CN113761980A - Smoking detection method and device, electronic equipment and machine-readable storage medium - Google Patents
Smoking detection method and device, electronic equipment and machine-readable storage medium Download PDFInfo
- Publication number
- CN113761980A CN113761980A CN202010501062.6A CN202010501062A CN113761980A CN 113761980 A CN113761980 A CN 113761980A CN 202010501062 A CN202010501062 A CN 202010501062A CN 113761980 A CN113761980 A CN 113761980A
- Authority
- CN
- China
- Prior art keywords
- thermal imaging
- face
- picture
- scene
- monitoring
- 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
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 77
- 230000000391 smoking effect Effects 0.000 title claims abstract description 42
- 238000001931 thermography Methods 0.000 claims abstract description 114
- 238000012544 monitoring process Methods 0.000 claims abstract description 98
- 238000000034 method Methods 0.000 claims abstract description 27
- 238000004891 communication Methods 0.000 claims description 14
- 230000004044 response Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 9
- 238000009434 installation Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000009471 action Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000005764 inhibitory process Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Images
Landscapes
- Fire-Detection Mechanisms (AREA)
- Alarm Systems (AREA)
- Fire Alarms (AREA)
Abstract
The application provides a smoking detection method, a device, an electronic device and a machine-readable storage medium, wherein the method comprises the following steps: when a fire point exists in a monitoring scene, acquiring a thermal imaging picture and a visible light picture which are acquired by thermal imaging equipment of the monitoring scene; performing face detection on a first region in the visible light picture associated with a first position based on the first position of the fire point in the thermal imaging picture; and if the human face is detected, alarming. The method can realize automatic detection of smokers and improve smoking alarm efficiency and accuracy.
Description
Technical Field
The present application relates to the field of security, and in particular, to a smoking detection method and apparatus, an electronic device, and a machine-readable storage medium.
Background
In order to ensure the physical health of people and the safety of property, smoking inhibition in a designated area is a trend, for example, in places with large people flow, such as schools and hospitals, and in areas where fire hazard prevention is needed, such as fire inhibition areas in ports.
The current common smoking prohibition measures are to find the smoking condition in the smoking prohibition area by a manual inspection mode.
However, practice shows that in the above scheme, the manual inspection mode is time-consuming and labor-consuming, and the smoking detection efficiency is low.
Disclosure of Invention
In view of the above, the present application provides a smoking detection method, a smoking detection apparatus, an electronic device and a machine-readable storage medium.
According to a first aspect of embodiments of the present application, there is provided a smoking detection method, comprising:
when a fire point exists in a monitoring scene, acquiring a thermal imaging picture and a visible light picture which are acquired by thermal imaging equipment of the monitoring scene;
based on a first position of a fire point in the thermal imaging picture, carrying out face detection on a first area in the visible light picture, wherein the first area is associated with the first position;
and if the human face is detected, alarming.
According to a second aspect of embodiments of the present application, there is provided a smoking detection device comprising:
the device comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is configured to acquire a thermal imaging picture and a visible light picture which are acquired by a thermal imaging device of a monitoring scene when a fire point exists in the monitoring scene;
the detection unit is configured to detect a face of a first area in the visible light picture, wherein the first area is associated with a first position in the thermal imaging picture based on the first position of the fire;
and the alarm unit is configured to alarm if the detection unit detects the human face.
According to a third aspect of the embodiments of the present application, there is provided an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
and a processor for implementing the smoking detection method of the first aspect when executing the program stored in the memory.
According to a fourth aspect of embodiments of the present application, there is provided a computer-readable storage medium having stored therein a computer program which, when executed by a processor, implements the smoking detection method of the first aspect.
According to a fifth aspect of embodiments herein there is provided a computer program stored on a machine-readable storage medium and which, when executed by a processor, causes the processor to carry out the method of smoking detection of the first aspect.
According to the smoking detection method, when a fire point exists in a monitoring scene, a thermal imaging picture and a visible light picture which are acquired by thermal imaging equipment of the monitoring scene are acquired, and face detection is performed on a first area, associated with a first position, in the visible light picture based on the first position of the fire point in the thermal imaging picture; if the face is detected, an alarm is given, and the automatic detection of the smoker is realized by the alarm mode under the condition that the face is detected in the area associated with the fire point, so that the smoking alarm efficiency and accuracy are improved.
