move past the camera in a transfer channel. The signals from said camera are processed in a computer to calculate the volume of each fish. During registration, the fish is illuminated by at least two light sources and is registered by at least two cameras placed around the transfer channel, such that reflected light or silhouettes of the fish from opposite sides of the fish is registered, to form a complete photographic recording of the transverse dimension of the fish over the length of the fish. This is used as the basis to calculate the weight of the fish.
Furthermore, said transfer channel is necessary so that one fish shall be pumped or shall swim past and also that it is necessary to estimate the speed of the fish so that the area of average profiles of the fish can be calculated for determining the part volume of fish. These volume parts are later added to give a total volume of the fish.
GB 2 2001 772 A describes a method and device to determine the length measurements of the quality of farmed fish. The fish is forced to swim through a transparent channel or pipe where it is subjected to radiation from at least one radiation source. The radiation is registered by the photo detector in a number of cameras arranged in a row along the channel. The length of the fish can then be calculated in a computer according to the degree of masking in the photo detectors.
Known from GB 2 203 540 A is a method and apparatus for measuring, counting and classifying fish. The fish is forced along a curved track with detectors and associated transmitters. On its journey through the track the fish breaks the beam from a first light sensor and thereafter the beam from a second light sensor, and from the time between the break in the beams and the distance to the sensors one can determine the speed and the length of the fish. This is thereafter used to estimate the total size of the fish.
NO168151 describes a method and apparatus for counting fish. The fish is forced through a channel where a number of CCD line cameras are arranged, and with an associated light source on the opposite side. Fish which passes the light source form an area of shadow which the camera registers. Thereafter, the cross sectional area of the fish can be calculated, for example, in a computer, and built on the area registration the number of fish which has passed can be calculated by adding together all the registered areas and dividing the total area by the last calculated average area.
EP 0984391 A1 shows a counting device which, with the help of two simultaneously activated cameras, determines the number and size of fish which pass in a channel. The number of fish is counted with the help of size and direction which are estimated from images which are taken by the cameras.
In the present invention light sources and cameras or other irradiation sources assembled opposite each other in a transfer channel are not used. Correspondingly it is also unnecessary to force the fish individually through the channel. Common to all the cited documents is that the apparatus and the systems partly are large, expensive and not easy to handle. Furthermore it shall also be pointed out that the above mentioned documents only describe the technological background.
With the present invention the object is to solve the problems of biomass measuring and appetite control/feeding in one and the same device in the netpen in a simple, completely automated, maintenance friendly and efficient way.
The above mentioned object is achieved with a method for registration of predominately freely moving objects in a fish farm netpen as described in the independent claim 1 , in that a camera housing with a number of underwater cameras are submerged in the netpen, suspended from a cable. Each camera takes individual images, at respective angles, of objects which freely pass the camera housing and sends said images to a computer processing unit. The computer processing unit analyses the images taken from different angles to determine the main pattern of the object, by grouping each pattern element from the relationship between shape, size, contrast and/or colour and by determining the mutual distance between given pattern elements for identification of a main pattern and, to determine, based on the main pattern, whether the objects are fish, pellets, faeces or other unknown elements.
Alternative embodiments of the method are characterised in that an object which has been defined as a fish based on approved placing of said main pattern is analysed with respect to be able to determine the volume of the object.
The analysis can determine the contour of the fish in each of the images from the cameras, based on the displacement of the contour in each of the images from the cameras, to estimate the distance along the contour of the fish whereupon a surface orientated in space with a known area is provided, and to look for pattern groups beyond said main pattern that can be identified and be positioned in all the images, and to estimate the distance to all identifiable pattern groups.
Furthermore the analysis can comprise the steps: to provide a surface in space with the shape of the fish independent of position or orientation, and based on positioning of dorsal fins, mouth, eye, ventral fins and tail, to estimate the volume on a vertical section of the fish which will be identical to the volume of half of the fish, and thereafter estimate the volume of the fish and thereby the weight.
The following steps can be carried out for the recognition of an object, after the computer processing unit has defined a fish and its position, the characteristic pattern on the fish is decided such as spots and variations in the fish scales and the mutual distance between these where these patterns are unique to each fish, and to apply the characteristic features to identify individual objects.
The analysis can be used to count the number of fish in the area of the netpen, in that the number of fish in the image area is counted, the mutual distance between the fish is estimated, and the swimming speed is estimated, whereupon the number of fish per volume is calculated.
By altering the vertical depth position of the camera a measure for the fish density through the water column is provided.
After the weight and the number of fish or fish density have been determined by the computer processing unit, the counting of pellets can be activated as a parameter for appetite control for the appetite of the fish and a signal can be sent to a control unit for the control of a feed distributor.
The main pattern can be used to determine the amount of pellets and faeces in an area of the netpen.
The above mentioned object is also achieved with a system as given in the independent claim 10. The system is characterised in that at least three of said underwater cameras in the camera housing are all fixed mounted in the form of a triangle, mainly pointing in the same direction where each camera is arranged to take individual images at respective angles of objects which freely pass the camera housing and to send said images to a computer processing unit, with the computer processing unit being arranged to analyse the images taken from different angles to determine the main pattern of the objects by grouping each
pattern element based on the relationship between shape, size, contrast and/or colour, and by determining the mutual distance between given pattern elements for identification of a main pattern and to decide, based on the main pattern, whether the objects are fish, pellets, faeces or other unknown elements.
Alternative embodiments are characterised in that said underwater camera is orientated in a fixed frame or plate with an individual fixed distance, forming a rigid and fixed unit, and is arranged in a protruding and outer eccentric housing part in a ball formed housing.
The outer housing part can be arranged to an in-between lying housing part which in turn can be arranged to a stationary housing.
The housing can be connected to a ballast body via a stay.
