CN111827740A - Swimming pool monitoring system and method based on binocular vision - Google Patents
Swimming pool monitoring system and method based on binocular vision Download PDFInfo
- Publication number
- CN111827740A CN111827740A CN201910452662.5A CN201910452662A CN111827740A CN 111827740 A CN111827740 A CN 111827740A CN 201910452662 A CN201910452662 A CN 201910452662A CN 111827740 A CN111827740 A CN 111827740A
- Authority
- CN
- China
- Prior art keywords
- swimmer
- image
- processing unit
- binocular
- swimming pool
- 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.)
- Pending
Links
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E04—BUILDING
- E04H—BUILDINGS OR LIKE STRUCTURES FOR PARTICULAR PURPOSES; SWIMMING OR SPLASH BATHS OR POOLS; MASTS; FENCING; TENTS OR CANOPIES, IN GENERAL
- E04H4/00—Swimming or splash baths or pools
- E04H4/06—Safety devices; Coverings for baths
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/204—Image signal generators using stereoscopic image cameras
- H04N13/239—Image signal generators using stereoscopic image cameras using two 2D image sensors having a relative position equal to or related to the interocular distance
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
Abstract
Based on binocular vision swimming pool monitored control system, including binocular camera, image processing unit, central processing unit, alarm device, connecting wire, power. The swimming pool monitoring method based on binocular vision comprises the steps that a binocular camera shoots monitoring area images to obtain left and right images of a monitoring area; the image processing unit extracts images of swimmers in the left and right images by using a stereo cognition method and carries out stereo matching on the left and right images according to a binocular stereo imaging principle to obtain a three-dimensional coordinate space of the swimmers; the image processing unit tracks the swimmer track in the determined three-dimensional coordinate space and monitors the swimmer position; the central processing unit deduces whether the swimmer is drowned according to the swimmer motion track; when the drowning occurs, giving a drowning alarm and sending the data to an alarm device; the alarm device displays the position information of the drowning person and gives an alarm sound. The equipment is simple, low in cost and easy to install and maintain; the method for determining the position of the swimmer by binocular vision and three-dimensional cognition has high precision; the multidimensional alarm device can provide convenience for drowning rescue quickly and intuitively.
Description
Technical Field
The invention belongs to the technical field of safety monitoring, and particularly relates to a swimming pool monitoring system and method based on binocular vision.
Background
Swimming is a traditional hot sports, and due to the swimming technique of the swimmer or physical conditions, the swimmer often has drowning events. At present, the safety monitoring measures of the swimming pool mainly comprise the following measures: firstly, the common lifeguard monitors that the lifeguard scans swimmers in a responsibility area on a swimming pool lookout chair or monitors the condition of the whole swimming pool through a water camera, and when a suspected drowner is found, the lifeguard immediately launches for rescue, the method has low cost and wide application, but the lifeguard needs to keep high concentration of attention, needs to endure long-time mental stress and is easy to generate work fatigue; secondly, a swimmer carries a monitor, the swimmer carries a monitoring device similar to a trouser belt, a bracelet and the like, when the position of the swimmer is lower than a preset safety depth or exceeds a certain set time, the monitoring device gives an alarm, and in addition, a microphone system is used for monitoring the breathing and heartbeat sounds of the swimmer and further measuring the disappearance and appearing intervals of the sounds, so as to judge whether the swimmer drowns or not, but the method has the defects of high false alarm rate and high system installation, use and maintenance cost, so the method is not widely adopted; thirdly, adopt simple camera monitoring alarm system, place the camera in the swimming pool bottom or install in the pond four walls, the computer simply handles the calculation to the video, judges whether drowned emergence, because in indoor swimming pool scene, the surface of water fluctuation also can cause the influence to the calculation processing judgement of computer, if adopt camera monitoring to handle, has higher requirement to data acquisition and data processing.