Drawings
FIG. 1 is a schematic flow diagram of a method of smoking detection shown in an exemplary embodiment of the present application;
FIG. 2 is a schematic flow diagram of another method of smoking detection shown in yet another exemplary embodiment of the present application;
FIG. 3 is a schematic flow chart illustrating a method for determining a second location of a fire within a monitored scene according to an exemplary embodiment of the present application;
fig. 4A is a schematic view of a smoke-forbidden area in a port according to an exemplary embodiment of the present application;
FIGS. 4B-4C are schematic diagrams of a method of determining GPS _ B and GPS _ C according to an exemplary embodiment of the present application;
FIG. 4D is a schematic illustration of a linkage zone shown in an exemplary embodiment of the present application;
FIG. 5 is a schematic diagram of a smoking detection device according to an exemplary embodiment of the present application;
FIG. 6 is a schematic structural view of another smoking detection device shown in yet another exemplary embodiment of the present application;
fig. 7 is a schematic diagram of a hardware structure of an electronic device according to an exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
In order to make the technical solutions provided in the embodiments of the present application better understood and make the above objects, features and advantages of the embodiments of the present application more comprehensible, the technical solutions in the embodiments of the present application are described in further detail below with reference to the accompanying drawings.
Referring to fig. 1, a schematic flow chart of a smoking detection method according to an embodiment of the present disclosure is shown in fig. 1, where the smoking detection method may include the following steps:
it should be noted that the execution subject in steps S100 to S120 may be a background server (may be referred to as a security platform) of the security system in the smoke-forbidden area.
In addition, the sequence numbers of the steps in the embodiments of the present application do not mean the execution sequence, and the execution sequence of each process should be determined by the functions and the internal logic of the process, and should not constitute any limitation on the implementation process of the embodiments of the present application.
And S100, when a fire point exists in the monitored scene, acquiring a thermal imaging picture and a visible light picture which are acquired by thermal imaging equipment of the monitored scene.
In the embodiment of the application, the fire detection can be performed on the monitored scene through the thermal imaging device, and the thermal imaging device does not have a face detection function generally, so that when the thermal imaging device detects the fire, the thermal imaging picture and the visible light picture can be reported to the security platform, and the security platform performs the face detection based on the thermal imaging picture and the visible light picture reported by the thermal imaging device.
For example, the thermal imaging device may track the fire when it is detected, and the thermal imaging device may periodically report the thermal imaging pictures and the visible light pictures before the fire leaves the monitoring range of the thermal imaging device.
Step S110, based on the first position of the fire point in the thermal imaging picture, carrying out face detection on a first area in the visible light picture, wherein the first area is associated with the first position.
In the embodiment of the application, since the position of the same target in the thermal imaging picture of the thermal imaging device and the position in the visible light picture are generally consistent, when the thermal imaging picture and the visible light picture of the monitored scene are acquired, the position of the fire point in the visible light picture can be determined based on the first position of the fire point in the thermal imaging picture, and based on the position, a region (referred to as a first region herein) for performing face detection is determined, and further, the face detection is performed on the first region of the visible light picture.
For example, assuming that the position of the fire point in the visible light picture is (x0, y0), a circular region within a preset radius range around (x0, y0) in the visible light picture may be determined as the first region.
And step S120, if the human face is detected, alarming.
In the embodiment of the application, the condition that the human face detection cannot be realized may occur in the visible light picture of the thermal imaging device in consideration of the fact that the quality of the visible light picture of the thermal imaging device is generally poor, so that when the visible light picture of a monitored scene is obtained, the human face detection can be performed on the first position of the visible light picture, and when the human face is detected, an alarm is given.
In one example, when a human face is detected in the acquired visible light picture acquired by the thermal imaging device, the human face may be further analyzed to determine whether the human face can be recognized.
When a face detected within the first region of the visible-light picture is identifiable, the associated person information may be identified based on the face image.
Correspondingly, when the smoking alarm is given, the personnel information related to the recognizable face can be output, for example, the personnel information related to the recognizable face is displayed through a display screen, or the personnel information related to the recognizable face is broadcasted through voice, so that the pertinence of the smoking alarm is improved.
For example, the person information associated with the recognizable face may include, but is not limited to, one or more of a name, identification information (e.g., an identification number), and a face image (e.g., a face image captured from a visible light picture, or a pre-stored face image of the person).
The security platform can give an alarm in a sound-light, voice or manual talkback mode.
It should be noted that, when a plurality of faces are detected in the first region of the visible light picture, each face may be identified separately, and when an alarm is given, the person information associated with each identifiable face (successfully identified face) is output.
