CN111540173A - Drowning alarm system and method based on intelligent picture recognition - Google Patents
Drowning alarm system and method based on intelligent picture recognition Download PDFInfo
- Publication number
- CN111540173A CN111540173A CN202010320050.3A CN202010320050A CN111540173A CN 111540173 A CN111540173 A CN 111540173A CN 202010320050 A CN202010320050 A CN 202010320050A CN 111540173 A CN111540173 A CN 111540173A
- Authority
- CN
- China
- Prior art keywords
- alarm
- area
- picture
- network
- server
- 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
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/08—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/10—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using wireless transmission systems
Abstract
The invention discloses a drowning alarm system and method based on intelligent picture recognition, which comprises the following steps: the picture acquisition devices are provided with a plurality of pictures and are respectively arranged in a plurality of regions of a coast/a water bank; the processing server receives and identifies the pictures collected by the picture collecting device and judges whether to send an alarm or not; the alarm server sends an alarm to the rescue personnel; and the alarm linkage server sends an alarm to the site of the water falling area. The present invention addresses the deficiencies of the prior art.
Description
Technical Field
The invention relates to a drowning protection system, in particular to a drowning alarm system and method based on intelligent picture recognition.
Background
The safety protection of the traditional coast or water bank to falling into water mainly adopts physical isolation of the bank, the protection mode is quite passive, and once falling into water occurs, no effective alarm mechanism exists, and the safety protection is quite unfavorable for first-time rescue. In recent years, due to rapid development of the video monitoring industry, a video monitoring technology is partially developed, and alarm information can be sent out when people cross a pre-defined danger boundary line through low-intelligence technologies such as line-crossing alarm and the like.
Disclosure of Invention
In view of the above-mentioned drawbacks in the prior art, an object of the present invention is to provide a system and a method for warning drowning based on intelligent picture recognition, so as to solve the drawbacks in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
in one aspect, a drowning alarm system based on intelligent picture recognition comprises:
the picture acquisition devices are provided with a plurality of pictures and are respectively arranged in a plurality of regions of a coast/a water bank;
the processing server receives and identifies the pictures collected by the picture collecting device and judges whether to send an alarm or not;
the alarm server sends an alarm to the rescue personnel;
and the alarm linkage server sends an alarm to the site of the water falling area.
The picture acquisition device is a high-definition intelligent camera.
The picture acquisition device is connected with the processing server through a network, and the processing server is respectively connected with the alarm server and the alarm linkage server through the network.
The network is a wireless network or a wired network.
The network is a local area network or a wide area network.
The alarm linkage server sends out an alarm through broadcasting and an alarm lamp.
On the other hand, the drowning alarm method based on intelligent picture recognition is characterized in that the drowning alarm system is erected on the site at the coast/waterside, the picture acquisition device transmits the analysis result of the acquired picture content to the processing server, and the processing server comprehensively judges the situation of the site and adopts a corresponding alarm mode.
The picture acquisition device identifies the picture content of the monitored area, and the area is divided into an area A, an area B and an area C;
the area A is an area in the coast/water bank, the area B is a transition area from the coast/water bank to the water surface, and the area C is an area on the water surface.
The processing server makes the following comprehensive judgment:
identifying that ships enter the area C, and identifying the real-time pictures of the area A and the area B frame by frame;
recognizing that no ship enters the area in the area C, and when the area A and the area B recognize that people appear in the picture, the processing server positions the picture acquisition devices in the corresponding areas, and starts the alarm linkage server through a network to send out an alarm to the areas;
and recognizing the man overboard situation.
The man overboard situation is judged as follows:
when the B area identifies that a person appears in the picture, analyzes the condition that the person suddenly disappears or the body acceleration is abnormal, and judges that the person falls into the water, the processing server is linked with the alarm server through the network to send an alarm to rescue workers, and meanwhile, the processing server is linked with the alarm linkage server through the network to send an alarm to the site of the area falling into the water.
In the technical scheme, the drowning alarm system and method based on intelligent picture recognition provided by the invention have the advantages that different scenes are intelligently recognized, and then the system can automatically adopt different alarm modes, so that the false alarm rate is reduced, and the coping efficiency of a manager is increased.
Drawings
FIG. 1 is a schematic diagram of a framework of an embodiment of the drowning warning system of the present invention;
FIG. 2 is a schematic flow chart illustrating an embodiment of a water-out warning method according to the present invention;
FIG. 3 is a schematic diagram of the embodiment of the drowning warning method of the present invention for identifying the presence of personnel in the area A and the area B;
fig. 4 is a schematic diagram of identifying a man overboard situation in an embodiment of the overboard warning method of the present invention.
Detailed Description
The technical scheme of the invention is further explained by combining the drawings and the embodiment.
Referring to fig. 1, the drowning alarm system based on intelligent picture recognition provided by the present invention includes:
the picture collection system 1 chooses for use the intelligent camera that has the picture recognition function, is provided with a plurality ofly, arranges respectively in a plurality of regions of coast/water bank, still need consider angle and the effect of finding a view simultaneously.
And the processing server 2 is used for receiving and identifying the pictures collected by the picture collecting device and judging whether to send a water falling alarm or not.
And the alarm server 3 is used for sending a water-falling alarm to the relevant rescue workers.
And the alarm linkage server 4 is used for sending broadcast, warning lights and other related warnings to the site related to the water-falling area.
The picture acquisition device 1 is connected with the processing server 2 through a network 5, and the processing server 2 is respectively connected with the alarm server 3 and the alarm linkage server 4 through the network.
The network 5 adopts a wireless network mode or a wired network mode.
The network 5 may be a local area network or a wide area network.
Referring to fig. 2 to 4, the present invention further provides a water-falling alarm method based on intelligent picture recognition, wherein a water-falling alarm system is installed on the coast/waterside, the picture collecting device 1 sends the analysis result of the collected picture content to the processing server 2, and the situation occurring on the site is comprehensively judged by the algorithm on the processing server 2, and a corresponding alarm mode is adopted.
The algorithm deployed on the processing server 2 herein mainly refers to an algorithm for performing deep analysis according to an analysis result of the picture content acquired by the picture acquisition device 1, that is, an existing intelligent picture recognition analysis algorithm. The main identification and analysis steps comprise the following steps: 1) image enhancement, 2) image restoration, 3) feature extraction and 4) image identification. The first two steps are mainly to improve the quality of the digitized image as much as possible by technical means and reconstruct the image to the quality close to the quality of a real image. While the latter two steps are the core of the algorithm. Image segmentation represents an image as a collection of physically meaningful connected regions based on a priori knowledge of the target and the background. The image segmentation adopted in the invention can select a segmentation method based on region characteristics, a segmentation method based on correlation matching and a segmentation method based on boundary characteristics. The prior knowledge of the object and background herein refers to the characteristics of the image of a calm water surface, a ship, etc. And the image recognition carries out 'feature extraction' and 'feature classification' on the image obtained by image processing, and then the image is compared and matched with the feature elements in the preset scene, so that a corresponding conclusion is obtained.
The working process of the water falling alarm system is as follows:
first, the screen capture device 1 recognizes the screen content of the monitored area, and based on the previously divided areas, the area a is an area within the coast/water bank, the area B is a transition area from the coast/water bank to the water surface, and the area C is an area on the water surface.
Then, the processing server 2 makes the following comprehensive judgment:
and identifying that ships enter the area C, and identifying the real-time pictures of the area A and the area B frame by frame.
When the ship in the area C is identified to enter the area, and when the person in the picture is identified in the areas A and B, the processing server 2 positions the picture acquisition device 1 corresponding to the area, and the alarm linkage server 4 is linked through the network 5 to send out an alarm to the area by the equipment such as a broadcast, an alarm lamp and the like.
The situation that a person falls into water is identified and judged as follows:
and B, when the person appears in the picture, analyzing the condition that the person suddenly disappears or the body acceleration is abnormal, and judging that the person falls into water. At the moment, the processing server 2 can be positioned in the picture acquisition device 1 in the area, the network 5 is linked with the alarm server 3 to send information such as pictures and positions of the scene to related rescuers to inform the rescuers of the coming rescue, and meanwhile, the network 5 is linked with the alarm linkage server 4 to link sound and light equipment such as nearby broadcasts and alarm lamps and the like to remind surrounding personnel of falling into water, if the rescue is possible to be carried out in time, the rescuers are reminded of falling into water carefully.
Warning when no ship, prevent the warning of falling into water: in the area C captured by the screen capture device 1, the processing server 2 determines that the area is the water surface, and determines that the area is the non-operation time. If a person appears in the picture in the A/B area, the processing server 2 can link the alarm server 3 through the network 5 by judging the position of the picture acquisition device 1, and then link the equipment such as the broadcast and the like near the position of the picture acquisition device 1 through the network 5 and the alarm linkage server 4, and remind the person of falling into the water carefully through the pre-recorded voice.
The drowning rescue alarm when the ship is in motion: the ship is judged to approach in the area C acquired by the picture acquisition device 1, the processing server 2 judges the operation time, the processing server 2 compares the images in the picture frame by frame, and if the situation that people disappear suddenly or the body acceleration is abnormal is analyzed in the area B, the situation that people fall into water is judged. At the moment, the processing server 2 is linked with the alarm server 3 through the network 5, the alarm server 3 sends information of specific areas and sites related to alarm to related rescue workers through a preset program, and the alarm linked server 4 is also linked with broadcasting and warning lamps and the like on the sites to perform sound-light alarm to prompt that dangers happen in the areas, so that the personnel on the sites can timely rescue and pay attention to the safety of the personnel.
In the first embodiment, when a person mistakenly breaks into an area of a wharf or a port where entry is forbidden in a non-working time and is identified by the picture of the picture acquisition device 1, the person can alarm in a linkage manner through the processing server 2, and the broadcast in the area can play voice to remind the person to rapidly leave and carefully fall into water. Meanwhile, security personnel can check the specific conditions of the site through prompts popped up by the video monitoring system, and if the intruder does not leave, the security personnel can go to the site to perform treatment in time.
In the second embodiment, in the working time, when workers fall down to water in a wharf or a port area due to carelessness, the processing server 2 can be quickly linked with the alarm server 3 according to the picture identified by the picture acquisition device 1 to send the position of the water falling and the situation of the site to security personnel, the security personnel can quickly start an emergency rescue mechanism, and can be linked with the alarm system 4 to give an audible and visual alarm to the site to remind other workers on the site of carelessness of falling into water, rescue in time and warns themselves of the water falling.
It should be understood by those skilled in the art that the above embodiments are only for illustrating the present invention and are not to be used as a limitation of the present invention, and that changes and modifications to the above described embodiments are within the scope of the claims of the present invention as long as they are within the spirit and scope of the present invention.
Claims (10)
1. The utility model provides a drowning alarm system based on intelligent picture discernment which characterized in that includes:
the picture acquisition devices are provided with a plurality of pictures and are respectively arranged in a plurality of regions of a coast/a water bank;
the processing server receives and identifies the pictures collected by the picture collecting device and judges whether to send an alarm or not;
the alarm server sends an alarm to the rescue personnel;
and the alarm linkage server sends an alarm to the site of the water falling area.
2. The intelligent picture recognition-based drowning warning system according to claim 1, wherein: the picture acquisition device is a high-definition intelligent camera.
3. The intelligent picture recognition-based drowning warning system according to claim 1, wherein: the picture acquisition device is connected with the processing server through a network, and the processing server is respectively connected with the alarm server and the alarm linkage server through the network.
4. The intelligent picture recognition-based drowning warning system according to claim 3, wherein: the network is a wireless network or a wired network.
5. The intelligent picture recognition-based drowning warning system according to claim 3, wherein: the network is a local area network or a wide area network.
6. The intelligent picture recognition-based drowning warning system according to claim 1, wherein: the alarm linkage server sends out an alarm through broadcasting and an alarm lamp.
7. A drowning alarm method based on intelligent picture recognition is characterized in that: the drowning alarm system according to any one of claims 1 to 6 is erected on a coast/waterside site, the analysis result of the acquired picture content by the picture acquisition device is sent to the processing server, and the situation occurring on the site is comprehensively judged by the processing server to adopt a corresponding alarm mode.
8. The intelligent picture recognition-based drowning warning system according to claim 7, wherein: the picture acquisition device identifies the picture content of the monitored area, and the area is divided into an area A, an area B and an area C;
the area A is an area in the coast/water bank, the area B is a transition area from the coast/water bank to the water surface, and the area C is an area on the water surface.
9. The intelligent picture recognition-based drowning warning system according to claim 8, wherein: the processing server makes the following comprehensive judgment:
identifying that ships enter the area C, and identifying the real-time pictures of the area A and the area B frame by frame;
recognizing that no ship enters the area in the area C, and when the area A and the area B recognize that people appear in the picture, the processing server positions the picture acquisition devices in the corresponding areas, and starts the alarm linkage server through a network to send out an alarm to the areas;
and recognizing the man overboard situation.
