CN111028480A - Drowning detection and alarm system - Google Patents
Drowning detection and alarm system Download PDFInfo
- Publication number
- CN111028480A CN111028480A CN201911244039.7A CN201911244039A CN111028480A CN 111028480 A CN111028480 A CN 111028480A CN 201911244039 A CN201911244039 A CN 201911244039A CN 111028480 A CN111028480 A CN 111028480A
- Authority
- CN
- China
- Prior art keywords
- detection
- drowning
- personnel
- module
- video
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/08—Alarms for ensuring the safety of persons responsive to the presence of persons in a body of water, e.g. a swimming pool; responsive to an abnormal condition of a body of water
Abstract
A drowning detection and alarm system comprises a high-performance embedded GPU computing device integrated with a video acquisition module, a personnel drowning detection module and an alarm module, wherein all modules run on the embedded GPU computing device, the video acquisition module decodes and converts a real-time video stream shot by a front-end camera to obtain video image data capable of being calculated, during detection, firstly video frame data of the front-end camera in a monitoring water area is acquired in real time through the video acquisition module, the personnel drowning detection module defines a detection area for the video frame data, then the personnel drowning detection module is utilized to carry out personnel detection on the video frame data in the defined detection area, once the condition that personnel drowning is found, an alarm signal is sent in time, and the drowning information of the personnel is sent to a background server; the invention is used for realizing all-weather 24-hour automatic real-time early warning of the drowning behavior of the personnel, effectively saves manpower and material resources, improves the accuracy, can be deployed at the front end, and is convenient and rapid.
Description
Technical Field
The invention relates to the technical field of video intelligent monitoring, in particular to a drowning detection and alarm system.
Background
Public parks developed in China have huge quantities of artificial lakes, reservoirs and lakes, and safety accidents are frequent in actual life due to the fact that safety measures are not in place, inspection is not forceful, monitoring is not effectively utilized and the like. It is therefore particularly important to be able to find the man overboard and to carry out rescue in the first moment.
The existing method for detecting people falling into water is mainly based on the traditional image processing algorithm, and the algorithm is greatly influenced by factors such as light, complex background, large lake surface fluctuation and the like, so that many false alarms are easily generated; and in addition, the method partially adopts a deep learning method to detect the drowning person, so that the interference caused by factors such as complex background and light can be effectively eliminated, but the method only collects the sample of the drowning person to carry out model training, and due to the fact that the postures of people are different in complex scenes, the interference is easy to generate, and the false alarm is also generated.
Disclosure of Invention
The present invention provides a drowning detection and alarm system to solve the above problems in the background art.
The technical problem solved by the invention is realized by adopting the following technical scheme:
a drowning detection and alarm system comprises a high-performance embedded GPU computing device integrated with a video acquisition module, a personnel drowning detection module and an alarm module, wherein, all modules run on the embedded GPU computing equipment, the video acquisition module utilizes ffmpeg or opencv software to decode and convert the real-time video stream shot by the front-end camera to obtain the video image data capable of being computed, and during detection, firstly, video frame data of a camera at the front end of a monitored water area is collected in real time through a video collecting module, a person falling water detecting module defines a detecting area for the video frame data, then the person falling water detecting module is used for carrying out person detection on the video frame data in the defined detecting area, once the person falling water condition is found, the alarm module sends an alarm signal in time, and sends the personnel falling water information to the background server to inform related personnel.
In the invention, the front-end camera and the high-performance embedded GPU computing equipment are arranged in a monitoring water area.
In the invention, the front-end camera is connected with the high-performance embedded GPU computing equipment through a TCP/IP protocol.
The invention also comprises a power supply which is connected with the front-end camera and the high-performance embedded GPU computing equipment.
In the invention, a memory is arranged in the high-performance embedded GPU computing equipment, and the memory is a detachable hard disk.
In the invention, the man falling water detection module and the alarm module are respectively arranged in a monitoring water area.
In the invention, a man falling water detection module acquires video image data of a monitored water area through a video acquisition module, then draws any polygon on the video image according to the shape of the monitored water area, demarcates a detection area, and stores 2D coordinate points of each vertex of the polygon demarcated the detection area; and detecting the video image data of the monitored water area by using an SSD target detection algorithm to obtain 2D coordinate points of all personnel central points in a video picture, finally obtaining a 2D coordinate point set of a delimited detection area polygon, judging whether all the personnel 2D coordinate points in the video image are in the delimited detection area polygon, if so, immediately sending an alarm signal, otherwise, entering the next round of detection.
In the invention, the alarm module sends an alarm signal to the background server through a TCP/IP protocol.
In the invention, an alarm is arranged in the alarm module.
Has the advantages that: the intelligent early warning system is integrated with a video image acquisition technology, a deep learning technology and a marking area detection technology, is used for realizing the automatic real-time early warning of the drowning behavior of people in 24 hours in all weather, effectively saves manpower and material resources, improves the accuracy, can be deployed at the front end, and is convenient and rapid.
Drawings
FIG. 1 is a flow chart illustrating a preferred embodiment of the present invention.
Fig. 2 is a schematic flow chart of a man-over-water detection module according to a preferred embodiment of the invention.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further explained below by combining the specific drawings.
Referring to fig. 1, a drowning detection and alarm system includes a video capture module, a people drowning detection module, an alarm module, and a high performance embedded GPU computing device (Nvidia jetson tx 2), all of which operate on the high performance embedded GPU computing device. The high-performance embedded GPU computing equipment is provided with software such as caffe, ffmpeg and opencv, the video acquisition module utilizes the ffmpeg or opencv software to decode and convert a real-time video stream shot by the front-end camera to obtain video image data capable of being computed, the high-performance embedded GPU computing equipment is respectively connected with the front-end camera, the personnel drowning detection module and the rear-end server, and the alarm module is connected with the personnel drowning detection module and the rear-end server; firstly, video frame data of a camera at the front end of a monitored water area are collected in real time through a video collecting module, a detection area is defined for the video frame data, personnel detection is carried out on the video frame data in the defined detection area through a personnel falling water detecting module, once the personnel falling water condition is found, an alarm signal is sent in time through an alarm module, personnel falling water information is sent to a background server, and related personnel are informed.
In the embodiment, the front-end camera is connected with the high-performance embedded GPU computing equipment through a TCP/IP protocol;
in this embodiment, the system further comprises a power supply, wherein the power supply is connected with the front-end camera and the high-performance embedded GPU computing equipment;
in this embodiment, a memory is arranged in the high-performance embedded GPU computing device, and the memory is a removable hard disk;
in the embodiment, the man falling water detection module and the alarm module are respectively arranged in a monitoring water area;
in this embodiment, as shown in fig. 2, the man-drowning detection module acquires video image data of a monitored water area through the video acquisition module, then draws any polygon on the video image according to the shape of the monitored water area, defines a detection area, and stores 2D coordinate points of each vertex of the polygon defining the detection area; and detecting the video image data of the monitored water area by using an SSD target detection algorithm to obtain 2D coordinate points of all personnel central points in a video picture, finally obtaining a 2D coordinate point set of a delimited detection area polygon, judging whether all the personnel 2D coordinate points in the video image are in the delimited detection area polygon, if so, immediately sending an alarm signal, otherwise, entering the next round of detection.
In this embodiment, the alarm module sends an alarm signal to the background server through a TCP/IP protocol.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. A drowning detection and alarm system is characterized by comprising a high-performance embedded GPU computing device integrated with a video acquisition module, a personnel drowning detection module and an alarm module, wherein all the modules run on the embedded GPU computing device, the video acquisition module utilizes ffmpeg or opencv software to decode and convert a real-time video stream shot by a front-end camera to obtain video image data capable of being calculated, when in detection, video frame data of the front-end camera in a monitoring water area are acquired in real time through the video acquisition module, the personnel drowning detection module defines a detection area for the video frame data, then the personnel drowning detection module is utilized to detect personnel for the video frame data in the defined detection area, once the condition that the personnel drowning is found, the alarm module sends an alarm signal in time and sends the information of the personnel drowning to a background server, and informing the relevant personnel.
2. The drowning detection and alarm system of claim 1, wherein the front-end camera and the high-performance embedded GPU computing device are installed in a monitored water area.
3. The drowning detection and alarm system of claim 2, wherein the front-end camera is connected with the high-performance embedded GPU computing device via TCP/IP protocol.
4. The drowning detection and alarm system of claim 1, wherein a memory is provided within the high performance embedded GPU computing device.
5. The system of claim 4, wherein the memory is a removable hard drive.
6. The drowning detection and alarm system of claim 1, wherein the drowning detection module and the alarm module are respectively disposed in a monitored water area.
