CN211293956U - AI-based identification and alarm system for abnormal agent on construction site - Google Patents
AI-based identification and alarm system for abnormal agent on construction site Download PDFInfo
- Publication number
- CN211293956U CN211293956U CN201921962566.7U CN201921962566U CN211293956U CN 211293956 U CN211293956 U CN 211293956U CN 201921962566 U CN201921962566 U CN 201921962566U CN 211293956 U CN211293956 U CN 211293956U
- Authority
- CN
- China
- Prior art keywords
- server
- identification
- abnormal
- alarm
- cloud 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.)
- Active
Links
Images
Landscapes
- Alarm Systems (AREA)
Abstract
The utility model relates to an AI-based identification and alarm system for abnormal agents in construction sites, which comprises a video collector, an action analysis edge server, a cloud monitoring server, an identification server, a display unit and an alarm device; the monitoring and identification of a plurality of construction sites can be realized. This discernment and alarm system adopts artificial intelligence model to detect unusual action, discerns unusual agent to report an emergency and ask for help or increased vigilance to the agent that relates to, inform the managers of scene building site simultaneously, be convenient for discover the problem and in time handle, realize the full flow fine-grained management of scene building site.
Description
Technical Field
The utility model relates to an discernment and alarm system especially relate to an identification and alarm system of job site abnormal behavior person based on AI.
Background
The engineering construction has the characteristics of obvious production scale bulk and production site fixity, about 70% of work occurs in a construction site, and site management in a construction stage is very important to engineering cost, progress, quality, safety and the like. The construction site is complicated in personnel, the construction period is different according to different project lengths, and the condition that a plurality of construction sites work together in different regions exists. For a large enterprise, branch companies exist all over the country, a plurality of construction sites are operated under the branch companies, construction conditions all over the country are complex, and the whole conditions of construction safety states, personnel safety states, quality safety states, violation warning and the like of all the construction sites need to be mastered timely and accurately to perform grading early warning.
The traditional monitoring system basically equals to furnishings if no monitoring center specially-assigned person is on duty, and only can play a certain role of deterrence and the role of video evidence collection afterwards. If a specially-assigned person is on duty, the project is often larger, the number of monitoring pictures is large, the on-duty person is difficult to pay attention to all the pictures, the illegal operation behaviors cannot be comprehensively and accurately identified through the monitoring pictures, and the early warning, alarming and preventing effects cannot be achieved in the bud. The safety monitoring of a plurality of construction sites is more complicated, and a plurality of difficulties exist in realizing unified safety monitoring management.
The identity and the behavior of a person can be identified by utilizing a deep learning algorithm of the AI visual neural network. At present, personnel on a project site can use a face recognition technology to realize the access management of a construction site and the automatic identification of a worker cap and a worker clothes (CN 201811032872.0). However, in the construction process of the on-site personnel, the whole process of the constructors cannot be tracked, and the individual risk prompt and the timely management aiming at specific abnormal behaviors cannot be realized. In addition, as the number of work projects increases, the same constructor may appear in different projects at different times, which increases the difficulty of management. A system for recognizing abnormal behaviors of construction personnel is needed in a construction site, active defense is achieved, early warning is achieved, and fine management of the construction site is facilitated.
SUMMERY OF THE UTILITY MODEL
The utility model provides a recognition and alarm system of job site unusual agent based on AI can discern a plurality of job site personnel's unusual action through high in the clouds, edge end server, reports an emergency and asks for help or increased vigilance unusual agent according to the identification result to inform job site managers.