10. The intelligent picture recognition-based drowning warning system of claim 9, wherein: the man overboard situation is judged as follows:
when the B area identifies that a person appears in the picture, analyzes the condition that the person suddenly disappears or the body acceleration is abnormal, and judges that the person falls into the water, the processing server is linked with the alarm server through the network to send an alarm to rescue workers, and meanwhile, the processing server is linked with the alarm linkage server through the network to send an alarm to the site of the area falling into the water.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010320050.3A CN111540173B (en) | 2020-04-22 | 2020-04-22 | Drowning alarm system and method based on intelligent picture recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010320050.3A CN111540173B (en) | 2020-04-22 | 2020-04-22 | Drowning alarm system and method based on intelligent picture recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111540173A true CN111540173A (en) | 2020-08-14 |
| CN111540173B CN111540173B (en) | 2021-07-27 |
Family
ID=71979432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010320050.3A Active CN111540173B (en) | 2020-04-22 | 2020-04-22 | Drowning alarm system and method based on intelligent picture recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111540173B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112382055A (en) * | 2020-10-26 | 2021-02-19 | 北京国睿信安科技有限公司 | Drowning prevention system applied to various water areas |
| CN112419665A (en) * | 2020-11-18 | 2021-02-26 | 上海电机学院 | Human near-water safety monitoring and alarming method based on target detection |
| CN113188000A (en) * | 2021-05-14 | 2021-07-30 | 太原理工大学 | Lake side downwater personnel identification rescue system and method |
| CN114913233A (en) * | 2022-06-10 | 2022-08-16 | 嘉洋智慧安全生产科技发展（北京）有限公司 | Image processing method, apparatus, device, medium, and product |
| 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 (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2054532A1 (en) * | 1990-11-01 | 1992-05-02 | Alfredo T. D. Valdez | Life-saving alarm for persons in a water medium |
| US20130214942A1 (en) * | 2012-02-21 | 2013-08-22 | Stephen Howard Joss | Man Overboard Detection, Tracking and Recovery |
| CN104268732A (en) * | 2014-09-30 | 2015-01-07 | 合肥三立自动化工程有限公司 | Intelligent multi-work-zone ship dispatching method based on digital channel |
| CN104506821A (en) * | 2015-01-07 | 2015-04-08 | 浙江省交通规划设计研究院 | Fast positioning system of ferry personnel falling into water based on digital image measurement |
| CN106940797A (en) * | 2017-04-28 | 2017-07-11 | 无锡北斗星通信息科技有限公司 | Identifying system based on image procossing |
| CN107154133A (en) * | 2017-06-22 | 2017-09-12 | 南京邮电大学 | A kind of regional early warning method based on defined position |
| WO2018232447A1 (en) * | 2017-06-19 | 2018-12-27 | Drone Sharks Pty Ltd. | A system and a method for monitoring a predetermined region in a water body |
| CN208922446U (en) * | 2018-11-27 | 2019-05-31 | 湖南联智桥隧技术有限公司 | A kind of overboard rescue alarm system in sea based on the LoRa communication technology |
| CN109840488A (en) * | 2019-01-24 | 2019-06-04 | 深圳市云恩科技有限公司 | A kind of ferry personal identification system and its recognition methods |
| CN110576951A (en) * | 2019-07-31 | 2019-12-17 | 安徽科微智能科技有限公司 | Water rescue system and method thereof |
| CN111028480A (en) * | 2019-12-06 | 2020-04-17 | 江西洪都航空工业集团有限责任公司 | Drowning detection and alarm system |
-
2020
- 2020-04-22 CN CN202010320050.3A patent/CN111540173B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2054532A1 (en) * | 1990-11-01 | 1992-05-02 | Alfredo T. D. Valdez | Life-saving alarm for persons in a water medium |
| US20130214942A1 (en) * | 2012-02-21 | 2013-08-22 | Stephen Howard Joss | Man Overboard Detection, Tracking and Recovery |
| CN104268732A (en) * | 2014-09-30 | 2015-01-07 | 合肥三立自动化工程有限公司 | Intelligent multi-work-zone ship dispatching method based on digital channel |
| CN104506821A (en) * | 2015-01-07 | 2015-04-08 | 浙江省交通规划设计研究院 | Fast positioning system of ferry personnel falling into water based on digital image measurement |
| CN106940797A (en) * | 2017-04-28 | 2017-07-11 | 无锡北斗星通信息科技有限公司 | Identifying system based on image procossing |
| WO2018232447A1 (en) * | 2017-06-19 | 2018-12-27 | Drone Sharks Pty Ltd. | A system and a method for monitoring a predetermined region in a water body |
| CN107154133A (en) * | 2017-06-22 | 2017-09-12 | 南京邮电大学 | A kind of regional early warning method based on defined position |
| CN208922446U (en) * | 2018-11-27 | 2019-05-31 | 湖南联智桥隧技术有限公司 | A kind of overboard rescue alarm system in sea based on the LoRa communication technology |
| CN109840488A (en) * | 2019-01-24 | 2019-06-04 | 深圳市云恩科技有限公司 | A kind of ferry personal identification system and its recognition methods |
| CN110576951A (en) * | 2019-07-31 | 2019-12-17 | 安徽科微智能科技有限公司 | Water rescue system and method thereof |
| CN111028480A (en) * | 2019-12-06 | 2020-04-17 | 江西洪都航空工业集团有限责任公司 | Drowning detection and alarm system |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112382055A (en) * | 2020-10-26 | 2021-02-19 | 北京国睿信安科技有限公司 | Drowning prevention system applied to various water areas |
| CN112419665A (en) * | 2020-11-18 | 2021-02-26 | 上海电机学院 | Human near-water safety monitoring and alarming method based on target detection |
| CN113188000A (en) * | 2021-05-14 | 2021-07-30 | 太原理工大学 | Lake side downwater personnel identification rescue system and method |
| CN113188000B (en) * | 2021-05-14 | 2022-07-01 | 太原理工大学 | System and method for identifying and rescuing people falling into water beside lake |
| CN114913233A (en) * | 2022-06-10 | 2022-08-16 | 嘉洋智慧安全生产科技发展（北京）有限公司 | Image processing method, apparatus, device, medium, and product |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111540173B (en) | 2021-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111540173B (en) | Drowning alarm system and method based on intelligent picture recognition | |
| CN110111516B (en) | Nuclear power station plant area security protection method and system | |
| CN111310556A (en) | Drowning prevention safety supervision system based on primary and middle school student area and monitoring method thereof | |
| CN105894735B (en) | A kind of intelligent vehicle-mounted fatigue monitoring system and method | |
| WO2022011828A1 (en) | System and method for detecting object that gets in and out of elevator, object detection system, elevator light curtain, and elevator device | |
| CN108275114B (en) | Oil tank anti-theft monitoring system | |
| CN110155274B (en) | Underwater intelligent lifesaving system for swimming pool | |
| CN108389359B (en) | Deep learning-based urban fire alarm method | |
| WO2018161849A1 (en) | Alarm system for falling in water based on image water texture and method therefor | |
| KR101036947B1 (en) | The automatic guard system to prevent the crime and accident using computer video image analysis technology | |
| KR100956978B1 (en) | The system which integrated manages a traffic accident notice area | |
| CN108647575A (en) | Drowned method for early warning based on optical visual analysis | |
| CN101188745A (en) | Intelligent drowning video monitoring system and method for natatorium | |
| CN202771441U (en) | Face recognition monitoring system | |
| JP3924171B2 (en) | Monitoring device for identifying monitoring objects | |
| CN106331605B (en) | A kind of floods detection system and method based on video | |
| CN112634561A (en) | Safety alarm method and system based on image recognition | |
| CN112382055A (en) | Drowning prevention system applied to various water areas | |
| CN114358609A (en) | Scenic spot tourism safety management system and method | |
| CN111028480A (en) | Drowning detection and alarm system | |
| CN108111808B (en) | Drowning detection method based on real-time video image analysis | |
| CN108960131A (en) | The anti-people of mechanical garage is strayed into detection method | |
| KR101937836B1 (en) | Apparatus and method for determinating composite video and audio status in tetrapod | |
| CN109872499B (en) | Block on-spot monitoring alarm system based on image recognition | |
| CN107729874B (en) | Swimming pool drowning detection method based on space-time neighborhood characteristics |
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 |