Disclosure of Invention
In view of the above problems, the present invention aims to provide a binocular vision-based swimming pool monitoring system and method, which effectively optimize swimming pool data acquisition and processing and improve the accuracy of swimming pool monitoring by using a technical means of binocular vision for swimming pool monitoring.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a binocular vision based swimming pool monitoring system, comprising: the binocular camera, the image processing unit, the central processing unit, the alarm device, the connecting line and the power supply;
the binocular camera is arranged above the swimming pool monitoring area or on the wall and used for shooting images of the monitoring area;
the image processing unit is connected with the binocular camera through a connecting line and is used for analyzing the shot monitoring area image to obtain a video analysis result;
the central processing unit is connected with the image processing unit and the alarm device through connecting wires and is used for judging whether drowning occurs or not according to a video analysis result obtained by the image processing unit, transmitting the result to the alarm device and issuing a drowning alarm instruction;
the alarm device comprises an image display device and a buzzer, wherein the image display device is used for displaying the position information of a drowning person, and the buzzer is used for giving an alarm sound to prompt the drowning condition;
the power supply is used for providing energy for the swimming pool monitoring system, and can be a storage battery or an external power supply.
Furthermore, a polarizer can be additionally arranged in front of the binocular camera lens and used for reducing the influence of reflected light of the water surface of the swimming pool on shooting.
The invention also provides a swimming pool monitoring method based on binocular vision, which comprises the following steps: carrying out three-dimensional calibration on the binocular camera; shooting a monitoring area image by a binocular camera, and acquiring a left image and a right image of the monitoring area; the image processing unit extracts images of swimmers in the left and right images by using a stereo cognition method and performs stereo matching on the left and right images according to a binocular stereo imaging principle to obtain a three-dimensional coordinate space of the swimmers; the image processing unit tracks the swimmer in the three-dimensional coordinate space and monitors the position of the swimmer in real time; the central processing unit deduces whether the swimmer is drowned according to the swimmer motion track; when the central processing unit judges that drowning occurs, a drowning alarm instruction is given and relevant data is sent to the alarm device; the alarm device displays the position information of the drowning person and gives an alarm sound.
Further, the extracting of the swimmer image in the left and right images by using the stereo cognitive method and the stereo matching of the left and right images according to the binocular stereo imaging principle to obtain the three-dimensional coordinates of the swimmer space includes: preprocessing the left image and the right image of the monitoring area; intelligently recognizing the left image and the right image of the preprocessed monitoring area, determining the generalized cognitive characteristics before stereo matching, and establishing a matching relation between the left image and the right image of the monitoring area to identify the cognitive attribute of the swimmer; identifying one or more specific cognitive characteristics corresponding to the cognitive attributes according to the cognitive attributes of the swimmer; carrying out stereo matching according to a binocular stereo imaging principle; and establishing a three-dimensional coordinate space of the swimmer by combining the specific cognitive characteristics.
Further, the preprocessing of the left image and the right image of the monitoring area comprises filtering, noise reduction, white balance, distortion processing and radiation change.
Further, the generalized cognitive features comprise one or more of textures, outlines and colors; the specific cognitive features are contained within the generalized cognitive features; specific categories of the cognitive attributes include color, contour, surface texture, and geometry of the contour.
Further, tracking the swimmer with the determined three-dimensional coordinate space, monitoring the position of the swimmer in real time, performing matching track by adopting a Kalman filtering method and a Hungarian algorithm, judging whether the motion track of the current frame is matched with the motion track in the previous frame of record, and if so, continuing tracking and recording; if the matching fails, judging the target to be newly added, and adding the current new motion track into the historical tracking record; if no target associated with a track in the historical track record is detected for a consecutive number of frames, the missing track record is deleted.
Furthermore, the method for the central processing unit to infer whether the swimmer is drowned according to the swimmer motion trail is to judge according to the swimming speed of the swimmer and whether the extracted contour of the swimmer image is changed drastically, and when the swimming speed of the swimmer is lower and the contour is changed drastically, the swimmer is judged to be drowned.
The invention has the beneficial effects that: the equipment adopted by the invention is simple, low in cost and easy to install and maintain; the real-time position of the swimmer is determined by adopting a binocular vision and three-dimensional cognition method, and the accuracy is high; a multidimensional alarm device is added, so that convenience is brought to drowning rescue quickly and intuitively.
Drawings
Fig. 1 is a schematic flow chart of the binocular vision-based swimming pool monitoring method of the present invention.
Detailed Description
The following detailed description of the preferred embodiments of the present invention, taken in conjunction with the accompanying drawings, will make the advantages and features of the invention easier to understand by those skilled in the art, and thus will clearly and clearly define the scope of the invention.
The invention mainly aims to provide a swimming pool monitoring system and a swimming pool monitoring method, which can monitor the behavior and the action of swimming persons in real time and analyze the behavior and the action by detecting the moving speed and the position of a target in a swimming pool, ensure that the swimming persons in the swimming pool are in a safe situation, timely send out an alarm when danger is detected, inform a lifesaver of drowning and provide the position information of the drowned person, and facilitate the rescue of the lifesaver.
In order to achieve the above object, the present invention provides a binocular vision-based swimming pool monitoring system and method, wherein a binocular camera is disposed above or at the side of a swimming pool to capture images of an area of the swimming pool, an image processing unit extracts images of a swimmer from the captured images of the area of the swimming pool by using a stereo recognition method and performs stereo matching on the left and right images according to a binocular stereo imaging principle to obtain a three-dimensional coordinate space of the swimmer, and performs track tracking on the swimmer with the determined three-dimensional coordinate space to monitor the position of the swimmer in real time, and then can determine whether the swimmer is drowned in real time according to the moving track of the swimmer, thereby determining the safety of the.
Referring to fig. 1, the embodiment of the present invention specifically includes the following steps:
(1) carrying out three-dimensional calibration on a binocular camera, shooting images of a monitored area by using the calibrated binocular camera, and acquiring left images and right images of the monitored area;
(2) preprocessing a left image and a right image of a monitoring area;
(3) intelligently recognizing the left image and the right image of the preprocessed monitoring area, determining the generalized cognitive characteristics before stereo matching, and establishing a matching relation between the left image and the right image of the monitoring area to identify the cognitive attribute of the swimmer;
(4) identifying one or more specific cognitive characteristics corresponding to the cognitive attributes according to the cognitive attributes of the swimmer;
(5) carrying out stereo matching according to a binocular stereo imaging principle;
(6) establishing a three-dimensional coordinate space of the swimmer by combining the specific cognitive characteristics;
(7) the image processing unit tracks the swimmer in the three-dimensional coordinate space and monitors the position of the swimmer in real time;
(8) the central processing unit deduces whether the swimmer is drowned according to the swimmer motion track;
(9) when the central processing unit judges that drowning occurs, a drowning alarm instruction is given and relevant data is sent to the alarm device;
(10) the alarm device displays the position information of the drowning person and gives an alarm sound.
In the step (1), the binocular camera shoots the images of the monitored area, and the acquiring of the left image and the right image of the monitored area comprises: because every group binocular camera shoots the field of vision scope limited, when the swimming pool area is great, in order to ensure to the omnidirectional control of swimming pool, at the regional top of swimming pool or indoor swimming pool wall mounting multiunit binocular camera around, multiunit binocular camera shoots in order to ensure that binocular camera can the complete swimming pool image of shooing to the different regions of swimming pool simultaneously.
The stereo calibration of the binocular camera comprises the following steps:
respectively calibrating a left camera and a right camera of a binocular camera to obtain an internal reference matrix A of the binocular camera and a rotation matrix R of the left camera1And a rotation matrix R of the right camera2And the translation vector T of the left camera1And a translation vector T of the right camera2;
Calculating a rotation matrix R and a translation vector T between the left camera and the right camera according to the following formula:
the preprocessing the left image and the right image of the monitoring area in the step (2) comprises the following steps: a polarizer is additionally arranged in front of a lens of the binocular camera, so that the influence of the reflected light of the water surface of the swimming pool on shooting is reduced; and filtering, noise reduction, white balance, distortion processing and radiation change are carried out on the left image and the right image shot by the binocular camera.