An AI-based identification and alarm system for abnormal actors in construction sites is characterized by comprising a video collector, an action analysis edge server, a cloud monitoring server, an identification server, a display unit and an alarm device;
the video collector is connected with the behavior analysis edge server and used for collecting videos and transmitting the videos to the behavior analysis edge server;
the behavior analysis edge server is deployed on different construction sites and comprises an AI analysis unit and a transmission unit, wherein the AI analysis unit analyzes transmitted videos frame by adopting a constructed artificial intelligence model and then pushes abnormal behavior videos to the cloud monitoring server through the transmission unit;
the cloud monitoring server is connected with the recognition server and the display unit and is used for carrying out statistical management on the abnormal behavior video, extracting the face image of the abnormal behavior in the abnormal behavior video and transmitting the face image to the recognition server;
the recognition server is used for recognizing the transmitted face image and transmitting a recognition result to the cloud monitoring server and the alarm device;
the display unit is connected with the cloud server and used for checking abnormal behavior videos and identification results;
and the warning device receives the identification result of the identification server and warns the abnormal actor according to the identification result.
The display unit comprises an early warning screen and is used for automatically popping up videos of abnormal behaviors.
The warning device comprises a wearable device for warning the abnormal actor.
And the cloud monitoring server pushes the identification result transmitted by the identification server to the terminal equipment of a construction site manager.
The AI-based construction site abnormal agent identification and alarm system fully utilizes artificial intelligent video machine learning such as deep learning identification technology, Internet of things sensing technology and wireless transmission technology, combines with actual conditions of a construction site, starts with multiple dimensions based on personnel behavior identification, article identification, safety understanding and identification, supervision, error correction and alarm and the like, and creates an integrated, intelligent and visual AI intelligent behavior analysis alarm platform for the industry.
This discernment and alarm system can realize that a plurality of building sites are on-spot to the control, the discernment of unusual agent, in case monitored control system shoots unusual action, the system can be immediately transfer the video of incident scene to the early warning screen on (various warning display terminal) to discern unusual agent, report an emergency and ask for help or increased vigilance to the agent that relates to inform the managers of site building site, be convenient for discover in time and handle the problem, realize the full flow fine-grained management of site building site. The system can greatly reduce the deployment of security check personnel and reduce the labor cost.
Drawings
FIG. 1 is a schematic diagram of the AI-based identification and alarm system for abnormal actors in a construction site;
among them, 1 gun type camera; 2 a dome or dome camera; 3 moving the camera; 4, analyzing an edge server by using behaviors; 5, a cloud monitoring server; 6 identifying the server; 7 a display unit; 8, an alarm device; and 9, terminal equipment.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some but not all of the relevant portions of the present invention are shown in the drawings.
Fig. 1 is a system for identifying an abnormal actor in a construction site based on AI, which includes a video collector, an action analysis edge server, a cloud monitoring server, an identification server, a display unit and an alarm device;
and the video collector is connected with the behavior analysis edge server and used for collecting the video and transmitting the video to the behavior analysis edge server. The video collector can be a fixed gun-shaped camera 1 and is suitable for being installed in all indoor and outdoor places; a dome camera 2 or a dome camera can be adopted, wherein the dome camera is suitable for being installed in an indoor office or a position with a ceiling, and the dome camera is suitable for being installed in 360-degree rotary monitoring in a large-range area; the camera can also be arranged on a movable bracket to form a movable camera 3 which can be set at different construction sites according to requirements. The system can select different types and numbers of cameras according to requirements.
The behavior analysis edge server 4 is deployed in different construction sites and comprises an AI analysis unit and a transmission unit, wherein the AI analysis unit analyzes transmitted videos frame by adopting a constructed artificial intelligence model, and then pushes abnormal behavior videos to the cloud monitoring server 5 through the transmission unit. The behavior analysis edge server is arranged near a construction site and is easy to collect video transmission, and the server is responsible for operating an AI algorithm model and identifying various behavior actions shot by the camera, such as whether to wear a safety helmet, whether to correctly wear the safety helmet, whether to fasten a safety belt and the like. Different AI model algorithms can be set according to different scenes so as to improve the accuracy of abnormal behavior identification. And transmitting the identified abnormal behavior video to a cloud monitoring server. The artificial intelligence model can be constructed by carrying out supervised training on the existing machine learning model by utilizing various machine learning methods and training samples. Wherein the model may include, but is not limited to, R-CNN, Fast R-CNN, SSD, YOLO, and the like.