7. The drowning detection and alarm system according to claim 1, wherein the drowning detection module acquires video image data of a monitored water area through the video acquisition module, then draws any polygon on the video image according to the shape of the area of the monitored water area, demarcates a detection area, and stores 2D coordinate points of each vertex of the polygon demarcating the detection area; and detecting the video image data of the monitored water area by using an SSD target detection algorithm to obtain 2D coordinate points of all personnel central points in a video picture, finally obtaining a 2D coordinate point set of a delimited detection area polygon, judging whether all the personnel 2D coordinate points in the video image are in the delimited detection area polygon, if so, immediately sending an alarm signal, otherwise, entering the next round of detection.
8. The drowning detection and alarm system according to claim 1, wherein the alarm module sends the alarm signal to the background server via a TCP/IP protocol.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911244039.7A CN111028480A (en) | 2019-12-06 | 2019-12-06 | Drowning detection and alarm system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911244039.7A CN111028480A (en) | 2019-12-06 | 2019-12-06 | Drowning detection and alarm system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111028480A true CN111028480A (en) | 2020-04-17 |
Family
ID=70204610
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911244039.7A Pending CN111028480A (en) | 2019-12-06 | 2019-12-06 | Drowning detection and alarm system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111028480A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111540173A (en) * | 2020-04-22 | 2020-08-14 | 上海振华重工电气有限公司 | Drowning alarm system and method based on intelligent picture recognition |
| CN112232299A (en) * | 2020-11-09 | 2021-01-15 | 江苏科技大学 | Automatic navigation method for rescuing drowning car based on deep learning |
| CN112489342A (en) * | 2020-11-26 | 2021-03-12 | 恒瑞通（福建）信息技术有限公司 | Village environment monitoring method and terminal serving for rural happy field |
| CN113688713A (en) * | 2021-08-18 | 2021-11-23 | 广东电网有限责任公司 | Cable protection method, device, system and medium based on dangerous behavior recognition |
| CN115311820A (en) * | 2022-07-11 | 2022-11-08 | 西安电子科技大学广州研究院 | Intelligent security system near water |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104134319A (en) * | 2014-08-13 | 2014-11-05 | 新昌县东茗乡德创机械厂 | Reservoir dangerous swimming area monitoring device |
| CN106448064A (en) * | 2016-09-12 | 2017-02-22 | 四川长虹电器股份有限公司 | Drowning early warning system and method based on intelligent mobile equipment |
| CN107122743A (en) * | 2017-04-28 | 2017-09-01 | 北京地平线机器人技术研发有限公司 | Security-protecting and monitoring method, device and electronic equipment |
| CN107578045A (en) * | 2017-09-19 | 2018-01-12 | 北京工业大学 | A kind of Underwater targets recognition based on machine vision |
| CN108111808A (en) * | 2017-11-30 | 2018-06-01 | 江西洪都航空工业集团有限责任公司 | A kind of overboard detection method based on real time video image analysis |
| CN109711261A (en) * | 2018-11-28 | 2019-05-03 | 山东师范大学 | A kind of indoor occupant localization method and device, building intelligence lighting system |
| JP2019091173A (en) * | 2017-11-13 | 2019-06-13 | 医療法人緑新会 | Support system |
| CN110110657A (en) * | 2019-05-07 | 2019-08-09 | 中冶赛迪重庆信息技术有限公司 | Method for early warning, device, equipment and the storage medium of visual identity danger |
| CN110119718A (en) * | 2019-05-15 | 2019-08-13 | 燕山大学 | A kind of overboard detection and Survivable Control System based on deep learning |
-
2019
- 2019-12-06 CN CN201911244039.7A patent/CN111028480A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104134319A (en) * | 2014-08-13 | 2014-11-05 | 新昌县东茗乡德创机械厂 | Reservoir dangerous swimming area monitoring device |
| CN106448064A (en) * | 2016-09-12 | 2017-02-22 | 四川长虹电器股份有限公司 | Drowning early warning system and method based on intelligent mobile equipment |
| CN107122743A (en) * | 2017-04-28 | 2017-09-01 | 北京地平线机器人技术研发有限公司 | Security-protecting and monitoring method, device and electronic equipment |
| CN107578045A (en) * | 2017-09-19 | 2018-01-12 | 北京工业大学 | A kind of Underwater targets recognition based on machine vision |
| JP2019091173A (en) * | 2017-11-13 | 2019-06-13 | 医療法人緑新会 | Support system |
| CN108111808A (en) * | 2017-11-30 | 2018-06-01 | 江西洪都航空工业集团有限责任公司 | A kind of overboard detection method based on real time video image analysis |
| CN109711261A (en) * | 2018-11-28 | 2019-05-03 | 山东师范大学 | A kind of indoor occupant localization method and device, building intelligence lighting system |
| CN110110657A (en) * | 2019-05-07 | 2019-08-09 | 中冶赛迪重庆信息技术有限公司 | Method for early warning, device, equipment and the storage medium of visual identity danger |
| CN110119718A (en) * | 2019-05-15 | 2019-08-13 | 燕山大学 | A kind of overboard detection and Survivable Control System based on deep learning |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111540173A (en) * | 2020-04-22 | 2020-08-14 | 上海振华重工电气有限公司 | Drowning alarm system and method based on intelligent picture recognition |
| CN112232299A (en) * | 2020-11-09 | 2021-01-15 | 江苏科技大学 | Automatic navigation method for rescuing drowning car based on deep learning |
| CN112232299B (en) * | 2020-11-09 | 2023-10-27 | 江苏科技大学 | Automatic navigation method for rescuing water-falling automobile based on deep learning |
| CN112489342A (en) * | 2020-11-26 | 2021-03-12 | 恒瑞通（福建）信息技术有限公司 | Village environment monitoring method and terminal serving for rural happy field |
| CN112489342B (en) * | 2020-11-26 | 2022-05-24 | 恒瑞通（福建）信息技术有限公司 | Village environment monitoring method and terminal serving for rural happy field |
| CN113688713A (en) * | 2021-08-18 | 2021-11-23 | 广东电网有限责任公司 | Cable protection method, device, system and medium based on dangerous behavior recognition |
| CN115311820A (en) * | 2022-07-11 | 2022-11-08 | 西安电子科技大学广州研究院 | Intelligent security system near water |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111028480A (en) | Drowning detection and alarm system | |
| CN107571977B (en) | FPGA-based autonomous lifesaving system and lifesaving method for small and medium water areas | |
| KR102095555B1 (en) | Analysis of illegal activities and monitoring based on recognition using unmanned aerial vehicle and artificial intelligence deep running that can monitor illegal activities in the field farm | |
| CN105611244B (en) | A kind of airport alien material detection method based on ball machine monitor video | |
| WO2019178851A1 (en) | Deep learning-based manhole cover loss detection system and method | |
| CN109996037B (en) | Safety monitoring method, device, equipment and system for water area | |
| CN106022230A (en) | Video-based detection method for drowning event in swimming pool | |
| CN108776937B (en) | Method and system for judging illegal ship fishing behavior based on binocular pan-tilt camera | |
| CN101188745B (en) | Intelligent drowning video monitoring system and method for natatorium | |
| CN104732726B (en) | Visitor waterborne identifies monitor supervision platform | |
| CN112362900A (en) | Unattended water level flow velocity monitoring camera and monitoring method | |
| CN110097787A (en) | A kind of ship collision warning monitoring system and method based on monitoring navigation light | |
| CN103366483A (en) | Monitoring alarm system | |
| CN112212922A (en) | Emergency water flow velocity monitoring equipment based on artificial intelligence technology | |
| CN204291242U (en) | A kind of intelligent monitoring for river drifting substances | |
| CN109238241B (en) | Vehicle-mounted automatic inspection system and inspection method for distribution line | |
| CN114627388B (en) | Foreign matter detection equipment and foreign matter detection method for power transmission line | |
| CN108111808B (en) | Drowning detection method based on real-time video image analysis | |
| CN113188000B (en) | System and method for identifying and rescuing people falling into water beside lake | |
| CN112347906B (en) | Method for detecting abnormal aggregation behavior in bus | |
| CN111383248A (en) | Method and device for judging red light running of pedestrian and electronic equipment | |
| CN112489372A (en) | Swimming pool monitoring and alarming system | |
| CN112233353A (en) | Artificial intelligence-based anti-fishing monitoring system and monitoring method thereof | |
| CN204948259U (en) | Based on the water quality monitoring instrument of digital picture | |
| CN207502720U (en) | A kind of airfield runway monitoring foreign bodies and removing guiding 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200417 |
|
| RJ01 | Rejection of invention patent application after publication |