The generalized cognitive features in the steps (3) and (4) comprise one or more of texture, contour and color; the specific cognitive features are contained within the generalized cognitive features; specific categories of the cognitive attributes include color, contour, surface texture, and geometry of the contour.
Performing stereo matching according to the binocular stereo imaging principle in the steps (5) and (6); establishing a three-dimensional coordinate space of the swimmer in combination with the specific cognitive features comprises: and carrying out three-dimensional matching based on the generalized cognitive features, combining limit constraint, searching corresponding points in left and right images, solving parallax by using a binocular three-dimensional imaging principle, recovering image depth information, further obtaining three-dimensional coordinates of the swimmer, and verifying a matching result by combining the specific cognitive features to create a three-dimensional coordinate space of the swimmer.
Performing track tracking on the swimmer with the three-dimensional coordinate space determined in the step (7), and monitoring the position of the swimmer in real time includes: matching tracks by adopting a Kalman filtering method and a Hungarian algorithm, determining a moving target in each frame of image after creating a three-dimensional coordinate space of a swimmer, recording the detected track in a variable table, and predicting the position of the next frame of different tracks by the Kalman filtering method according to the historical tracks recorded in the variable table;
on the other hand, different targets in the record list are matched with the track positions predicted by adopting a Kalman filtering method, the tracks in the record list are optimally matched by adopting a Hungarian algorithm according to the comparison result of the distance between the detection point and the prediction point and the threshold value, whether the motion track of the current frame is matched with the motion track in the record of the previous frame is judged, and if the motion track of the current frame is matched with the motion track in the record of the previous frame, the tracking record is continued; if the matching fails, judging the target to be newly added, and adding the current new motion track into the historical tracking record; if no target associated with a track in the historical track record is detected for a consecutive number of frames, the missing track record is deleted.
The method for the central processing unit to infer whether the swimmer is drowned according to the swimmer motion trail in the step (8) is to judge according to the swimming speed of the swimmer and whether the extracted swimmer image outline is violently changed, and specifically comprises the following steps: when the swimming speed of the swimmer suddenly becomes lower than the conventional swimming speed, the possibility of drowning of the swimmer can be judged; secondly, when the swimmer swims normally, the outline shape of the swimmer in the image is not obviously changed along with time, and when the outline of the swimmer is changed violently, the swimmer is judged to be drowned.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical solutions and the inventive concepts of the present invention with equivalent substitutions, changes, material substitutions, improvements, etc. within the technical scope of the present invention.
Claims (8)
1. The utility model provides a swimming pool monitored control system based on binocular vision which characterized in that includes: the binocular camera, the image processing unit, the central processing unit, the alarm device, the connecting line and the power supply;
the binocular camera is arranged above the swimming pool monitoring area or on the wall and used for shooting images of the monitoring area;
the image processing unit is connected with the binocular camera through a connecting line and is used for analyzing the shot monitoring area image to obtain a video analysis result;
the central processing unit is connected with the image processing unit and the alarm device through connecting wires and is used for judging whether drowning occurs or not according to a video analysis result obtained by the image processing unit, transmitting the result to the alarm device and issuing a drowning alarm instruction;
the alarm device comprises an image display device and a buzzer, wherein the image display device is used for displaying the position information of a drowning person, and the buzzer is used for giving an alarm sound to prompt the drowning condition;
the power supply is used for providing energy for the swimming pool monitoring system, and can be a storage battery or an external power supply.
2. The binocular camera of claim 1, wherein a polarizer is added in front of the lens of the binocular camera to reduce the effect of the reflected light from the water surface of the swimming pool on the photographing.
3. A swimming pool monitoring method based on binocular vision is characterized by comprising the following steps: carrying out three-dimensional calibration on the binocular camera; shooting a monitoring area image by a binocular camera, and acquiring a left image and a right image of the monitoring area; the image processing unit extracts images of swimmers in the left and right images by using a stereo cognition method and performs stereo matching on the left and right images according to a binocular stereo imaging principle to obtain a three-dimensional coordinate space of the swimmers; the image processing unit tracks the swimmer in the three-dimensional coordinate space and monitors the position of the swimmer in real time; the central processing unit deduces whether the swimmer is drowned according to the swimmer motion track; when the central processing unit judges that drowning occurs, a drowning alarm instruction is given and relevant data is sent to the alarm device; the alarm device displays the position information of the drowning person and gives an alarm sound.
4. The binocular vision based swimming pool monitoring method of claim 3, wherein the extracting of the swimmer image in the left and right images by using the stereo cognitive method and stereo matching of the left and right images according to the binocular stereo imaging principle to obtain the spatial three-dimensional coordinates of the swimmer comprises: preprocessing the left image and the right image of the monitoring area; intelligently recognizing the left image and the right image of the preprocessed monitoring area, determining the generalized cognitive characteristics before stereo matching, and establishing a matching relation between the left image and the right image of the monitoring area to identify the cognitive attribute of the swimmer; identifying one or more specific cognitive characteristics corresponding to the cognitive attributes according to the cognitive attributes of the swimmer; carrying out stereo matching according to a binocular stereo imaging principle; and establishing a three-dimensional coordinate space of the swimmer by combining the specific cognitive characteristics.
5. The pre-processing of the left and right images of the monitored area as claimed in claim 4, wherein pre-processing comprises filtering, noise reduction, white balance, warping, radial variation.
6. The intelligent cognition of the left image and the right image of the monitoring area which are preprocessed according to the claim 4, the generalized cognitive characteristics before the stereo matching are determined, and the matching relation between the left image and the right image of the monitoring area is established so as to identify the cognitive attributes of the swimmer, wherein the generalized cognitive characteristics comprise one or more of textures, outlines and colors; the specific cognitive features are contained within the generalized cognitive features; specific categories of the cognitive attributes include color, contour, surface texture, and geometry of the contour.
7. The binocular vision based swimming pool monitoring method as recited in claim 3, wherein the trajectory tracking is performed on the swimmers determining the three-dimensional coordinate space, the matching trajectories of the swimmers position are monitored in real time by adopting a Kalman filtering method and a Hungarian algorithm, whether the motion trajectory of the current frame is matched with the motion trajectory in the previous frame of record is judged, and if so, the tracking record is continued; if the matching fails, judging the target to be newly added, and adding the current new motion track into the historical tracking record; if no target associated with a track in the historical track record is detected for a consecutive number of frames, the missing track record is deleted.
8. The binocular vision based swimming pool monitoring method of claim 3, wherein the method of the central processing unit deducing whether the swimmer is drowned according to the swimmer's movement track is judged according to the swim speed of the swimmer and whether the extracted contour of the image of the swimmer is drastically changed, and it is judged that the swimmer is drowned when the swim speed of the swimmer is low and the contour drastically changes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910452662.5A CN111827740A (en) | 2019-05-28 | 2019-05-28 | Swimming pool monitoring system and method based on binocular vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910452662.5A CN111827740A (en) | 2019-05-28 | 2019-05-28 | Swimming pool monitoring system and method based on binocular vision |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111827740A true CN111827740A (en) | 2020-10-27 |
Family
ID=72912533
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910452662.5A Pending CN111827740A (en) | 2019-05-28 | 2019-05-28 | Swimming pool monitoring system and method based on binocular vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111827740A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113688724A (en) * | 2021-08-24 | 2021-11-23 | 桂林电子科技大学 | Swimming pool drowning monitoring method based on binocular vision |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1741083A (en) * | 2004-08-24 | 2006-03-01 | 盛大庆 | Drowning radio alarming device on swimnaing pool/seaside resort |
US20110074945A1 (en) * | 2009-09-29 | 2011-03-31 | Yuko Watanabe | Imaging apparatus |
CN107545247A (en) * | 2017-08-23 | 2018-01-05 | 北京伟景智能科技有限公司 | Three-dimensional cognitive approach based on binocular identification |
CN107566797A (en) * | 2017-09-07 | 2018-01-09 | 青岛博晶微电子科技有限公司 | A kind of drowned monitor and detection device of swimming pool |
CN108731587A (en) * | 2017-04-14 | 2018-11-02 | 中交遥感载荷(北京)科技有限公司 | A kind of the unmanned plane dynamic target tracking and localization method of view-based access control model |
US20190197867A1 (en) * | 2016-08-25 | 2019-06-27 | Meni Menashe Zinger | Sensor system and method |
-
2019
- 2019-05-28 CN CN201910452662.5A patent/CN111827740A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1741083A (en) * | 2004-08-24 | 2006-03-01 | 盛大庆 | Drowning radio alarming device on swimnaing pool/seaside resort |
US20110074945A1 (en) * | 2009-09-29 | 2011-03-31 | Yuko Watanabe | Imaging apparatus |
US20190197867A1 (en) * | 2016-08-25 | 2019-06-27 | Meni Menashe Zinger | Sensor system and method |
CN108731587A (en) * | 2017-04-14 | 2018-11-02 | 中交遥感载荷(北京)科技有限公司 | A kind of the unmanned plane dynamic target tracking and localization method of view-based access control model |
CN107545247A (en) * | 2017-08-23 | 2018-01-05 | 北京伟景智能科技有限公司 | Three-dimensional cognitive approach based on binocular identification |
CN107566797A (en) * | 2017-09-07 | 2018-01-09 | 青岛博晶微电子科技有限公司 | A kind of drowned monitor and detection device of swimming pool |
Non-Patent Citations (1)
Title |
---|
颜志国等: "《多摄像机协同关注目标检测跟踪技术》", 30 June 2017, 东南大学出出版社 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113688724A (en) * | 2021-08-24 | 2021-11-23 | 桂林电子科技大学 | Swimming pool drowning monitoring method based on binocular vision |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107622505B (en) | Drowning monitoring and detecting method for swimming pool | |
CN106022230B (en) | A kind of swimming pool drowning event detecting method based on video | |
CN104287946B (en) | Blind person's avoidance suggestion device and method | |
CN105894702A (en) | Invasion detecting alarming system based on multi-camera data combination and detecting method thereof | |
Shoaib et al. | View-invariant fall detection for elderly in real home environment | |
WO2002097758A1 (en) | Drowning early warning system | |
CN109766796B (en) | Deep pedestrian detection method for dense crowd | |
CN107229922A (en) | A kind of fatigue driving monitoring method and device | |
CN112165600B (en) | Drowning identification method and device, camera and computer system | |
CN109076190A (en) | Detect the device and method of abnormal conditions | |
KR100326203B1 (en) | Method and apparatus for face photographing and recognizing by automatic trading a skin color and motion | |
CN104484654B (en) | Anti- drowned recognition methods based on pattern-recognition and fingerprint matching location algorithm | |
Alshbatat et al. | Automated vision-based surveillance system to detect drowning incidents in swimming pools | |
CN112489371A (en) | Swimming pool drowning prevention early warning system based on computer vision | |
CN110852362B (en) | Drowning event detection method and device and computer readable storage medium | |
CN112270807A (en) | Old man early warning system that tumbles | |
CN113920461A (en) | Power grid operation and maintenance process image monitoring system and monitoring method | |
CN112309077A (en) | Drowning alarm method and drowning alarm device for swimming pool | |
CN112084963A (en) | Monitoring early warning method, system and storage medium | |
CN114219833A (en) | Overwater and underwater computer vision comprehensive drowning judgment system | |
CN111827740A (en) | Swimming pool monitoring system and method based on binocular vision | |
US20210150191A1 (en) | A Method and Apparatus for Detecting Drowning | |
CN209101365U (en) | A kind of cigarette stove all-in-one machine having unmanned identification function | |
CN107729874B (en) | Swimming pool drowning detection method based on space-time neighborhood characteristics | |
CN116342645A (en) | Multi-target tracking method for natatorium scene |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201027 |
|
RJ01 | Rejection of invention patent application after publication |