Furthermore the housing can be equipped with an electronic compass so that position in relation to a given fixed point in the suspension system itself can be estimated with the help of the computer processing unit.
Reference is made to the enclosed figures which show an example of an embodiment of the invention, in which:
Figure 1a shows a netpen with a device according to the invention,
Figure 1b shows the device in more detail, Figure 2 shows the positioning of the cameras in the device according to the invention,
Figures 3a and 3b show the positioning of the cameras in the device in relation to an object,
Figures 4a, 4b, 4c show images taken by the device according to the invention, Figure 5a shows an object in a coordinate system, and
Figures 5b and 5c show converted images.
Fig.1a shows a netpen 15 in which is placed a closed unit 2, shown in detail in fig. 1b, containing three underwater cameras 1a, 1b and 1c in a rigid frame 16 with mutual fixed distance and angle pointing in the same direction towards a feeding area 26 with fish 10. The frame 16 with the cameras 1a, 1b and 1c form a triangle 1 which is preferably surrounded by one or more watertight and preferably ball-shaped housing 2, which in turn can be divided into a moveable,
doubly-connected housing 2a, 2b and a stationary part 2c, where the housing part 2a is eccentrically orientated as a protruding eye in relation to the parts 2b, 2c. Thereby to be able to move the triangle quickly over a large area and at the same time limit fouling, collection of food residues and to be as gentle as possible towards the fish such that sores do not appear, is achieved. The triangle housing 2 is shown designed as a closed housing for the protection of the electronics.
From each of the cameras 1a, 1b and 1c, a cable 17a, 17b and 17c, is attached, collected in a common cable 19 via a junction box 18 to which, according to the invention, other sensors 24 for temperature, oxygen, compass etc., can also be connected and which distribute signals and electricity transfer via a common cable 20, where this again also can contain signals and electricity supply to means for power transfer, for example, a gear motor 23 for rotation of the ball housing 2a, 2b.
The number of cables can, in this way, be minimised and it becomes a simpler installation with less maintenance. The cable 20 is led up to a control centre, processor or computer unit 8 via an underwater connection 21 , and placed on a feeding automat/distributor 9 or netpen floating collar 10 which in turn has a wireless communication to a central PC 5. It shall be pointed out that the computer processing unit does not need to be arranged as shown in the figures, but can, for example, be the mentioned PC 5. The unit 8 will in this case also be a communication unit. The processing unit 8 or the feeding automat/distributor 9 is connected to transport pipes for the feeding and can, as shown in fig. 1a, move the triangle housing 2 round in the netpen 15 lengthwise and depth wise, preferably via a suspension 6 with a winch 7. The positioning can take place automatically from the processor 8 for the best possible position in relation to the amount of fish, feed distribution, oxygen, current and wind.
In this way, the triangle housing 2 can be used for average weight measurements, counting the fish and counting feed pellets in one and same compact unit, in that images from the cameras 1a, 1b and 1c in the frame send images, such as three dimensional images, to the processor 8 and/or the PC 5, and where the fish is not damaged, stressed or alarmed by physical geometrical barriers in the netpen, at the same time as there is not an unnecessary number of criss-crossing cables causing problems for operational
safety and maintenance of the net case, such as, for example, cleaning of net bags 15 and sorting the fish, etc.
According to the invention one can imagine that the triangular ball housing 2 is programmed via the computer unit 8 to have a given position for the counting of the pellets and appetite control and another position covering the correct measurement area for average weight measurements or be positioned in relation to environmental conditions controlled by the processor or the computer unit 8 or the PC 5.
For stability and to compensate for large buoyancy caused by the volume of the triangular housing 2, a ballast body 25 is shown, for example, a ball connected to the lower part of the triangle housing 2c via a fixed stay 26.
Fig. 2 shows the cameras 1a, 1b and 1c orientated in relation to each other in the frame 16 and figs. 3a and 3b show the individual visual angles 27a, 27b and 27c of the three cameras covering one and the same fish 10 in arbitrary swimming position in relation to the fixed visual angles of the cameras seen from two sides.
Figs. 4a, 4b and 4c show how the cameras 1a, 1b and 1c individually show images of the coordinate position of the fish 10 on the screen so that the algorithm of the software can recognise the same fish 10 and identify the objects as fish 10, pellets 11 and faeces 12. As images are taken at the same time, the distance to, for example, the fish 10 is determined, and in addition the software can pick out the coordinates of the contour of, for example, the fish 10 in an arbitrary position swimming sidewise or up or down in relation to the cameras 1a, 1b and 1c.
The figures 5a, 5b and 5c show how the arbitrary position in space of the objects 10, 11 and 12 can be converted for all images of fish 10, pellets 11 and faeces 12 to a two-dimensional coordinate system and from the estimated polar coordinates of a side outline and a breadth outline easily identify and estimate the weight of the fish 10, count the fish 10, and count feed pellets 11 by separation of faeces 12.
In that there are three different camera images that are taken at the same time, one will have a dynamic correlation such that the determination of the
coordinates in space from each camera image will increase the accuracy of the measurements in that one will draw the outline in space from three positions which, with the help of the software, identify the polar coordinates of the outlines and the contour, and in this way one can interpolate the outer contours of the objects even if there is some overlapping in that, for example, one fish partially shades the measuring object itself or the fish 10 which is to be determined, pellets 11 which with the help of algorithms on the software shall be separated from the faeces 12, respectively, and thereafter be counted.
In this way one has attained a device which does not alarm the fish or damage the fish and which automatically can measure the average weight dynamically and with more images that form the basis for a more accurate and reliable average measurement of the fish.
In addition, pellets 11 can be separated out from the faeces 12 more easily such that the number of pellets measured in the feeding area can control the feed amounts from automated feed machines, feed buoys or feed distributers 9, and that one can, by counting the number of fish 10 in the area, be sure to have the fish in eating mode before one connects up an automated appetite control unit. This will in turn be an important premise for trusting an appetite control unit. In addition, one achieves in that images are taken from several cameras 1 and by taking a sufficient number of images, and also identification possibilities of, for example, the same pellet, in that this sinks down, to measure the angle deviation, distance and speed of sinking of this pellet 11 , for in this way to measure local currents in the water. This can in turn be an advantage with respect to where in the netpen it is appropriate to feed at any given time.
In the following, the mode of action of the system is described. The system identifies all objects in front of the camera. Based on learning, the camera will be able to identify the position and orientation in space of any object in relation to the camera. By analysing two or more images and identifying the arbitrary positioning on a unique object in these images, the system will be able to estimate the speed and direction of the individual objects.
To identify objects and categorise these, every change in contrast and colour is analysed to form the basis for outline of the pattern. Each pattern element is grouped based on, for example, shape, size, contrast and colour. A mutual
distance between given pattern elements gives identification of a main pattern, which is part of recognising the fish.
Recognition of the main pattern on a fish can be related to such features as: - eye gill lid mouth dorsal fins ventral fins - tail fin
Correspondingly, it will be possible to identify pellets, faeces and other unknown elements based on defined groupings of patterns.
An object which has been identified as a fish from approved position of the above mentioned main pattern is analysed with regard to being able to determine the volume of the object.
The analysis determines the contour of the fish in each of the images from the cameras. From the displacement of the contours in each of the images from the cameras, the distance along the contour of the fish is calculated. This gives a surface orientated in space with an area which is now known. The analysis continues by searching for pattern groups beyond the above mentioned main pattern that can be identified and be placed in all the images, and the distance to all identifiable pattern groups is estimated. After this analysis, the system will have a surface in space with the shape of the fish independent of position or orientation. Based on the positioning of, for example, dorsal fins, mouth, eye, ventral fins and tail, the system is capable of calculating the volume of a vertical section of the fish which will be identical to the volume of half the fish. As the fish is symmetrical about the vertical section, the volume of the fish is calculated and thus the weight (displaced water).
When one has identified a fish and its position, the system will find characteristic patterns on the fish, such as dots and variations in the fish scales and mutual distance between these. These patterns are unique to each fish and are used to identify individual fish. This ensures that the system will recognise if a fish is still in the image. This identity will prevent the average weight
determinations being influenced by the same individual being average weight determined several times.
From deviations in the pattern systems that form the basis for determination of a fish, these give an indication of the quality of an individual object. One will then analyse within the contour of the fish and look for patterns of known deviations that can be identified as:
Damages on fish caused by predators - Damages from fungi
Damages from bacteria Viral diseases
Parasites, such as attacks by lice Crippled individuals
Based on the movement pattern and orientation of the fish, it is possible to be able to discover sick or injured fish without causing apparent damage. Reports about the health of the individual fish in the netpen are generated from the above mentioned analysis.
The system is capable of estimating the density of fish per volume in relation to the depth. The number of fish in the image area is counted. The mutual distance between the fish is estimated. The speed of swimming is estimated. This provides an estimation of the number of fish per volume. Changes in the position, vertical position (in the depth) of the camera will give a measure of the fish density through the water column.
From analysis of fish density, the system will be able to give an indication to feeding systems about the location of the fish in relation to the surface. Where the fish density increases in the uppermost part of the netpen before or during feeding there be will interest from the fish to get hold of some feed. When the fish density decreases in the uppermost layers of the netpen, the fish is satiated and the fish density will increase deeper in the netpen. Then the camera will also be able to count the increasing number of pellets in the netpen.
From analysis of several images where objects are identified as identical over two or more series of images, the speed of these objects can be estimated in relation to the camera, as the system estimates distance between each series
of images and as the time between the image series is known, the speed and direction of the particles are estimated. For the particles that are identified as pellets, one can estimate the flow velocity along three axes, as the average sinking velocity for any type of pellet is known.
By identifying and following individual fish over several images, the system will estimate the swimming speed of individual fish. This gives an indication of the stress level of the fish based on the swimming speed of the fish.
Claims
1. Method for registration of predominately freely moving objects in a fish farm netpen, in which a camera housing (2) with a number of underwater cameras is submerged into the netpen, suspended from a cable (20), characterised in that each camera (1a, 1b, 1c) takes individual images at respective angles of objects which freely pass the camera housing and sends said images to a computer processing unit (8), and that the computer processing unit (8) analyses the images taken at different angles to determine a main pattern of the objects, by grouping each pattern element from the ratio between shape, size, contrast and/or colour, and by determining mutual distance between given pattern elements for identification of the main pattern, and to determine, based on the main pattern, whether the objects are fish
(10), pellets (11), faeces (12), or other unknown elements.
2. Method according to claim 1, characterised in that an object, which has been defined as a fish based on approved location of said main pattern, is analysed with regard to being able to determine the volume of the individual object.
3. Method according to claim 2, characterised in that the analysis determines the contour of the fish in each of the images from the cameras, by the following steps: from the displacement of the contour in each of the images from the cameras, to estimate distance along the contour of the fish, whereupon a surface orientated in space with a known area is generated, to search for pattern groups beyond said main pattern that can be identified and be positioned in all the images, and to estimate the distance to all identifiable pattern groups.
4. Method according to claim 3, characterised in that the analysis further comprises the steps: to provide a surface in space with the shape of the fish, independent of position or orientation, and from the position of dorsal fins, mouth, eye, ventral fins and tail, to estimate the volume of a vertical section of the fish that will be identical to the volume of half the fish, and thereafter estimate the volume of the fish and thereby its weight.
5. Method according to claim 2, characterised by the following steps for recognition of an individual object: after the computer processing unit (8) has defined a fish and its position, the characteristic pattern on the fish is determined, such as dots and variation in the fish scales and mutual distance between these, where these patterns are unique to each fish, and to apply the characteristic features to identify individual objects.
6. Method according to claim 5, characterised in that the analysis is used to count the number offish in an area of the netpen, in that the number offish in the image area is counted, the mutual distance between the fish is estimated, and the swimming speed is estimated, whereupon the number offish per volume is calculated.
7. Method according to claim 6, characterised in that the vertical depth position of the camera is altered to provide a measure of the fish density through the water column.
8. Method according to claims 1-7, characterised i n that after the weight, number of fish (10) or fish density have been estimated by the computer processing unit (8), counting of pellets (11) is activated as a parameter to the appetite control of the appetite of the fish, and to send a signal to a control unit to control a feed distributer (9).
9. Method according to claim 1, characterised in that the main pattern is used to determine the amount of pellets (11) and faeces (12) in an area of the netpen.
10. System for registration of predominately freely moving objects in a fish farm netpen, comprising a camera housing (2) with a number of underwater cameras, arranged to be submerged in the netpen, suspended from a cable (20), characterised in that at least three of said underwater cameras (1a, 1b, 1c) in the camera housing (2) are mutually fixedly mounted in the form of a triangle, pointing, in the main, in the same visual direction, where each camera is arranged to take individual images at respective angles of objects that freely pass the camera housing and to send said images to a computer processing unit (8), wherein the computer processing unit (8) is arranged to analyse the images taken from different angles to determine the main pattern of the objects, by grouping each pattern element from relations between shape, size, contrast and/or colour, and by determining the mutual distance between given pattern elements for identification of the main pattern and to determine, based on the main pattern, whether the objects are fish (10), pellets (11), faeces (12), or other unknown elements.
11. System according to claim 10, characterised in that said underwater cameras (1a, 1b, 1c) are orientated in a fixed frame or plate (16) at an individual fixed distance, forming a rigid and fixed unit and are arranged in a protruding and outer, eccentric housing part (2a) in a ball-formed housing (2).
12. System according to claim 11, characterised in that the outer housing part (2a) is arranged to an in-between lying housing part (2b), which in turn is arranged to a stationary housing (2c).
13. System according to claim 10, characterised in that the housing (2) is connected to a ballast body (25), via a stay (26).
14. System according to claim 10, characterised in that the housing (2) is equipped with an electronic compass (24), such that the position with regard to a given fixed point in the suspension system (6, 7) itself can be estimated with the help of the computer processing unit (8).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP08779101.8A EP2178362B1 (en) | 2007-07-09 | 2008-07-03 | Means and method for average weight determination and appetite feeding |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
NO20073563 | 2007-07-09 | ||
NO20073563 | 2007-07-09 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2009008733A1 true WO2009008733A1 (en) | 2009-01-15 |
Family
ID=40228777
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/NO2008/000254 WO2009008733A1 (en) | 2007-07-09 | 2008-07-03 | Means and method for average weight determination and appetite feeding |
Country Status (3)
Country | Link |
---|---|
EP (1) | EP2178362B1 (en) |
NO (1) | NO330863B1 (en) |
WO (1) | WO2009008733A1 (en) |
Cited By (47)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012030226A1 (en) * | 2010-08-31 | 2012-03-08 | Aage Skagen | Device for holding and positioning equipment at - and method for feeding fish in - a cage. |
WO2013053597A1 (en) * | 2011-10-12 | 2013-04-18 | Salvision As | Method and system for detecting a louse on fish |
CN103168731A (en) * | 2013-04-02 | 2013-06-26 | 中国水产科学研究院淡水渔业研究中心 | Multi-water-depth and multi-angle underwater fish camera system |
CN103238550A (en) * | 2013-05-18 | 2013-08-14 | 宁波市镇海秀洋广告装饰有限公司 | Automatic bait throwing device |
US20130223693A1 (en) * | 2010-08-31 | 2013-08-29 | Glenn Chamberlain | Methods and systems for determining fish catches |
WO2014098614A1 (en) * | 2012-12-20 | 2014-06-26 | Ebtech As | System and method for calculating physical dimensions for freely movable objects in water |
CN108601337A (en) * | 2016-02-05 | 2018-09-28 | 花王株式会社 | The individual discrimination method of zebra fish |
WO2019180698A1 (en) * | 2018-03-20 | 2019-09-26 | Giliocean Technology Ltd | Method and system for extraction of statistical sample of moving objects |
WO2020046523A1 (en) * | 2018-08-27 | 2020-03-05 | Aquabyte, Inc. | Optimal feeding based on signals in an aquaculture environment |
WO2020072438A1 (en) * | 2018-10-05 | 2020-04-09 | X Development Llc | Sensor positioning system |
CN111491508A (en) * | 2017-12-20 | 2020-08-04 | 英特维特国际股份有限公司 | System for fish ectoparasite monitoring in aquaculture |
CN111511202A (en) * | 2017-12-20 | 2020-08-07 | 英特维特国际股份有限公司 | System for fish ectoparasite monitoring in aquaculture |
ES2791551A1 (en) * | 2019-05-03 | 2020-11-04 | Inst Espanol De Oceanografia Ieo | PROCEDURE FOR THE IDENTIFICATION AND CHARACTERIZATION OF FISH AND AUTOMATIC FEED SUPPLY SYSTEM THAT MAKES USE OF THE SAME (Machine-translation by Google Translate, not legally binding) |
US10863727B2 (en) | 2015-10-22 | 2020-12-15 | Intervet Inc. | Method for automatic sea lice monitoring in salmon aquaculture |
JPWO2019172363A1 (en) * | 2018-03-09 | 2021-02-04 | 日本電気株式会社 | Information processing equipment, object measurement system, object measurement method and computer program |
WO2021038753A1 (en) * | 2019-08-28 | 2021-03-04 | ウミトロン ピーティーイー エルティーディー | Aquatic animal detection device, information processing device, terminal device, aquatic animal detection system, aquatic animal detection method, and aquatic animal detection program |
JP2021060421A (en) * | 2016-09-30 | 2021-04-15 | 日本電気株式会社 | Fish body length measurement system, fish body length measurement method, and fish body length measurement program |
EP4008179A1 (en) * | 2020-12-04 | 2022-06-08 | Siemens Aktiengesellschaft | Method and system for determining biomass of aquatic animals |
US20220245555A1 (en) * | 2019-06-19 | 2022-08-04 | Subc3D As | System and method for depiction and counting of external structures on a fish |
US11464213B2 (en) | 2017-06-28 | 2022-10-11 | Observe Technologies Limited | Decision making system and method of feeding aquatic animals |
US11475689B2 (en) | 2020-01-06 | 2022-10-18 | X Development Llc | Fish biomass, shape, size, or health determination |
US11490601B2 (en) | 2020-12-23 | 2022-11-08 | X Development Llc | Self-calibrating ultrasonic removal of ectoparasites from fish |
US11533861B2 (en) | 2021-04-16 | 2022-12-27 | X Development Llc | Control systems for autonomous aquaculture structures |
US11533893B2 (en) | 2017-12-20 | 2022-12-27 | Intervet Inc. | Method and system for external fish parasite monitoring in aquaculture |
US11594058B2 (en) | 2019-11-12 | 2023-02-28 | X Development Llc | Entity identification using machine learning |
US11611685B2 (en) | 2021-05-10 | 2023-03-21 | X Development Llc | Enhanced synchronization framework |
JP2023512412A (en) * | 2020-02-07 | 2023-03-27 | エックス デベロップメント エルエルシー | Camera winch control for dynamic surveillance |
US11623536B2 (en) | 2021-09-01 | 2023-04-11 | X Development Llc | Autonomous seagoing power replenishment watercraft |
US11632939B2 (en) | 2017-12-20 | 2023-04-25 | Intervet Inc. | System for external fish parasite monitoring in aquaculture |
US11657498B2 (en) | 2020-04-10 | 2023-05-23 | X Development Llc | Multi-chamber lighting controller for aquaculture |
US11659820B2 (en) | 2020-03-20 | 2023-05-30 | X Development Llc | Sea lice mitigation based on historical observations |
US11688196B2 (en) | 2018-01-25 | 2023-06-27 | X Development Llc | Fish biomass, shape, and size determination |
US11688154B2 (en) | 2020-05-28 | 2023-06-27 | X Development Llc | Analysis and sorting in aquaculture |
US11700839B2 (en) | 2021-09-01 | 2023-07-18 | X. Development | Calibration target for ultrasonic removal of ectoparasites from fish |
US11711617B2 (en) | 2021-05-03 | 2023-07-25 | X Development Llc | Automated camera positioning for feeding behavior monitoring |
JP2023104045A (en) * | 2022-01-17 | 2023-07-28 | 株式会社ミラック光学 | Primary industry product information collecting system |
US11737434B2 (en) | 2021-07-19 | 2023-08-29 | X Development Llc | Turbidity determination using computer vision |
US11778991B2 (en) | 2020-11-24 | 2023-10-10 | X Development Llc | Escape detection and mitigation for aquaculture |
US11821158B2 (en) | 2021-07-12 | 2023-11-21 | X Development Llc | Autonomous modular breakwater system |
US11825816B2 (en) | 2020-05-21 | 2023-11-28 | X Development Llc | Camera controller for aquaculture behavior observation |
US11842473B2 (en) | 2021-12-02 | 2023-12-12 | X Development Llc | Underwater camera biomass prediction aggregation |
US11864537B2 (en) | 2021-03-07 | 2024-01-09 | ReelData Inc. | AI based feeding system and method for land-based fish farms |
US11864536B2 (en) | 2021-05-14 | 2024-01-09 | X Development Llc | State-specific aquaculture feeder controller |
US11864535B2 (en) | 2021-12-21 | 2024-01-09 | X Development Llc | Mount for a calibration target for ultrasonic removal of ectoparasites from fish |
US11877549B2 (en) | 2021-11-22 | 2024-01-23 | X Development Llc | Controller for seaweed farm |
US12022811B2 (en) | 2014-08-27 | 2024-07-02 | Vaki Fiskeldiskerfi Hf | Automatic grading system for living aquatic organisms |
US12051222B2 (en) | 2021-07-13 | 2024-07-30 | X Development Llc | Camera calibration for feeding behavior monitoring |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
NO332103B1 (en) * | 2010-12-13 | 2012-06-25 | Ocea As | System and method for calculating the size of marine organisms in water |
NO20180299A1 (en) * | 2018-02-27 | 2018-11-05 | Nauplius Solutions As | Device for operation and maintenance of breeding cages. |
GB2570748B (en) * | 2018-09-04 | 2020-01-01 | Rovco Ltd | Subsea camera module and multi camera system |
NO20190203A1 (en) * | 2019-02-13 | 2020-03-25 | Stingray Marine Solutions As | A cage observation system with a submerged observation unit |
ES2786798B2 (en) * | 2019-04-11 | 2022-02-08 | Univ Oviedo | Biomass estimation system in aquaculture based on optical sensors and neural networks |
US20230172169A1 (en) * | 2021-12-02 | 2023-06-08 | X Development Llc | Underwater feed movement detection |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2201772A (en) | 1986-10-16 | 1988-09-07 | Papirind Forskningsinst | An opto-electronic method for determining by length-measurement the quality of cultured fish and a device for implementing the method |
GB2203540A (en) | 1987-04-01 | 1988-10-19 | Birtingur H F | Measuring, counting & classifying fish |
EP0984391A1 (en) | 1997-05-29 | 2000-03-08 | Core Corp. | Device for counting fish population passing through a fish pass |
JP2000201568A (en) * | 1999-01-18 | 2000-07-25 | Hitachi Ltd | Automatic feeding system for aquatic organism |
US20040023612A1 (en) * | 2002-08-02 | 2004-02-05 | Kriesel Marshall S. | Apparatus and methods for the volumetric and dimensional measurement of livestock |
EP1510125A1 (en) | 2003-08-26 | 2005-03-02 | Sociedad Comercial E Industrial Equa Limitada | Method for monitoring and controlling the non-consumed food in fish farms |
WO2005025309A1 (en) * | 2003-08-11 | 2005-03-24 | Kristian Lillerud | Method and device for recording and determining the weight of fish |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3101938B2 (en) * | 1996-03-27 | 2000-10-23 | 株式会社日立製作所 | Automatic feeding device and method for aquatic organisms |
-
2008
- 2008-07-03 WO PCT/NO2008/000254 patent/WO2009008733A1/en active Application Filing
- 2008-07-03 EP EP08779101.8A patent/EP2178362B1/en not_active Not-in-force
- 2008-07-03 NO NO20082999A patent/NO330863B1/en active IP Right Review Request
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2201772A (en) | 1986-10-16 | 1988-09-07 | Papirind Forskningsinst | An opto-electronic method for determining by length-measurement the quality of cultured fish and a device for implementing the method |
GB2203540A (en) | 1987-04-01 | 1988-10-19 | Birtingur H F | Measuring, counting & classifying fish |
EP0984391A1 (en) | 1997-05-29 | 2000-03-08 | Core Corp. | Device for counting fish population passing through a fish pass |
JP2000201568A (en) * | 1999-01-18 | 2000-07-25 | Hitachi Ltd | Automatic feeding system for aquatic organism |
US20040023612A1 (en) * | 2002-08-02 | 2004-02-05 | Kriesel Marshall S. | Apparatus and methods for the volumetric and dimensional measurement of livestock |
WO2005025309A1 (en) * | 2003-08-11 | 2005-03-24 | Kristian Lillerud | Method and device for recording and determining the weight of fish |
EP1510125A1 (en) | 2003-08-26 | 2005-03-02 | Sociedad Comercial E Industrial Equa Limitada | Method for monitoring and controlling the non-consumed food in fish farms |
Non-Patent Citations (1)
Title |
---|
See also references of EP2178362A4 |
Cited By (81)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103079401A (en) * | 2010-08-31 | 2013-05-01 | 奥格·斯卡根 | Device for holding and positioning equipment at - and method for feeding fish in - a cage |
US20130223693A1 (en) * | 2010-08-31 | 2013-08-29 | Glenn Chamberlain | Methods and systems for determining fish catches |
CN103079401B (en) * | 2010-08-31 | 2015-09-09 | 奥格·斯卡根 | For keep at cage place and positioning equipment device and in cage the method for feeding fish |
US9367930B2 (en) * | 2010-08-31 | 2016-06-14 | University Of Massachusetts | Methods and systems for determining fish catches |
WO2012030226A1 (en) * | 2010-08-31 | 2012-03-08 | Aage Skagen | Device for holding and positioning equipment at - and method for feeding fish in - a cage. |
WO2013053597A1 (en) * | 2011-10-12 | 2013-04-18 | Salvision As | Method and system for detecting a louse on fish |
WO2014098614A1 (en) * | 2012-12-20 | 2014-06-26 | Ebtech As | System and method for calculating physical dimensions for freely movable objects in water |
CN103168731A (en) * | 2013-04-02 | 2013-06-26 | 中国水产科学研究院淡水渔业研究中心 | Multi-water-depth and multi-angle underwater fish camera system |
CN103238550A (en) * | 2013-05-18 | 2013-08-14 | 宁波市镇海秀洋广告装饰有限公司 | Automatic bait throwing device |
US12022811B2 (en) | 2014-08-27 | 2024-07-02 | Vaki Fiskeldiskerfi Hf | Automatic grading system for living aquatic organisms |
US10863727B2 (en) | 2015-10-22 | 2020-12-15 | Intervet Inc. | Method for automatic sea lice monitoring in salmon aquaculture |
US11659821B2 (en) | 2015-10-22 | 2023-05-30 | Intervet Inc. | Method for automatic sea lice monitoring in salmon aquaculture |
EP3412147A4 (en) * | 2016-02-05 | 2019-09-04 | Kao Corporation | Individual identification method for zebrafish |
US10750723B2 (en) | 2016-02-05 | 2020-08-25 | Kao Corporation | Method of identifying individual zebrafish |
CN108601337A (en) * | 2016-02-05 | 2018-09-28 | 花王株式会社 | The individual discrimination method of zebra fish |
CN108601337B (en) * | 2016-02-05 | 2021-05-18 | 花王株式会社 | Individual identification method of zebra fish |
JP2021060421A (en) * | 2016-09-30 | 2021-04-15 | 日本電気株式会社 | Fish body length measurement system, fish body length measurement method, and fish body length measurement program |
JP7004094B2 (en) | 2016-09-30 | 2022-01-21 | 日本電気株式会社 | Fish length measurement system, fish length measurement method and fish length measurement program |
JP2021193394A (en) * | 2016-09-30 | 2021-12-23 | 日本電気株式会社 | Fish body length measuring system, fish body length measuring method, and fish body length measuring program |
JP7188527B2 (en) | 2016-09-30 | 2022-12-13 | 日本電気株式会社 | Fish length measurement system, fish length measurement method and fish length measurement program |
US11464213B2 (en) | 2017-06-28 | 2022-10-11 | Observe Technologies Limited | Decision making system and method of feeding aquatic animals |
US11925173B2 (en) | 2017-06-28 | 2024-03-12 | Observe Technologies Limited | Data collection system and method for feeding aquatic animals |
US11980170B2 (en) | 2017-12-20 | 2024-05-14 | Intervet Inc. | System for external fish parasite monitoring in aquaculture |
CN111491508A (en) * | 2017-12-20 | 2020-08-04 | 英特维特国际股份有限公司 | System for fish ectoparasite monitoring in aquaculture |
US11849707B2 (en) | 2017-12-20 | 2023-12-26 | Intervet Inc. | Method and system for external fish parasite monitoring in aquaculture |
US11533893B2 (en) | 2017-12-20 | 2022-12-27 | Intervet Inc. | Method and system for external fish parasite monitoring in aquaculture |
US11825814B2 (en) | 2017-12-20 | 2023-11-28 | Intervet Inc. | System for external fish parasite monitoring in aquaculture |
US11632939B2 (en) | 2017-12-20 | 2023-04-25 | Intervet Inc. | System for external fish parasite monitoring in aquaculture |
CN111511202A (en) * | 2017-12-20 | 2020-08-07 | 英特维特国际股份有限公司 | System for fish ectoparasite monitoring in aquaculture |
CN111491508B (en) * | 2017-12-20 | 2022-05-24 | 英特维特国际股份有限公司 | System for fish ectoparasite monitoring in aquaculture |
US11688196B2 (en) | 2018-01-25 | 2023-06-27 | X Development Llc | Fish biomass, shape, and size determination |
US11328439B2 (en) | 2018-03-09 | 2022-05-10 | Nec Corporation | Information processing device, object measurement system, object measurement method, and program storage medium |
JPWO2019172363A1 (en) * | 2018-03-09 | 2021-02-04 | 日本電気株式会社 | Information processing equipment, object measurement system, object measurement method and computer program |
JP7001145B2 (en) | 2018-03-09 | 2022-01-19 | 日本電気株式会社 | Information processing equipment, object measurement system, object measurement method and computer program |
CN111868472A (en) * | 2018-03-20 | 2020-10-30 | 吉利海洋科技有限公司 | System and method for extracting statistical samples of multiple moving objects |
WO2019180698A1 (en) * | 2018-03-20 | 2019-09-26 | Giliocean Technology Ltd | Method and system for extraction of statistical sample of moving objects |
WO2020046523A1 (en) * | 2018-08-27 | 2020-03-05 | Aquabyte, Inc. | Optimal feeding based on signals in an aquaculture environment |
JP7194815B2 (en) | 2018-10-05 | 2022-12-22 | エックス デベロップメント エルエルシー | Sensor positioning system |
US20220217952A1 (en) * | 2018-10-05 | 2022-07-14 | X Development Llc | Sensor positioning system |
EP4005376A1 (en) * | 2018-10-05 | 2022-06-01 | X Development LLC | Sensor positioning system for an aquaculture system |
WO2020072438A1 (en) * | 2018-10-05 | 2020-04-09 | X Development Llc | Sensor positioning system |
CN113260253B (en) * | 2018-10-05 | 2023-08-15 | X开发有限责任公司 | Sensor positioning system |
US11659819B2 (en) | 2018-10-05 | 2023-05-30 | X Development Llc | Sensor positioning system |
JP2022501021A (en) * | 2018-10-05 | 2022-01-06 | エックス デベロップメント エルエルシー | Sensor positioning system |
CN113260253A (en) * | 2018-10-05 | 2021-08-13 | X开发有限责任公司 | Sensor positioning system |
ES2791551A1 (en) * | 2019-05-03 | 2020-11-04 | Inst Espanol De Oceanografia Ieo | PROCEDURE FOR THE IDENTIFICATION AND CHARACTERIZATION OF FISH AND AUTOMATIC FEED SUPPLY SYSTEM THAT MAKES USE OF THE SAME (Machine-translation by Google Translate, not legally binding) |
US20220245555A1 (en) * | 2019-06-19 | 2022-08-04 | Subc3D As | System and method for depiction and counting of external structures on a fish |
WO2021038753A1 (en) * | 2019-08-28 | 2021-03-04 | ウミトロン ピーティーイー エルティーディー | Aquatic animal detection device, information processing device, terminal device, aquatic animal detection system, aquatic animal detection method, and aquatic animal detection program |
US11594058B2 (en) | 2019-11-12 | 2023-02-28 | X Development Llc | Entity identification using machine learning |
US11983950B2 (en) | 2019-11-12 | 2024-05-14 | X Development Llc | Entity identification using machine learning |
US11756324B2 (en) | 2020-01-06 | 2023-09-12 | X Development Llc | Fish biomass, shape, size, or health determination |
US11475689B2 (en) | 2020-01-06 | 2022-10-18 | X Development Llc | Fish biomass, shape, size, or health determination |
US11877062B2 (en) | 2020-02-07 | 2024-01-16 | X Development Llc | Camera winch control for dynamic monitoring |
JP7350181B2 (en) | 2020-02-07 | 2023-09-25 | エックス デベロップメント エルエルシー | Camera winch control for dynamic surveillance |
JP2023512412A (en) * | 2020-02-07 | 2023-03-27 | エックス デベロップメント エルエルシー | Camera winch control for dynamic surveillance |
US11659820B2 (en) | 2020-03-20 | 2023-05-30 | X Development Llc | Sea lice mitigation based on historical observations |
US11657498B2 (en) | 2020-04-10 | 2023-05-23 | X Development Llc | Multi-chamber lighting controller for aquaculture |
US11825816B2 (en) | 2020-05-21 | 2023-11-28 | X Development Llc | Camera controller for aquaculture behavior observation |
US11688154B2 (en) | 2020-05-28 | 2023-06-27 | X Development Llc | Analysis and sorting in aquaculture |
US11778991B2 (en) | 2020-11-24 | 2023-10-10 | X Development Llc | Escape detection and mitigation for aquaculture |
JP7494392B2 (en) | 2020-11-24 | 2024-06-03 | エックス デベロップメント エルエルシー | Escape detection and mitigation for aquaculture |
EP4008179A1 (en) * | 2020-12-04 | 2022-06-08 | Siemens Aktiengesellschaft | Method and system for determining biomass of aquatic animals |
US11690359B2 (en) | 2020-12-23 | 2023-07-04 | X Development Llc | Self-calibrating ultrasonic removal of ectoparasites from fish |
US11490601B2 (en) | 2020-12-23 | 2022-11-08 | X Development Llc | Self-calibrating ultrasonic removal of ectoparasites from fish |
US11864537B2 (en) | 2021-03-07 | 2024-01-09 | ReelData Inc. | AI based feeding system and method for land-based fish farms |
US11533861B2 (en) | 2021-04-16 | 2022-12-27 | X Development Llc | Control systems for autonomous aquaculture structures |
US11711617B2 (en) | 2021-05-03 | 2023-07-25 | X Development Llc | Automated camera positioning for feeding behavior monitoring |
US11611685B2 (en) | 2021-05-10 | 2023-03-21 | X Development Llc | Enhanced synchronization framework |
US11778127B2 (en) | 2021-05-10 | 2023-10-03 | X Development Llc | Enhanced synchronization framework |
US11864536B2 (en) | 2021-05-14 | 2024-01-09 | X Development Llc | State-specific aquaculture feeder controller |
US11821158B2 (en) | 2021-07-12 | 2023-11-21 | X Development Llc | Autonomous modular breakwater system |
US12051222B2 (en) | 2021-07-13 | 2024-07-30 | X Development Llc | Camera calibration for feeding behavior monitoring |
US11737434B2 (en) | 2021-07-19 | 2023-08-29 | X Development Llc | Turbidity determination using computer vision |
US11700839B2 (en) | 2021-09-01 | 2023-07-18 | X. Development | Calibration target for ultrasonic removal of ectoparasites from fish |
US11623536B2 (en) | 2021-09-01 | 2023-04-11 | X Development Llc | Autonomous seagoing power replenishment watercraft |
US12051231B2 (en) | 2021-11-12 | 2024-07-30 | X Development Llc | Analysis and sorting in aquaculture |
US11877549B2 (en) | 2021-11-22 | 2024-01-23 | X Development Llc | Controller for seaweed farm |
US11842473B2 (en) | 2021-12-02 | 2023-12-12 | X Development Llc | Underwater camera biomass prediction aggregation |
US11864535B2 (en) | 2021-12-21 | 2024-01-09 | X Development Llc | Mount for a calibration target for ultrasonic removal of ectoparasites from fish |
JP2023104045A (en) * | 2022-01-17 | 2023-07-28 | 株式会社ミラック光学 | Primary industry product information collecting system |
JP7473888B2 (en) | 2022-01-17 | 2024-04-24 | 株式会社ミラック光学 | Primary Industry Product Information Collection System |
Also Published As
Publication number | Publication date |
---|---|
NO330863B1 (en) | 2011-08-01 |
EP2178362A1 (en) | 2010-04-28 |
EP2178362A4 (en) | 2013-01-09 |
EP2178362B1 (en) | 2016-11-09 |
NO20082999L (en) | 2009-01-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2178362B1 (en) | Means and method for average weight determination and appetite feeding | |
Davis et al. | The video plankton recorder (VPR): design and initial results | |
WO2017204660A1 (en) | Arrangement and method for measuring the biological mass of fish, and use of the arrangement | |
KR101540707B1 (en) | Method for the automatic grading of abalone based on image processing technology | |
RU2469530C2 (en) | Device and method for providing information about animals as they pass through passage for animals | |
EP3316220B1 (en) | Method for determining tuna biomass in a water zone and corresponding system | |
CN111511201A (en) | System for fish ectoparasite monitoring in aquaculture | |
DK2777390T3 (en) | Fish sorting system for sorting fish in a towed nets | |
Beddow et al. | Predicting salmon biomass remotely using a digital stereo-imaging technique | |
CN116034917A (en) | Method and system for monitoring fish ectoparasites in aquaculture | |
Moore et al. | Physical constraints of chemoreception in foraging copepods | |
Zhang et al. | Measurement of swimming pattern and body length of cultured Chinese sturgeon by use of imaging sonar | |
WO2017001971A1 (en) | Method and system for measuring biomass volume and weight of a fish farming tank | |
CN116034916A (en) | Method and system for monitoring fish ectoparasites in aquaculture | |
Li et al. | Estimation of pig weight by machine vision: A review | |
Bhoj et al. | Image processing strategies for pig liveweight measurement: Updates and challenges | |
CN113920138A (en) | Cow body size detection device based on RGB-D camera and detection method thereof | |
EP4240146A1 (en) | Automatic scanning system for fish | |
Hassan et al. | Information fusion in aquaculture: A state-of the art review | |
CN110136192A (en) | A kind of ox body ruler algorithm detected based on deep learning and characteristic portion | |
Lee et al. | Weight estimation of the sea cucumber (Stichopus japonicas) using vision-based volume measurement | |
Lopes et al. | Fish farming autonomous calibration system | |
Minagawa et al. | Determining the weight of pigs with image analysis | |
JP7075765B2 (en) | Liquid content measuring device and method | |
JP7233688B2 (en) | Method and system for measuring substances in liquid |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 08779101 Country of ref document: EP Kind code of ref document: A1 |
|
DPE1 | Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101) | ||
DPE1 | Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101) | ||
DPE1 | Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101) | ||
NENP | Non-entry into the national phase |
Ref country code: DE |
|
REEP | Request for entry into the european phase |
Ref document number: 2008779101 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2008779101 Country of ref document: EP |