Therefore, in the flow of the method shown in fig. 1, by acquiring the thermal imaging picture and the visible light picture acquired by the thermal imaging device when a fire point exists in the monitoring scene, performing face detection based on the acquired thermal imaging picture and the visible light picture, and giving an alarm when a face is detected, an automatic detection of a smoker is realized by performing an alarm in a manner that a face is detected in a region associated with the fire point, and the efficiency and accuracy of smoking alarm are improved.
In a possible embodiment, as shown in fig. 2, the smoking detection method provided in the embodiment of the present application may further include the following steps:
step S130, if the human face is not detected, determining a second position of the fire point in the monitoring scene based on the first position of the fire point in the thermal imaging picture.
And step S140, based on the second position, issuing a monitoring task to the video monitoring front end in the second area associated with the second position, so that the video monitoring front end receiving the monitoring task performs face detection.
And step S150, when face detection response information reported by the video monitoring front end is received, giving an alarm, wherein the face detection response information is sent when the video monitoring front end detects a face.
For example, when a human face is not detected in a first region of a visible light picture captured by a thermal imaging device, a location of a fire within a monitored scene (referred to herein as a second location) may be determined based on the first location of the fire in the thermal imaging picture, and a monitoring task may be issued to a video monitoring front end within a region associated with the second location (referred to herein as a second region) based on the second location.
For example, the second area may be a circular area within a preset radius from the second position as a center.
When the video monitoring front end in the second area receives the monitoring task, the automatic face detection can be carried out, and the camera lens is linked to carry out locking snapshot so as to carry out face snapshot.
When the video monitoring front end in the second area detects a human face, human face detection response information can be sent to the security platform to inform the security platform that the human face is detected.
It should be noted that, if the video monitoring front end does not detect a human face, but detects a human body, the video monitoring front end may also report human face detection response information to the security platform, so that the security platform gives an alarm; or, the video monitoring front end may track the detected human body until the tracked human body leaves the monitoring range of the camera, or report the human face detection response information to the security platform when a human face matched with the human body (matched by the position information of the human body and the human face) is detected.
When the security platform receives the face detection response information of the video monitoring front end, an alarm can be given.
In one example, to improve the pertinence of smoking alarm, when a human face is detected, the video monitoring front end may further analyze the human face to determine whether the human face can be identified. When the detected face is identifiable, the associated person information is identified based on the face image.
It should be noted that, under the condition that face recognition is required, when the video monitoring front end receives a monitoring task, if a recognizable face is not detected but a human body is detected, the video monitoring front end may track the detected human body until the tracked human body leaves the monitoring range of the camera, or detect a recognizable face matched with the human body (matched by the position information of the human body and the face).
When the video monitoring front end acquires the face identification information, the acquired face identification information can be reported to the security platform, that is, the face detection response information reported to the security platform by the video monitoring front end can include the face identification information.
When the security platform receives the face recognition information reported by the video monitoring front end, the security platform can give an alarm and output the received face recognition information.
For example, the person information associated with the recognizable face may include, but is not limited to, one or more of a name, identification information (e.g., an identification number), and a face image (e.g., a face snapshot reported by a face camera, or a pre-stored face image of the person).
Therefore, in the method flow shown in fig. 2, when the information of the smoker is not identified based on the visible light image of the thermal imaging device, the face detection can be performed by linking the video monitoring front end in the monitoring scene based on the position of the fire point in the monitoring scene, and an alarm is given when the face is detected, so that the probability of detecting the smoker is improved.
It should be noted that, in this embodiment of the application, after the security platform issues the monitoring task, the video monitoring front end that receives the monitoring task may report the face snapshot to the security platform instead of performing face recognition, and the security platform performs face recognition based on the received face snapshot to obtain face recognition information.
In addition, after the security platform determines that the fire point disappears from the monitoring range of the thermal imaging device, the monitoring task issued to the video monitoring front end can be cancelled, so that the video monitoring front end stops executing the monitoring task issued by the security platform.
In one example, referring to fig. 3, in step S130, determining a second location of the fire in the monitored scene based on the first location of the fire in the thermal imaging picture may be implemented by:
step S131, determining a third position in the monitoring scene corresponding to the first position based on the first position and the corresponding relation between the position information in the thermal imaging picture and the position information in the monitoring scene;
and S132, determining a second position of the fire point in the monitoring scene based on the third position, the installation position of the thermal imaging device and the upper limit and the lower limit of the preset height of the human body.
For example, determining the location of the fire in the monitored scene based on the location of the fire in the thermal imaging picture may be accomplished by establishing a correspondence between location information in the thermal imaging picture (e.g., coordinates in a thermal imaging picture coordinate system) and location information within the monitored scene (e.g., latitude and longitude).
However, it is considered that the position of the fire in the monitoring scene determined based on the above manner is the position of the fire point in the horizontal plane, i.e., the position of the fire point in the horizontal plane. However, in consideration of the height of the smoker, the position of the fire point determined in the above manner in the monitoring scene may be deviated from the position of the actual smoker, and therefore, it is necessary to further determine the position of the smoker based on the position of the fire point in the horizontal plane.
For example, the position of the fire in the monitoring scene corresponding to the first position (the position of the fire in the horizontal plane, referred to as a third position herein) may be determined based on the first position of the fire in the thermal imaging picture and the correspondence between the position information in the thermal imaging picture and the position information in the monitoring scene.
Further, a second location of the fire point within the monitored scene (which may be understood as a location of the smoker within the monitored scene) may be determined based on the third location, the mounting location of the thermal imaging device, and the preset upper and lower body height limits.
For example, the distance between the third position and the thermal imaging device in the horizontal direction may be determined based on the third position and the installation position of the thermal imaging device, and further, based on the distance, the installation height of the thermal imaging device, and the preset upper limit and the lower limit of the body height, the distance between the fire point position corresponding to the preset upper limit of the body height and the third position in the horizontal direction, and the distance between the fire point position corresponding to the preset lower limit of the body height and the third position in the horizontal direction may be determined.
It should be noted that, considering that the scene such as a harbor usually has a height relative to the horizontal plane, there is a deviation between the installation height of the thermal imaging device and the height relative to the horizontal plane, and there is a deviation between the height of the smoker and the height of the smoker relative to the horizontal plane, and therefore, in determining the second position, the height of the monitoring scene relative to the horizontal plane is also considered, and the specific implementation is described below with reference to specific examples.
In one example, the correspondence between the position information in the thermal imaging picture and the position information in the monitored scene may be determined based on the position of the preset reference object in the thermal imaging picture and the position of the preset reference object in the monitored scene.
In order to enable those skilled in the art to better understand the technical solutions provided by the embodiments of the present application, the technical solutions provided by the embodiments of the present application are described below with reference to specific examples.
Referring to fig. 4A, in this embodiment, the smoking detection in the smoke banned area of the harbor is taken as an example. As shown in fig. 4A, the smoke-forbidden area may be deployed with one or more thermal imaging cameras (two are taken as an example in the figure) and one or more video monitoring front ends (such as a human face and human body camera, a plurality of are taken as an example in the figure).
In this embodiment, a background server (which may be called a security platform) of a security system in a smoke-banned area in a port realizes a smoking detection process as follows (taking face recognition as an example):
1. when a fire point exists in a monitoring scene, acquiring a thermal imaging picture and a visible light picture which are acquired by thermal imaging equipment;
in this embodiment, the thermal imaging device may include a thermal imaging channel and a visible light channel, and the thermal imaging image of the monitored scene is acquired through the thermal imaging channel and the visible light image of the monitored scene is acquired through the visible light channel, respectively.
The thermal imaging device can detect fire points based on thermal imaging images acquired by the thermal imaging channel, trigger snapshot when the fire points are detected, obtain thermal imaging pictures of a monitored scene through the thermal imaging channel snapshot respectively, obtain visible light pictures of the monitored scene through the visible light channel snapshot, and report the thermal imaging pictures and the visible light pictures obtained through snapshot to a security platform.
2. Based on the position of the fire point in the thermal imaging picture, carrying out face detection on the visible light picture in the region associated with the position, and carrying out face recognition when the face is detected;
3. and if the recognizable face is detected, alarming and displaying the personnel information related to the recognizable face.
Illustratively, the security platform can be linked with an alarm device to perform smoking alarm, and the alarm mode includes but is not limited to acousto-optic, voice or manual talkback and the like.
4. And if the recognizable face is not detected, determining the position of the fire point in the monitoring scene based on the position of the fire point in the thermal imaging picture.
For example, the location in the monitored scene is a GPS (Global Positioning System) location (i.e., longitude and latitude).