And the cloud monitoring server 5 is connected with the recognition server 6 and the display unit 7 and is used for performing statistical analysis on the abnormal behavior video, extracting the abnormal behavior face image in the abnormal behavior video and transmitting the abnormal behavior face image to the recognition server. The cloud monitoring server can store the transmitted abnormal behavior video data, analyze the abnormal behavior video image frames, extract a face image (OpenCV) and transmit the face image to the recognition server. The cloud monitoring server realizes the unified management of each construction site through the edge end server 4, collects and analyzes data of each construction site through network connection, and supervises the abnormity of each project construction site. When the face of the behavior video is not extracted, the cloud monitoring server 5 may directly perform broadcast warning and notify the site manager through the recognition server 6. In addition, the cloud monitoring server 5 receives the identification result of the identification server and sends the result to a field manager, and the manager can check the abnormal behavior of the mobile phone APP.
And the recognition server 6 is used for recognizing the transmitted face image and transmitting a recognition result to the cloud monitoring server 5 and the alarm device 8. The identification server can also directly perform broadcast alarm according to the cloud monitoring server. The recognition server 6 pre-collects face images of all job site constructors, and is located near the display unit end for the safety of face data. The display unit also accesses abnormal behavior video data stored in the cloud monitoring server through the identification server.
And the display unit 7 is connected with the cloud monitoring server 5 and used for checking the abnormal behavior video and the recognition result. The user can also set at the cloud monitoring server 5 according to needs, and once the abnormal behavior video data are received, the video of the accident scene is immediately transferred to the display unit 7, so that the on-duty personnel can find problems in time.
And an alarm device 8 for receiving the recognition result of the recognition server 6 and giving an alarm to the abnormal agent according to the recognition result. The alarm device 8 can be a broadcast, a site alarm through sound or a light alarm. For example, the recognition server may output a set of electronic voices containing names of the persons with abnormal behaviors to the broadcasting system, and the broadcasting system host starts a speaker in the early warning area to broadcast the electronic voice warning after receiving the instruction. The identification server 6 can also give an alarm through a mobile phone of a constructor or wearable intelligent equipment, such as a smart watch. The method can be used for alarming according to different abnormal behaviors, if the constructor does not correctly wear the safety helmet, the alarm is triggered, the identification server identifies the constructor and alarms through the smart phone, and the method is effective in noisy construction sites.
The recognition system can achieve early warning in advance, active defense and timely problem finding, and achieves whole-course fine management of a plurality of site construction sites. Once the abnormal behaviors are shot by the monitoring system, the system can immediately transfer videos of the incident scene to an early warning screen (various warning display terminals), identify abnormal actors, alarm related actors and inform managers of the site, so that problems can be found and processed timely, and fine management of the whole process of the site is realized. The system can greatly reduce the deployment of security check personnel and reduce the labor cost.
It should be noted that the foregoing is only a preferred embodiment of the present invention and the technical principles applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail with reference to the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the scope of the present invention.
Claims (3)
1. An AI-based identification and alarm system for abnormal actors in construction sites is characterized by comprising a video collector, an action analysis edge server, a cloud monitoring server, an identification server, a display unit and an alarm device; the video collector is connected with the behavior analysis edge server; the behavior analysis edge server is deployed on different construction sites and comprises an AI analysis unit and a transmission unit; the cloud monitoring server is connected with the identification server and the display unit; the identification server transmits the identification result to the cloud monitoring server and the alarm device; the display unit is connected with the cloud server; and the warning device receives the identification result of the identification server and warns the abnormal actor according to the identification result.
2. The identification and alert system of claim 1 wherein the alert device includes a wearable device to alert an anomalous agent.
3. The identification and alarm system of claim 1, wherein the alarm device comprises a job site manager terminal device, and the cloud monitoring server pushes the identification result transmitted by the identification server to the terminal device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201921962566.7U CN211293956U (en) | 2019-11-14 | 2019-11-14 | AI-based identification and alarm system for abnormal agent on construction site |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201921962566.7U CN211293956U (en) | 2019-11-14 | 2019-11-14 | AI-based identification and alarm system for abnormal agent on construction site |
Publications (1)
Publication Number | Publication Date |
---|---|
CN211293956U true CN211293956U (en) | 2020-08-18 |
Family
ID=72022116
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201921962566.7U Active CN211293956U (en) | 2019-11-14 | 2019-11-14 | AI-based identification and alarm system for abnormal agent on construction site |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN211293956U (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111966067A (en) * | 2020-08-25 | 2020-11-20 | 浙江交投丽新矿业有限公司 | Personnel safety management and control system for sandstone aggregate plant |
CN112188164A (en) * | 2020-09-29 | 2021-01-05 | 爱动超越人工智能科技(北京)有限责任公司 | AI vision-based violation real-time monitoring system and method |
CN112288225A (en) * | 2020-09-24 | 2021-01-29 | 上海荷福人工智能科技(集团)有限公司 | Engineering construction management system and method based on AI algorithm and super calculation |
CN112305980A (en) * | 2020-11-13 | 2021-02-02 | 武汉畅唯安宁科技有限公司 | Operation management platform for comprehensive monitoring of intelligent building |
CN112488483A (en) * | 2020-11-25 | 2021-03-12 | 上上德盛集团股份有限公司 | AI technology-based EHS transparent management system and management method |
CN112766210A (en) * | 2021-01-29 | 2021-05-07 | 苏州思萃融合基建技术研究所有限公司 | Safety monitoring method and device for building construction and storage medium |
CN113033326A (en) * | 2021-03-05 | 2021-06-25 | 优得新能源科技(宁波)有限公司 | Photovoltaic power station construction treading assembly monitoring method |
CN113191252A (en) * | 2021-04-28 | 2021-07-30 | 北京东方国信科技股份有限公司 | Visual identification system for production control and production control method |
CN114051120A (en) * | 2021-10-26 | 2022-02-15 | 远光软件股份有限公司 | Video alarm method, device, storage medium and electronic equipment |
CN114145531A (en) * | 2021-07-19 | 2022-03-08 | 国网江苏省电力有限公司江阴市供电分公司 | Distribution network uninterrupted operation safety standard monitoring method |
CN114173094A (en) * | 2021-12-06 | 2022-03-11 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Video monitoring method and device, computer equipment and storage medium |
WO2022160414A1 (en) * | 2021-01-29 | 2022-08-04 | 南方电网调峰调频发电有限公司 | System for monitoring power plant |
CN117788763A (en) * | 2023-12-18 | 2024-03-29 | 慧之安信息技术股份有限公司 | Method and system for enhancing AR prompt function based on big data analysis |
-
2019
- 2019-11-14 CN CN201921962566.7U patent/CN211293956U/en active Active
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111966067A (en) * | 2020-08-25 | 2020-11-20 | 浙江交投丽新矿业有限公司 | Personnel safety management and control system for sandstone aggregate plant |
CN112288225A (en) * | 2020-09-24 | 2021-01-29 | 上海荷福人工智能科技(集团)有限公司 | Engineering construction management system and method based on AI algorithm and super calculation |
CN112188164A (en) * | 2020-09-29 | 2021-01-05 | 爱动超越人工智能科技(北京)有限责任公司 | AI vision-based violation real-time monitoring system and method |
CN112305980A (en) * | 2020-11-13 | 2021-02-02 | 武汉畅唯安宁科技有限公司 | Operation management platform for comprehensive monitoring of intelligent building |
CN112488483A (en) * | 2020-11-25 | 2021-03-12 | 上上德盛集团股份有限公司 | AI technology-based EHS transparent management system and management method |
CN112488483B (en) * | 2020-11-25 | 2024-03-26 | 上上德盛集团股份有限公司 | EHS transparent management system and management method based on AI technology |
WO2022160414A1 (en) * | 2021-01-29 | 2022-08-04 | 南方电网调峰调频发电有限公司 | System for monitoring power plant |
CN112766210A (en) * | 2021-01-29 | 2021-05-07 | 苏州思萃融合基建技术研究所有限公司 | Safety monitoring method and device for building construction and storage medium |
CN113033326A (en) * | 2021-03-05 | 2021-06-25 | 优得新能源科技(宁波)有限公司 | Photovoltaic power station construction treading assembly monitoring method |
CN113033326B (en) * | 2021-03-05 | 2022-06-14 | 优得新能源科技(宁波)有限公司 | Photovoltaic power station construction treading assembly monitoring method |
CN113191252A (en) * | 2021-04-28 | 2021-07-30 | 北京东方国信科技股份有限公司 | Visual identification system for production control and production control method |
CN114145531A (en) * | 2021-07-19 | 2022-03-08 | 国网江苏省电力有限公司江阴市供电分公司 | Distribution network uninterrupted operation safety standard monitoring method |
CN114051120A (en) * | 2021-10-26 | 2022-02-15 | 远光软件股份有限公司 | Video alarm method, device, storage medium and electronic equipment |
CN114173094A (en) * | 2021-12-06 | 2022-03-11 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Video monitoring method and device, computer equipment and storage medium |
CN117788763A (en) * | 2023-12-18 | 2024-03-29 | 慧之安信息技术股份有限公司 | Method and system for enhancing AR prompt function based on big data analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN211293956U (en) | AI-based identification and alarm system for abnormal agent on construction site | |
CN107911653B (en) | Intelligent video monitoring module, system, method and storage medium for residence | |
KR101716365B1 (en) | Module-based intelligent video surveillance system and antitheft method for real-time detection of livestock theft | |
KR102195706B1 (en) | Method and Apparatus for Detecting Intruder | |
US20100231714A1 (en) | Video pattern recognition for automating emergency service incident awareness and response | |
CN109377697A (en) | Rapid Alarm method of disposal under a kind of intensive camera head environment | |
CN112112629A (en) | Safety business management system and method in drilling operation process | |
CN103152601A (en) | Intelligent failure-reporting camera and network management client system thereof | |
CN110555964A (en) | Multi-data fusion key area early warning system and method | |
CN106454253A (en) | Method and system for detecting area wandering | |
CN113011833A (en) | Safety management method and device for construction site, computer equipment and storage medium | |
CN109544870B (en) | Alarm judgment method for intelligent monitoring system and intelligent monitoring system | |
WO2024124970A1 (en) | Monitoring apparatus and method for performing behavior recognition in complex environment | |
KR20230004421A (en) | System for detecting abnormal behavior based on artificial intelligence | |
CN111178241A (en) | Intelligent monitoring system and method based on video analysis | |
CN111652128B (en) | High-altitude power operation safety monitoring method, system and storage device | |
CN114418388A (en) | Personnel management method and device based on image recognition and storage medium | |
KR101005568B1 (en) | Intelligent security system | |
CN111223011A (en) | Food safety supervision method and system for catering enterprises based on video analysis | |
CN110602453B (en) | Internet of things big data intelligent video security monitoring system | |
CN111860187A (en) | High-precision worn mask identification method and system | |
CN210091231U (en) | Wisdom garden management system | |
CN113627321A (en) | Image identification method and device based on artificial intelligence and computer equipment | |
CN107820051A (en) | Monitoring system and its monitoring method and device | |
CN109327681B (en) | Specific personnel identification alarm system and method thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant |