CN111277748A - Construction site fire management system based on video intelligent analysis and implementation method thereof - Google Patents

Construction site fire management system based on video intelligent analysis and implementation method thereof Download PDF

Info

Publication number
CN111277748A
CN111277748A CN202010013746.1A CN202010013746A CN111277748A CN 111277748 A CN111277748 A CN 111277748A CN 202010013746 A CN202010013746 A CN 202010013746A CN 111277748 A CN111277748 A CN 111277748A
Authority
CN
China
Prior art keywords
video
monitoring
fire
information
data
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
Application number
CN202010013746.1A
Other languages
Chinese (zh)
Inventor
牛永玺
徐新
靳善翔
张弦
钱炜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Zhiwei Information Technology Co ltd
Original Assignee
Shanghai Zhiwei Information Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Zhiwei Information Technology Co ltd filed Critical Shanghai Zhiwei Information Technology Co ltd
Priority to CN202010013746.1A priority Critical patent/CN111277748A/en
Publication of CN111277748A publication Critical patent/CN111277748A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00Television systems
    • H04N7/18Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/50Context or environment of the image
    • G06V20/52Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B17/00Fire alarms; Alarms responsive to explosion
    • G08B17/10Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B17/00Fire alarms; Alarms responsive to explosion
    • G08B17/12Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
    • G08B17/125Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/695Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00Details of television systems
    • H04N5/76Television signal recording

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Theoretical Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Fire Alarms (AREA)
  • Alarm Systems (AREA)

Abstract

The utility model provides a building site fire management system and implementation method based on video intelligent analysis, with the building site fire region according to before the fire, in the fire, three stage after the fire, carry out contrastive analysis to the image and the benchmark image that people, thing and environment obtained through the video, including environmental monitoring, personnel wear the monitoring, personnel's tracking monitoring, personnel's identification monitoring, firework monitoring. The monitoring tool uses a camera which is designed by an AI algorithm acceleration chip with built-in image recognition, smoke recognition, object recognition and face recognition algorithms to carry out video shooting and intelligent analysis application. The video is transmitted to a background construction site fire management software system through a camera for data comparison and real-time management, and the background construction site fire management software system comprises a user data system, a data analysis and verification system, an alarm system and a report system so as to achieve the intelligent and data effects of construction site fire management.

Description

Construction site fire management system based on video intelligent analysis and implementation method thereof
Technical Field
The invention relates to the technical field of construction site fire video analysis, in particular to a construction site fire management system based on video intelligent analysis and an implementation method thereof.
Background
The operation of firing refers to the performance of temporary operations that may produce sparks, flames and glowing surfaces. Common fire operations include electric welding, gas welding (hot cutting), and the like. If the fire operation is not managed in a standard way, fire and even explosion accidents are easily caused. Safety is therefore the first factor to be guaranteed. The safety guarantee not only guarantees the safety of the society, but also guarantees the safety of fire operators, guardians and night watchers. In the management work of firing work, the trend of improving safety early warning by using advanced scientific technology is already a trend.
In the special environment of the fire operation area (flat ground, high altitude, underground and closed places), the whole process before, during and after the fire is finished is a link needing whole-process monitoring. And video surveillance is the most central part.
At present, whether the environment of a fire scene meets the fire requirement, whether a field operator is consistent with an applicant, whether the operator wears the electric furnace to meet the standard, whether the electric furnace leaves the field in advance after the fire is over and the like are judged by people. The biggest disadvantage of the ordinary video monitoring is that the ordinary video monitoring completely depends on manual monitoring. Due to the fact that too many videos are generated, monitoring personnel are limited, and people cannot monitor the video information of hundreds of cameras at all because of being easy to fatigue and neglect when staring at a monitoring picture for a long time. According to the relevant data analysis, the monitoring personnel may miss up to 95% of the pictures after 20 minutes. It is thought that the monitoring of people is limited, and the occurrence of emergency events is unpredictable, and it is difficult to ensure whether there is omission of events only by artificial monitoring. Once a potential safety hazard event occurs, no intelligent video analysis is available, and immediate judgment and early warning cannot be made, so that the method can only be used as a tool for obtaining evidence afterwards.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a construction site fire management system based on video intelligent analysis and an implementation method thereof, and solves the problems of the prior art, the existing management means, the existing fire flow specification loophole and the like. A new application and an implementation method are provided for site fire management in three stages of before, during and after fire, and environment monitoring, personnel wearing monitoring, personnel tracking monitoring and quality control identification monitoring in the fire process are achieved. And carrying out video intelligent analysis and management design on the smoke and fire monitoring. Therefore, intelligent management of site fire is achieved, pre-judgment, timely alarming and talkback are conducted on the event in advance, rapid response is conducted on the abnormity of people and objects in the fire area, and the event video is traced and the mode of the label is analyzed.
In order to achieve the purpose, the invention is realized by the following technical scheme:
a construction site fire management system based on video intelligent analysis comprises a data processing and analyzing module, a user database, a video monitoring and alarming system, a ball machine module and a label collector; the label collector is used for collecting label information on a welder in a welding field and transmitting the collected information data to the data processing and analyzing module; the ball machine module is used for collecting video picture information in a welding field and transmitting the data stream to a video monitoring alarm system through RTSP; the video monitoring alarm system is used for uploading the acquired video picture information to the data processing analysis module; the data processing and analyzing module is used for processing and analyzing the received information data, verifying the received information data with the data information of the user database, transmitting abnormal information to the video monitoring and alarming system through data, and sending an alarming signal by the video monitoring and alarming system.
Preferably, the dome camera module adopts a 4G/5G transmission camera device based on an AI algorithm chip, and comprises a video monitoring system, a face recognition system, a smoke and fire recognition system and an object recognition system.
Preferably, the smoke and fire identification system comprises a flame mode and a smoke mode.
Preferably, the video monitoring and alarming system controls the dome camera module through the cloud platform.
The invention also provides a construction site fire management implementation method based on video intelligent analysis, which comprises the following steps:
step 1) placing a label collector on an operation accessory of a welder, and adding a TAG label on a helmet or clothes of the welder;
step 2) monitoring the operation of a welder by using a camera video based on an AI algorithm, and intercepting pictures at intervals for background face information monitoring; receiving TAG label information on the helmet or clothes of the welder through a label collector;
step 3) analyzing and judging whether the data acquired by the label is abnormal or not by a data processing and analyzing module, and judging whether the welder is normal or not; monitoring information acquired by the ball machine is transmitted to a video monitoring alarm system for analyzing the open fire state;
step 4) when abnormal information occurs, the video monitoring alarm system sends an alarm signal, the monitoring center prompts an operator and further makes manual judgment, the operator can check the video record of the corresponding abnormal node, and if the problem exists, the system can automatically manage the construction site by clicking an alarm button;
and 5) after the fire is started, no sign of the fire is generated within 30 minutes of the monitoring range of the camera of the AI algorithm, and after 30 minutes, the guardian is confirmed to finish monitoring.
The invention provides a construction site fire management system based on video intelligent analysis and an implementation method thereof. The method has the following beneficial effects:
1. compared with manual monitoring, the safety management work of the fire working process can be further enhanced;
2. the monitoring time is more durable, and compared with the field on-duty personnel, the video monitoring of a duty room and the like, the uninterrupted monitoring and analysis of the whole operation process can be realized;
3. the monitoring capability is stronger, and compared with the identification of artificial naked eyes, the intelligent video analysis capability is more advantageous in a complex environment;
4. the monitoring strategy is more flexible, various monitoring strategies can be configured, various abnormal scenes can be found in time, the timeliness is greatly enhanced, and the detection efficiency is greatly improved;
5. an emergency management platform is formed, and the efficiency of management and control work is improved;
6. the product is beneficial to forming an emergency mechanism with unified command and dispatch, complete functions, sensitive response and high operation efficiency, and the capability of guaranteeing public safety and handling emergencies is improved;
7. the intelligent analysis camera can identify different objects like people, discover abnormal conditions in the monitoring picture, and can send out an alarm in a fastest and optimal mode, so that real-time early warning and alarming of real-time monitored video information are realized, and the real-time early warning and the alarming are not only taken as the after-the-fact evidence.
Drawings
In order to more clearly illustrate the present invention or the prior art solutions, the drawings that are needed in the description of the prior art will be briefly described below.
FIG. 1 is a schematic diagram of the structure of the present invention;
FIG. 2 is a schematic diagram of the structure of a tag collector in the present invention;
FIG. 3 is a flow chart of the background management system for managing before, during and after a site fire in the invention;
FIG. 4 is a flow chart of the background management system for managing a site before a fire occurs in the present invention;
FIG. 5 is a flow chart of the background management system for managing a site fire in accordance with the present invention;
FIG. 6 is a flow chart of the background management system for managing a site after a fire occurs.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings.
In the first embodiment, as shown in fig. 1-2, a construction site fire management system based on video intelligent analysis includes a data processing and analyzing module, a user database, a video monitoring and alarming system, a dome camera module and a tag collector; the label collector is used for collecting label information on a welder in a welding field and transmitting the collected information data to the data processing and analyzing module; the ball machine module is used for collecting video picture information in a welding field and transmitting the data stream to a video monitoring alarm system through RTSP; the video monitoring alarm system is used for uploading the acquired video picture information to the data processing analysis module; the data processing and analyzing module is used for processing and analyzing the received information data, verifying the received information data with the data information of the user database, transmitting abnormal information to the video monitoring and alarming system through data, and sending an alarming signal by the video monitoring and alarming system.
When the construction site fire is managed, the state information of a welding site is collected by the dome camera module and is transmitted to the data processing and analyzing module through the video monitoring and alarming system, the open fire state can be analyzed, when a large open fire occurs, an alarm can be given, the label information on a welder in the welding site is collected by the label collector, and the data information is transmitted to the data processing and analyzing module to judge whether the welder is normal or not; the identity information of a welder is detected more clearly through mutual assistance of the ball machine module and the label collector; therefore, the alarm can be given out at the first time when an emergency happens, and the quick response of workers, such as the intrusion of personnel, can be facilitated; and the video can be stored through the video monitoring alarm system, so that the label tracing of abnormal behaviors of personnel is realized.
The method comprises the steps of detecting a fire area in real time by combining an object tracking and object recognition algorithm based on deep learning with an artificial intelligence AI chip, intelligently analyzing a real-time video stream acquired in the whole fire process, and analyzing and tracking a target appearing in a camera scene by separating a background and the target in the scene by using a computer image visual analysis technology. According to the video content intelligent analysis function, different alarm rules are preset in scenes of different cameras, once a target has a behavior violating predefined rules in the scene, the system can automatically give an alarm, so that the video monitoring is intelligent, the effect of intelligent video analysis on the whole fire safety operation is fully exerted, and therefore a sufficiently reliable guarantee is provided for a place needing high abstinence for the fire operation, and the situation is prevented in the bud.
In this embodiment, the dome camera module adopts a 4G/5G transmission camera device based on an AI algorithm chip, and includes a video monitoring system, a face recognition system, a smoke and fire recognition system, and an object recognition system.
In this embodiment, the smoke and fire identification system includes flame identification and smoke identification.
In this embodiment, the video monitoring and warning system controls the dome camera module through the cloud platform.
The application scenarios and the management flows of the site fire management system of the embodiment to the site before, during and after fire are shown in fig. 3-6;
the method comprises the steps that a labor worker firstly puts forward a fire application before firing, a project manager carries out examination and approval, when the examination and approval is passed, the labor worker firstly carries out fire signing-in and then carries out fire implementation, in the implementation process, a ball machine module carries out remote monitoring, when the fire is finished, the labor worker carries out fire signing-off and then finishes after the project safety worker carries out sign-off and approval.
The second embodiment of the invention also provides a construction site fire management implementation method based on video intelligent analysis, which comprises the following steps of:
step 1) placing a label collector on an operation accessory of a welder, and adding a TAG label on a helmet or clothes of the welder;
step 2) monitoring the operation of a welder by using a camera video based on an AI algorithm, and intercepting pictures at intervals for background human face information monitoring, wherein if the monitoring result shows that the welder is not corresponding to a person, abnormal triggering is provided; receiving TAG label information on the helmet or clothes of the welder through a label collector;
step 3) analyzing and judging whether the data acquired by the label is abnormal or not by a data processing and analyzing module, and judging whether the welder is normal or not; monitoring information acquired by the ball machine is transmitted to a video monitoring alarm system for analyzing the open fire state;
step 4) when abnormal information occurs, the video monitoring alarm system sends an alarm signal, the monitoring center prompts an operator and further makes manual judgment, the operator can check the video record of the corresponding abnormal node, and if the problem exists, the system can automatically manage the construction site by clicking an alarm button;
and 5) after the fire is started, no sign of the fire is generated within 30 minutes of the monitoring range of the camera of the AI algorithm, and after 30 minutes, the guardian is confirmed to finish monitoring.
The application can continuously and continuously detect in real time in the whole process of the firing operation, replaces the complicated monitoring work of part of daily manual work, simplifies the working intensity of daily management, and enables managers to have more time and energy to handle emergency. When illegal operation behaviors or potential safety hazards occur, the video analysis function can automatically recognize and trigger video alarm prompts.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (5)

1. The utility model provides a building site fire management system based on video intelligent analysis which characterized in that: the system comprises a data processing and analyzing module, a user database, a video monitoring and alarming system, a dome camera module and a label collector;
the label collector is used for collecting label information on a welder in a welding field and transmitting the collected information data to the data processing and analyzing module;
the ball machine module is used for collecting video picture information in a welding field and transmitting the data stream to a video monitoring alarm system through RTSP;
the video monitoring alarm system is used for uploading the acquired video picture information to the data processing analysis module;
the data processing and analyzing module is used for processing and analyzing the received information data, verifying the received information data with the data information of the user database, transmitting abnormal information to the video monitoring and alarming system through data, and sending an alarming signal by the video monitoring and alarming system.
2. The construction site fire management system based on video intelligent analysis and the implementation method thereof according to claim 1 are characterized in that: the dome camera module adopts a 4G/5G transmission camera device based on an AI algorithm chip and comprises a video monitoring system, a face recognition system, a firework recognition system and an object recognition system.
3. The construction site fire management system based on video intelligent analysis and the implementation method thereof according to claim 1 are characterized in that: the smoke and fire identification system includes a flame mode and a smoke mode.
4. The construction site fire management system based on video intelligent analysis and the implementation method thereof according to claim 1 are characterized in that: the video monitoring and alarming system controls the ball machine module through the cloud platform.
5. A construction site fire management implementation method based on video intelligent analysis is characterized by comprising the following steps:
step 1) placing a label collector on an operation accessory of a welder, and adding a TAG label on a helmet or clothes of the welder;
step 2) monitoring the operation of a welder by using a camera video based on an AI algorithm, and intercepting pictures at intervals for background face information monitoring; receiving TAG label information on the helmet or clothes of the welder through a label collector;
step 3) analyzing and judging whether the data acquired by the label is abnormal or not by a data processing and analyzing module, and judging whether the welder is normal or not; monitoring information acquired by the ball machine is transmitted to a video monitoring alarm system for analyzing the open fire state;
step 4) when abnormal information occurs, the video monitoring alarm system sends an alarm signal, the monitoring center prompts an operator and further makes manual judgment, the operator can check the video record of the corresponding abnormal node, and if the problem exists, the system can automatically manage the construction site by clicking an alarm button;
and 5) after the fire is started, no sign of the fire is generated within 30 minutes of the monitoring range of the camera of the AI algorithm, and after 30 minutes, the guardian is confirmed to finish monitoring.
CN202010013746.1A 2020-01-07 2020-01-07 Construction site fire management system based on video intelligent analysis and implementation method thereof Pending CN111277748A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010013746.1A CN111277748A (en) 2020-01-07 2020-01-07 Construction site fire management system based on video intelligent analysis and implementation method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010013746.1A CN111277748A (en) 2020-01-07 2020-01-07 Construction site fire management system based on video intelligent analysis and implementation method thereof

Publications (1)

Publication Number Publication Date
CN111277748A true CN111277748A (en) 2020-06-12

Family

ID=71111963

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010013746.1A Pending CN111277748A (en) 2020-01-07 2020-01-07 Construction site fire management system based on video intelligent analysis and implementation method thereof

Country Status (1)

Country Link
CN (1) CN111277748A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112001697A (en) * 2020-08-17 2020-11-27 四川浪鲸智能科技有限公司 Intelligent cloud artificial intelligence platform system
CN112733607A (en) * 2020-12-11 2021-04-30 国网浙江省电力有限公司绍兴供电公司 Transformer substation site safety management method based on physical ID
CN113500596A (en) * 2021-07-07 2021-10-15 上海建工七建集团有限公司 Fire operation auxiliary robot system and monitoring method thereof
CN114205688A (en) * 2021-12-14 2022-03-18 上海建科工程咨询有限公司 Intelligent supervision system and method
CN114578737A (en) * 2022-03-09 2022-06-03 南京华脉科技股份有限公司 Intelligent security monitoring system based on 5G network
CN115249394A (en) * 2021-12-31 2022-10-28 重庆工程职业技术学院 Engineering construction device based on BIM

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112001697A (en) * 2020-08-17 2020-11-27 四川浪鲸智能科技有限公司 Intelligent cloud artificial intelligence platform system
CN112733607A (en) * 2020-12-11 2021-04-30 国网浙江省电力有限公司绍兴供电公司 Transformer substation site safety management method based on physical ID
CN113500596A (en) * 2021-07-07 2021-10-15 上海建工七建集团有限公司 Fire operation auxiliary robot system and monitoring method thereof
CN114205688A (en) * 2021-12-14 2022-03-18 上海建科工程咨询有限公司 Intelligent supervision system and method
CN115249394A (en) * 2021-12-31 2022-10-28 重庆工程职业技术学院 Engineering construction device based on BIM
CN114578737A (en) * 2022-03-09 2022-06-03 南京华脉科技股份有限公司 Intelligent security monitoring system based on 5G network
CN114578737B (en) * 2022-03-09 2023-10-17 国网上海市电力公司超高压分公司 Intelligent security monitoring system based on 5G network

Similar Documents

Publication Publication Date Title
CN111277748A (en) Construction site fire management system based on video intelligent analysis and implementation method thereof
CN103150856B (en) Fire flame video monitoring and early warning system
CN211293956U (en) AI-based identification and alarm system for abnormal agent on construction site
CN112183317B (en) Live working field violation behavior detection method based on space-time diagram convolutional neural network
CN106454250A (en) Intelligent recognition and early warning processing information platform
KR101036947B1 (en) The automatic guard system to prevent the crime and accident using computer video image analysis technology
KR102398841B1 (en) Method and system for determining danger in constuction sites based on image analysis
CN110867046A (en) Intelligent car washer video monitoring and early warning system based on cloud computing
CN101231778A (en) Camera shooting self-extinguishing warning system
CN112488483A (en) AI technology-based EHS transparent management system and management method
CN113011833A (en) Safety management method and device for construction site, computer equipment and storage medium
CN114333273A (en) Intelligent analysis system and method for nuclear power construction site
CN112112629A (en) Safety business management system and method in drilling operation process
CN113206978A (en) Security intelligent monitoring early warning system and method for oil and gas pipeline station
CN110349360A (en) A kind of building window area deployment system and monitoring method
CN110285801A (en) The localization method and device of intelligent safety helmet
CN112541439A (en) Intelligent video monitoring method and system for power plant
CN112532920A (en) Construction site system intelligent monitoring implementation method and system
CN115567690A (en) Intelligent monitoring system capable of automatically identifying dangerous points of field operation
CN111486537B (en) Air conditioner with security and monitoring functions
CN116523492A (en) Hydropower station supervision method and system, electronic equipment and storage medium
CN115022598A (en) Water and electricity safety artificial intelligence video monitoring system
CN203204762U (en) A fire flame video early warning system
CN112153065A (en) Environment perception information verification system based on artificial intelligence and network security
CN112800896A (en) Security emergency measure self-response method and system based on knowledge graph

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20200612