To enable the determination of the GPS location of the target based on its location in the thermographic image, the location of the thermographic camera may be calibrated in advance, which includes but is not limited to: the position (GPS, mounting height) of the thermal imaging camera, the GPS position of a reference object (preferably an object with a fixed position, such as a building) within the field of view of the thermal imaging camera.
It should be noted that the calibration of the GPS position of the reference object is to determine the corresponding relationship between the coordinates in the coordinate system of the thermal imaging image and the GPS position, and since there is an error in the calibration of a single GPS position, the accuracy of the corresponding relationship can be improved by calibrating a plurality of reference objects and determining the corresponding relationship between the GPS position and the position in the thermal imaging image by combining a plurality of calibration point transformations, and the more the number of reference objects is, the higher the accuracy of the corresponding relationship can be, but the larger the computation amount is, so the number of reference objects can be determined based on the accuracy requirement and the processing performance.
Because the calibration points corresponding to the reference objects are related, the principle of calibrating the positions of the reference objects needs to be unified. Meanwhile, considering that a harbor area is an area close to a horizontal plane, for an object with a certain height, such as a building, a mountain and the like, the top GPS position and the bottom GPS position are deviated, and the bottom GPS position is closer to the actual longitude and latitude, so that when the reference object is calibrated, the horizontal plane calibration principle, that is, the reference object calibration is performed based on the GPS position at the bottom of the reference object.
For example, based on the GPS position of the reference object within the field of view of the thermal imaging camera and the coordinates of the reference object in the thermal imaging image of the thermal imaging camera, the correspondence of the coordinates in the thermal imaging image coordinate system to the GPS position may be determined.
Further, when a fire is detected, the GPS location of the fire may be determined based on the location of the fire in the thermal imaging picture reported by the thermal imaging camera.
Considering that the GPS position of the fire (referred to as GPS _ a herein) is determined according to the above correspondence, it is the GPS position when the fire is at the horizontal plane, and it does not consider the height of the smoker, and the height of the plane of the port smoking ban with respect to the horizontal plane.
In order to improve the accuracy of the fire point GPS position, the height range of the fire point relative to the horizontal plane can be determined based on the height of the plane of the smoke-banned area of the port relative to the horizontal plane (which needs to be configured in a security platform and is a fixed value) and the preset upper limit and lower limit of the height of the human body.
Based on the GPS position of the fire point when it is in the horizontal plane (i.e., GPS _ a), and the GPS position of the thermal imaging camera (assumed to be GPS _ R), the horizontal distance between GPS _ a and GPS _ R (assumed to be L0) can be determined, based on L0, and the height of the thermal imaging camera relative to the horizontal plane (the installation height of the thermal imaging camera + the height of the smoke-forbidden port area relative to the horizontal plane), the angle between the horizontal plane and the line connecting GPS _ a and the thermal imaging camera (assumed to be α) can be determined, and further, based on the angle, the upper and lower preset human body limits, and the height of the smoke-forbidden port area relative to the horizontal plane, the GPS position of the smoker can be determined.
For example, referring to fig. 4B and 4C, assuming that the height of the plane of the smoke-forbidden area of the port relative to the horizontal plane is 5 meters, and the upper limit and the lower limit of the height of the human body are 2.4 meters and 0.5 meter, respectively, the height of the fire point relative to the horizontal plane ranges from 5.5 meters to 7.4 meters.
Assuming that the horizontal distance between GPS _ a and GPS _ R is 50 meters, it can be determined that:
tanα＝10/50
as can be seen, α is about 11.31 °.
Further, the horizontal distance between the GPS position of the highest fire point (assumed to be GPS _ B) and GPS _ a can be determined:
l1 ═ 7.4/tan α ═ 37 m
I.e. the highest fire is actually 13 meters (50-37 ═ 13) from the thermal imaging camera.
Similarly, the horizontal distance between the GPS position of the lowest fire point (assumed to be GPS _ C) and GPS _ a can be determined:
l2 ═ 5.5/tan α ═ 27.5 m
I.e. the lowest fire is actually 22.5 meters (50-27.5 ═ 22.5) from the thermal imaging camera.
For example, after determining GPS _ B and GPS _ C, the security platform may determine that the actual location of the fire is within 50m of the range of the GPS _ B and GPS _ C, which may be schematically illustrated in fig. 4D.
5. And based on the position of the fire point in the monitoring scene, issuing a monitoring task to a human face human body camera in the area associated with the position.
Illustratively, when the human face camera in the area shown in fig. 4D receives the monitoring task, the human face camera can perform automatic human face detection, and perform locking snapshot by linking with the lens, and perform human face snapshot and human face recognition.
It should be noted that, when the human face and human body camera receives the monitoring task, if the recognizable human face is not detected but the human body is detected, the human face and human body camera may track the detected human body until the tracked human body leaves the monitoring range of the camera, or detect the recognizable human face matched with the tracked human body.
When the human face camera acquires the human face identification information, the acquired human face identification information can be reported to the security platform.
For example, when the security platform determines that the fire point disappears from the monitoring range of the thermal imaging camera and the duration time reaches a preset time (e.g., 30 seconds), the monitoring task can be cancelled, that is, a monitoring task cancelling instruction is issued to the human face human body camera, and when the human face human body camera receives the monitoring task cancelling instruction, the execution of the monitoring task issued by the security platform can be stopped.
6. And when the face recognition information reported by the face human body camera is received, alarming and displaying the received face recognition information.
In the embodiment of the application, when a fire point exists in a monitoring scene, a thermal imaging picture and a visible light picture which are acquired by thermal imaging equipment of the monitoring scene are acquired, and face detection is carried out on a first area which is associated with a first position in the visible light picture based on the first position of the fire point in the thermal imaging picture; if the face is detected, an alarm is given, and the automatic detection of the smoker is realized by the alarm mode under the condition that the face is detected in the area associated with the fire point, so that the smoking alarm efficiency and accuracy are improved.
The methods provided herein are described above. The following describes the apparatus provided in the present application:
referring to fig. 5, a schematic structural diagram of a smoking detection device according to an embodiment of the present application is shown in fig. 5, where the smoking detection device may include:
an obtaining unit 510, configured to obtain a thermal imaging picture and a visible light picture collected by a thermal imaging device of a monitoring scene when a fire exists in the monitoring scene;
a detection unit 520 configured to perform face detection on a first region associated with a first position in the visible light picture based on the first position of the fire in the thermal imaging picture;
and an alarm unit 530 configured to alarm if the detection unit detects a human face.
In a possible embodiment, as shown in fig. 6, the smoking detection device further comprises:
a determining unit 540 configured to determine a second position of the fire point within the monitored scene based on the first position of the fire point in the thermal imaging picture if the detecting unit 520 does not detect the human face;
the task issuing unit 550 is configured to issue a monitoring task to a video monitoring front end in a second area associated with a second position based on the second position, so that the video monitoring front end performs face detection and recognition;
the warning unit 530 is further configured to warn when receiving the face detection response information reported by the video surveillance front end, where the face detection response information is sent when the video surveillance front end detects a face.
In a possible embodiment, the determining unit 540 is specifically configured to determine, based on the first position and the correspondence between the position information in the thermal imaging picture and the position information in the monitored scene, a third position in the monitored scene corresponding to the first position;
and determining a second position of the fire point in the monitoring scene based on the third position, the installation position of the thermal imaging device and the preset upper limit and the lower limit of the height of the human body.
In a possible embodiment, the determining unit 540 is further configured to determine a corresponding relationship between the position information in the thermal imaging picture and the position information in the monitoring scene based on the position of the preset reference object in the thermal imaging picture and the position of the preset reference object in the monitoring scene.
Fig. 7 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present disclosure. The electronic device may include a processor 701, a communication interface 702, a memory 703, and a communication bus 704. The processor 701, the communication interface 702, and the memory 703 communicate with each other via a communication bus 704. Wherein, the memory 703 is stored with a computer program; the processor 701 may perform the above-described puff detection method by executing a program stored on the memory 703.
The memory 703, as referred to herein, may be any electronic, magnetic, optical, or other physical storage device that can contain or store information such as executable instructions, data, and the like. For example, the memory 702 may be: a RAM (random Access Memory), a volatile Memory, a non-volatile Memory, a flash Memory, a storage drive (e.g., a hard drive), a solid state drive, any type of storage disk (e.g., an optical disk, a dvd, etc.), or similar storage medium, or a combination thereof.
Embodiments of the present application also provide a machine-readable storage medium, such as the memory 703 in fig. 7, storing a computer program, which can be executed by the processor 701 in the electronic device shown in fig. 7 to implement the smoking detection method described above.
Embodiments of the present application also provide a computer program, which is stored in a machine-readable storage medium, such as the memory 703 in fig. 7, and when executed by a processor, causes the processor 701 to perform the smoking detection method described above.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (10)
1. A method of smoking detection, comprising:
when a fire point exists in a monitoring scene, acquiring a thermal imaging picture and a visible light picture which are acquired by thermal imaging equipment of the monitoring scene;
performing face detection on a first region in the visible light picture associated with a first position based on the first position of the fire point in the thermal imaging picture;
and if the human face is detected, alarming.
2. The method of claim 1, further comprising:
if the human face is not detected, determining a second position of the fire point in the monitoring scene based on a first position of the fire point in the thermal imaging picture;
based on the second position, issuing a monitoring task to a video monitoring front end in a second area associated with the second position so that the video monitoring front end performs face detection;
and when receiving the face detection response information reported by the video monitoring front end, giving an alarm, wherein the face detection response information is sent when the video monitoring front end detects a face.
3. The method of claim 2, wherein determining the second location of the fire within the monitored scene based on the first location of the fire in the thermographic image comprises:
determining a third position in the monitored scene corresponding to the first position based on the first position and the corresponding relation between the position information in the thermal imaging picture and the position information in the monitored scene;
and determining a second position of the fire point in the monitoring scene based on the third position, the installation position of the thermal imaging device and the upper limit and the lower limit of the preset height of the human body.
4. The method of claim 3, further comprising:
and determining the corresponding relation between the position information in the thermal imaging picture and the position information in the monitoring scene based on the position of a preset reference object in the thermal imaging picture and the position of the preset reference object in the monitoring scene.
5. A smoking detection device, comprising:
the device comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is configured to acquire a thermal imaging picture and a visible light picture which are acquired by a thermal imaging device of a monitoring scene when a fire point exists in the monitoring scene;
a detection unit configured to perform face detection on a first region associated with a first position in the visible light picture based on the first position of the fire in the thermal imaging picture;
and the warning unit is configured to give a warning if the detection unit detects a human face.
6. The apparatus of claim 5, further comprising:
a determining unit configured to determine a second position of the fire point within the monitored scene based on the first position of the fire point in the thermal imaging picture if the detecting unit does not detect a human face;
the task issuing unit is configured to issue a monitoring task to a video monitoring front end in a second area associated with the second position based on the second position so that the video monitoring front end performs face detection;
the warning unit is further configured to warn when face detection response information reported by the video monitoring front end is received, and the face detection response information is sent when a face is detected by the video monitoring front end.
7. The apparatus of claim 6,
the determining unit is specifically configured to determine a third position within the monitored scene corresponding to the first position based on the first position and a corresponding relationship between position information in the thermal imaging picture and position information within the monitored scene;
and determining a second position of the fire point in the monitoring scene based on the third position, the installation position of the thermal imaging device and the upper limit and the lower limit of the preset height of the human body.
8. The apparatus of claim 7,
the determining unit is further configured to determine a corresponding relationship between the position information in the thermal imaging picture and the position information in the monitoring scene based on the position of a preset reference object in the thermal imaging picture and the position of the preset reference object in the monitoring scene.
9. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method of any one of claims 1 to 4 when executing a program stored in the memory.
10. A machine readable storage medium, characterized in that a computer program is stored in the computer readable storage medium, which computer program, when being executed by a processor, carries out the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010501062.6A CN113761980B (en) | 2020-06-04 | 2020-06-04 | Smoking detection method, smoking detection device, electronic equipment and machine-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010501062.6A CN113761980B (en) | 2020-06-04 | 2020-06-04 | Smoking detection method, smoking detection device, electronic equipment and machine-readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113761980A true CN113761980A (en) | 2021-12-07 |
| CN113761980B CN113761980B (en) | 2024-03-01 |
Family
ID=78783795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010501062.6A Active CN113761980B (en) | 2020-06-04 | 2020-06-04 | Smoking detection method, smoking detection device, electronic equipment and machine-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113761980B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2618857A (en) * | 2022-05-13 | 2023-11-22 | Man Chee Liu | Cigarette smoke alarm device for non-smoking space |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009015519A (en) * | 2007-07-03 | 2009-01-22 | Omron Corp | Smoker detection device, smoker alarm system, smoker monitoring server, unextinguished cigarette alarm device, smoker detection method and smoker detection program |
| CN202196458U (en) * | 2011-08-24 | 2012-04-18 | 苏州飞锐智能科技有限公司 | Face recognition system |
| US20120262583A1 (en) * | 2011-04-18 | 2012-10-18 | Xerox Corporation | Automated method and system for detecting the presence of a lit cigarette |
| WO2013157466A1 (en) * | 2012-04-20 | 2013-10-24 | 株式会社デンソー | Smoking detection device, method and program |
| CN105530484A (en) * | 2015-12-30 | 2016-04-27 | 广州励丰文化科技股份有限公司 | Monitoring method and system under wearable device and multi-camera scene |
| WO2019051777A1 (en) * | 2017-09-15 | 2019-03-21 | 深圳传音通讯有限公司 | Reminding method and reminding system based on intelligent terminal |
| CN109635673A (en) * | 2018-11-22 | 2019-04-16 | 深圳爱莫科技有限公司 | Cigarette smoking recognition methods and device |
| CN109711307A (en) * | 2018-12-19 | 2019-05-03 | 中科天网（广东）科技有限公司 | A kind of smoking evidence collecting method based on recognition of face |
-
2020
- 2020-06-04 CN CN202010501062.6A patent/CN113761980B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009015519A (en) * | 2007-07-03 | 2009-01-22 | Omron Corp | Smoker detection device, smoker alarm system, smoker monitoring server, unextinguished cigarette alarm device, smoker detection method and smoker detection program |
| US20120262583A1 (en) * | 2011-04-18 | 2012-10-18 | Xerox Corporation | Automated method and system for detecting the presence of a lit cigarette |
| CN202196458U (en) * | 2011-08-24 | 2012-04-18 | 苏州飞锐智能科技有限公司 | Face recognition system |
| WO2013157466A1 (en) * | 2012-04-20 | 2013-10-24 | 株式会社デンソー | Smoking detection device, method and program |
| CN105530484A (en) * | 2015-12-30 | 2016-04-27 | 广州励丰文化科技股份有限公司 | Monitoring method and system under wearable device and multi-camera scene |
| WO2019051777A1 (en) * | 2017-09-15 | 2019-03-21 | 深圳传音通讯有限公司 | Reminding method and reminding system based on intelligent terminal |
| CN109635673A (en) * | 2018-11-22 | 2019-04-16 | 深圳爱莫科技有限公司 | Cigarette smoking recognition methods and device |
| CN109711307A (en) * | 2018-12-19 | 2019-05-03 | 中科天网（广东）科技有限公司 | A kind of smoking evidence collecting method based on recognition of face |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2618857A (en) * | 2022-05-13 | 2023-11-22 | Man Chee Liu | Cigarette smoke alarm device for non-smoking space |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113761980B (en) | 2024-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9767663B2 (en) | GPS directed intrusion system with data acquisition | |
| CN103726879B (en) | Utilize camera automatic capturing mine ore deposit to shake and cave in and the method for record warning in time | |
| CN111982291B (en) | Fire point positioning method, device and system based on unmanned aerial vehicle | |
| CN111604888B (en) | Inspection robot control method, inspection system, storage medium and electronic device | |
| CN109219836A (en) | Pass in and out limited community's monitoring system | |
| US9714833B2 (en) | Method of determining the location of a point of interest and the system thereof | |
| US11210529B2 (en) | Automated surveillance system and method therefor | |
| CN112215037B (en) | Object tracking method and device, electronic equipment and computer readable storage medium | |
| JP2023126352A (en) | Program, video monitoring method, and video monitoring system | |
| CN112288975A (en) | Event early warning method and device | |
| CN113761980A (en) | Smoking detection method and device, electronic equipment and machine-readable storage medium | |
| KR101046819B1 (en) | Method and system for watching an intrusion by software fence | |
| US10970982B2 (en) | Video surveillance apparatus and method | |
| CN113068000B (en) | Video target monitoring method, device, equipment, system and storage medium | |
| JP7031817B2 (en) | Surveillance systems, surveillance programs, and storage media | |
| KR102630275B1 (en) | Multi-camera fire detector | |
| KR102270858B1 (en) | CCTV Camera System for Tracking Object | |
| CN112036363B (en) | Smoking behavior detection method and device | |
| KR20180000205A (en) | Apparatus and method for intelligently analyzing video | |
| WO2011025359A1 (en) | System and method to determine suspicious behavior | |
| JP7354461B2 (en) | Monitoring system and method | |
| KR101942998B1 (en) | 3D FGIS omitted | |
| CN112330917B (en) | Method, device and system for positioning fire point | |
| KR101926435B1 (en) | Object tracking system using time compression method | |
| CN113963502B (en) | All-weather illegal behavior automatic inspection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |