CN111401288A - Fixed scene monitoring system for engineering project operation - Google Patents

Fixed scene monitoring system for engineering project operation Download PDF

Info

Publication number
CN111401288A
CN111401288A CN202010213580.8A CN202010213580A CN111401288A CN 111401288 A CN111401288 A CN 111401288A CN 202010213580 A CN202010213580 A CN 202010213580A CN 111401288 A CN111401288 A CN 111401288A
Authority
CN
China
Prior art keywords
module
behavior
recognition
fixed
scene
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
CN202010213580.8A
Other languages
Chinese (zh)
Inventor
吕青峰
陈强
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.)
Chongqing Desheng Dingsheng Industrial Development Co ltd
Original Assignee
Chongqing Desheng Dingsheng Industrial Development 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 Chongqing Desheng Dingsheng Industrial Development Co ltd filed Critical Chongqing Desheng Dingsheng Industrial Development Co ltd
Priority to CN202010213580.8A priority Critical patent/CN111401288A/en
Publication of CN111401288A publication Critical patent/CN111401288A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/18Status alarms
    • G08B21/24Reminder alarms, e.g. anti-loss alarms
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B25/00Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
    • G08B25/01Alarm 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
    • G08B25/08Alarm 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Emergency Management (AREA)
  • Business, Economics & Management (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Multimedia (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Alarm Systems (AREA)

Abstract

The invention discloses a fixed scene monitoring system for engineering project operation, which comprises a camera shooting acquisition system, a video acquisition system and a video acquisition system, wherein the camera shooting acquisition system is used for acquiring continuous image video and audio of a fixed construction scene; the information authentication system is used for collecting and authenticating identity information, face information and characteristics of constructors participating in a fixed construction scene; the behavior recognition system is used for monitoring conventional behaviors generated in a fixed construction scene and identifying abnormal behaviors; the behavior management system is used for collecting, classifying and storing behavior actions; the alarm system is used for carrying out alarm reminding when the behavior recognition system recognizes abnormal behaviors; the deep learning system is used for performing deep learning of behavior action recognition judgment according to the behavior recognition system and the behavior management system; the cloud server is used for providing information communication and transmission, data interaction and data storage. The invention has the advantages of convenient collection, real-time early warning and accurate backtracking.

Description

Fixed scene monitoring system for engineering project operation
Technical Field
The invention relates to the field related to engineering supervision, in particular to a fixed scene monitoring system for engineering project operation.
Background
The infrastructure is always an important strength in China, rapid development of urban construction in China is guaranteed, the infrastructure is also output outwards as national strength, and in project engineering of the infrastructure, a condition which generally receives attention except quality is a construction period.
In the engineering project of the new infrastructure, relate to multiple building unit, various raw and other materials, different building scenes and numerous constructors, therefore on-the-spot monitoring is an action that is very difficult to realize, the significance of on-the-spot monitoring lies in the detailed video data of record building production process, can enough play the effect of supervising and urging the progress, can also go back to the important significance of pursuing the responsibility, help engineering project correct the error in time in the work progress, avoid producing the great construction mistake, on-the-spot monitoring at present stage mostly adopts the mode of fixed monitoring cooperation manual inspection to go on, can save a large amount of video data but, be difficult to accurate definite time node when backtracking, cause the waste, and do not possess the function that the scene proruption situation sent the warning.
Disclosure of Invention
To the deficiency of the prior art, the technical problem to be solved by the present patent application is: how to provide a scene-fixed monitoring system of engineering project operation convenient to gather, early-warning in real time, trace back accurately.
In order to achieve the purpose, the invention adopts the following technical scheme:
a fixed scene monitoring system for engineering project operation comprises a camera shooting acquisition system, an information authentication system, a behavior identification system, a behavior management system, an alarm system, a deep learning system and a cloud server; the camera shooting acquisition system is used for acquiring continuous image video and audio of a fixed construction scene; the information authentication system is used for collecting and authenticating identity information, face information and characteristics of constructors participating in a fixed construction scene; the behavior recognition system is used for monitoring conventional behaviors generated in a fixed construction scene and identifying abnormal behaviors; the behavior management system is used for collecting, classifying and storing behavior actions; the alarm system is used for carrying out alarm reminding when the behavior recognition system recognizes abnormal behaviors; the deep learning system is used for performing deep learning of behavior action recognition judgment according to the behavior recognition system and the behavior management system; the cloud server is used for providing information communication and transmission, data interaction and data storage.
Preferably, the camera shooting and collecting system is divided into a fixed collecting device and a mobile collecting device according to different constructed scenes, the fixed collecting device and the mobile collecting device are high-definition shooting heads, and the high-definition cameras are all provided with communication modules.
Preferably, the information authentication system comprises an identity acquisition subsystem and an identity recognition subsystem, the identity acquisition subsystem comprises an entry module and a first storage module, the identity recognition subsystem comprises a certificate recognition module and an image recognition module, and the identity recognition module further comprises a feature recognition module.
Specifically, the feature identification module comprises a color identification unit and a height identification unit.
Preferably, the behavior recognition system includes a motion capture module, a velocity capture module, a sound capture module, and a computation module.
Preferably, the behavior recognition system is provided with a marking system, the marking system is in communication connection with the cloud server, and the marking content of the marking system is a time point and a time period.
Preferably, the alarm system comprises an alarm and a text transmission module.
Preferably, the behavior management system comprises a collection module, a second storage module and a screening module.
Preferably, the deep learning system comprises a data sorting module, a data exchange module, a data cleaning module, a data comparison module, a data analysis module and a data training module.
Preferably, the cloud server includes a communication subsystem, a cloud storage subsystem and an image presentation subsystem.
Has the advantages that:
the invention adopts the situation of setting a scene in a construction site, captures, identifies and judges the behaviors of constructors in the scene to form a real-time online monitoring system, and has the advantages that:
(1) monitoring logic and monitoring scenes can be quickly established, images acquired by videos are transmitted and identified, the efficiency is high, and the response is quick;
(2): through behavior recognition, the operation behaviors of constructors in a scene can be autonomously supervised and analyzed, and meanwhile, potential safety hazards in the construction scene can be monitored;
(3): the system has an alarm function, can remind constructors and remote monitoring personnel of site scenes in time, achieves online real-time monitoring and guarantees timely processing;
(4): the system can deeply and automatically learn and continuously improve the recognition efficiency and accuracy.
Description of the drawings:
FIG. 1 is a scene-fixed monitoring system for engineering project operation based on big data disclosed by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Referring to fig. 1, a scene-fixed monitoring system for engineering project operation comprises a camera shooting acquisition system, an information authentication system, a behavior identification system, a behavior management system, an alarm system, a deep learning system and a cloud server; the camera shooting acquisition system is used for acquiring continuous image video and audio of a fixed construction scene; the information authentication system is used for collecting and authenticating identity information, face information and characteristics of constructors participating in a fixed construction scene; the behavior recognition system is used for monitoring conventional behaviors generated in a fixed construction scene and identifying abnormal behaviors; the behavior management system is used for collecting, classifying and storing behavior actions; the alarm system is used for carrying out alarm reminding when the behavior recognition system recognizes abnormal behaviors; the deep learning system is used for performing deep learning of behavior action recognition judgment according to the behavior recognition system and the behavior management system; the cloud server is used for providing information communication and transmission, data interaction and data storage.
Furthermore, the camera shooting and collecting system is divided into a fixed collecting device and a mobile collecting device according to different constructed scenes, the fixed collecting device and the mobile collecting device are high-definition shooting heads, and communication modules are mounted on the high-definition cameras.
Specifically, during construction, the fixed collection device is used for monitoring the whole construction site, for example, during building construction, the collection range of the fixed collection device is a construction preparation area around a building main body and the building, the movable collection device is movable, the fixed collection device cannot be installed in advance in the building construction process for the process from the beginning to the end, and therefore the movable collection device needs to be provided and needs to be provided with a mounting bracket to avoid damage.
Furthermore, the information authentication system comprises an identity acquisition subsystem and an identity recognition subsystem, wherein the identity acquisition subsystem comprises an entry module and a first storage module, the identity recognition subsystem comprises a certificate recognition module and an image recognition module, and the identity recognition module is also provided with a feature recognition module.
Specifically, the entry module is used for entering identity information of constructors in the area in the plan, the entered content comprises personal information and image information, and in addition, the identity information, the job number information and the like can be selectively added.
Specifically, the certificate identification module is used for identifying one or more combined information such as identity cards, work cards and certificates, accuracy is improved, the image identification module is used for checking consistency of operators and information, the feature identification module is used for identifying physical and physical features of the operators during identity authentication, including heights, dresses colors and the like, and is used for binding with the image identification module through other information to form a feature information set, so that people in a fixed scene can be distinguished conveniently.
Specifically, the feature identification module comprises a color identification unit and a height identification unit.
Further, the behavior recognition system includes a motion capture module, a velocity capture module, a sound capture module, and a computation module.
Specifically, the motion capture module is used for identifying conventional motions, work motions and illegal motions, for example, the conventional motions include daily common motions such as walking and talking; the working actions comprise body states or action rules which are different from conventional actions and generated by operators in the construction process, the records in the action management system are called for identification, and the illegal actions are illegal construction actions recorded in the action management system, such as actions of fighting, smoking, dangerous actions, dangerous construction actions and the like which are forbidden by orders at a construction site.
Specifically, the speed capture module identifies all speeds including people and objects in a scene, and captures the speed of the content to judge whether dangerous behaviors exist in the time, and if the object moves too fast, people with construction abnormal conditions probably run, the object falls and the like, and all factors threatening construction safety are provided.
Specifically, the sound capture module is used for collecting the voice of a construction site, analyzing the semantic meaning, and judging whether a help calling and other words exist.
Specifically, the calculation module is used for supervising increase and decrease of personnel in a construction site, calling the behavior recognition module and the information authentication system when the increase or decrease of the identified personnel occurs, re-determining the personnel in the area, judging the actual situation of the personnel in the scene through the face information and the feature information, and recording the stay time of the personnel and the downtime of the personnel through timing.
Furthermore, the behavior recognition system is provided with a marking system, the marking system is in communication connection with the cloud server, and the marking content of the marking system is a time point and a time period.
Specifically, the mark of the marking system is a time axis, namely, violation actions, violation semantics, too fast speed or long-time stillness of personnel occur in the behavior recognition system, and when the personnel increase and decrease conditions, the marking system uses time as a mark in information collected by the shooting acquisition system, transmits signals to the cloud server, completes highlight display, facilitates timely positioning in the backtracking process, shortens backtracking time and improves efficiency.
Further, the alarm system comprises an alarm and a text transmission module.
Specifically, when the marking system has a marking behavior, the signal can be transmitted to the cloud server according to the preset condition, an alarm is generated, and the alarm is arranged on a construction site and a background monitoring center, so that quick response is realized.
Specifically, the text content can be preset, and the alarm system transmits the preset text to the communicator of the relevant responsible person or manager according to different types of the abnormality occurring on the spot, wherein the form is not limited to short messages, voice calls or mails.
Further, the behavior management system comprises a collection module, a second storage module and a screening module.
Specifically, the collection module searches, records and calls conventional behaviors and action behaviors in a network based on a big data technology, the violation module learns through manual input, the second storage module is used for storing, updating and deleting data, and the screening module completes action identification and judgment distinguishing under the cooperation of the deep learning system to complete action type classification.
Furthermore, the deep learning system comprises a data sorting module, a data exchange module, a data cleaning module, a data comparison module, a data analysis module and a data training module.
Specifically, the collected behavior data and the data generated in the long-term use process are sorted, cleaned, exchanged, contrastively analyzed and trained, deep learning based on the AI technology is completed, accuracy of behavior judgment is strengthened, and accuracy of early warning is improved.
Further, the cloud server comprises a communication subsystem, a cloud storage subsystem and an image presentation subsystem.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.

Claims (9)

1. A scene-fixed monitoring system for engineering project operation is characterized by comprising a camera shooting acquisition system, an information authentication system, a behavior identification system, a behavior management system, an alarm system, a deep learning system and a cloud server;
the camera shooting acquisition system is used for acquiring continuous image video and audio of a fixed construction scene; the information authentication system is used for collecting and authenticating identity information, face information and characteristics of constructors participating in a fixed construction scene;
the behavior recognition system is used for monitoring conventional behaviors generated in a fixed construction scene and identifying abnormal behaviors;
the behavior management system is used for collecting, classifying and storing behavior actions;
the alarm system is used for carrying out alarm reminding when the behavior recognition system recognizes abnormal behaviors;
the deep learning system is used for performing deep learning of behavior action recognition judgment according to the behavior recognition system and the behavior management system;
the cloud server is used for providing information communication and transmission, data interaction and data storage.
2. The system for monitoring the fixed scene of the engineering project operation according to claim 1, wherein the camera shooting and collecting system is divided into a fixed collecting device and a mobile collecting device according to different construction scenes, the fixed collecting device and the mobile collecting device are both high-definition cameras, and communication modules are mounted on the high-definition cameras.
3. The system for monitoring the fixed scene of the engineering project operation as claimed in claim 2, wherein the information authentication system comprises an identity acquisition subsystem and an identity recognition subsystem, the identity acquisition subsystem comprises an entry module and a first storage module, the identity recognition subsystem comprises a certificate recognition module and an image recognition module, and the identity recognition module further comprises a feature recognition module.
4. The system of claim 3, wherein the behavior recognition system comprises a motion capture module, a velocity capture module, a sound capture module, and a computation module.
5. The system for monitoring the fixed scene of the engineering project operation according to claim 4, wherein the behavior recognition system is provided with a marking system, the marking system is in communication connection with the cloud server, and the marking content of the marking system is a time point and a time period.
6. The system of claim 5, wherein the alarm system comprises an alarm and a text transmission module.
7. The system of claim 6, wherein the behavior management system comprises a collection module, a second storage module, and a screening module.
8. The system of claim 7, wherein the deep learning system comprises a data sorting module, a data exchange module, a data cleaning module, a data comparison module, a data analysis module, and a data training module.
9. The system of claim 8, wherein the cloud server comprises a communication subsystem, a cloud storage subsystem, and an image rendering subsystem.
CN202010213580.8A 2020-03-24 2020-03-24 Fixed scene monitoring system for engineering project operation Pending CN111401288A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010213580.8A CN111401288A (en) 2020-03-24 2020-03-24 Fixed scene monitoring system for engineering project operation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010213580.8A CN111401288A (en) 2020-03-24 2020-03-24 Fixed scene monitoring system for engineering project operation

Publications (1)

Publication Number Publication Date
CN111401288A true CN111401288A (en) 2020-07-10

Family

ID=71434592

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010213580.8A Pending CN111401288A (en) 2020-03-24 2020-03-24 Fixed scene monitoring system for engineering project operation

Country Status (1)

Country Link
CN (1) CN111401288A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113625603A (en) * 2021-07-27 2021-11-09 金鹏电子信息机器有限公司 Security monitoring management system and management method based on big data
CN114827561A (en) * 2022-03-07 2022-07-29 成都极米科技股份有限公司 Projection control method, projection control device, computer equipment and computer-readable storage medium
CN115240145A (en) * 2022-09-22 2022-10-25 深圳市睿拓新科技有限公司 Method and system for detecting illegal operation behaviors based on scene recognition
CN116895142A (en) * 2023-09-11 2023-10-17 关天建设工程有限公司 Global monitoring method and system for building construction

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104320638A (en) * 2014-11-24 2015-01-28 张宏鑫 Intelligent integrated monitoring and controlling system and surveillance video processing method
CN107730428A (en) * 2017-10-17 2018-02-23 贾俊力 Job site intelligent monitoring administration system and its control method
CN109376613A (en) * 2018-09-29 2019-02-22 东莞中国科学院云计算产业技术创新与育成中心 Video brainpower watch and control system based on big data and depth learning technology
KR20190082692A (en) * 2019-06-21 2019-07-10 엘지전자 주식회사 System And Method For Safety Management
CN110163154A (en) * 2019-05-23 2019-08-23 湖南机电职业技术学院 Video monitoring system based on artificial intelligence

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104320638A (en) * 2014-11-24 2015-01-28 张宏鑫 Intelligent integrated monitoring and controlling system and surveillance video processing method
CN107730428A (en) * 2017-10-17 2018-02-23 贾俊力 Job site intelligent monitoring administration system and its control method
CN109376613A (en) * 2018-09-29 2019-02-22 东莞中国科学院云计算产业技术创新与育成中心 Video brainpower watch and control system based on big data and depth learning technology
CN110163154A (en) * 2019-05-23 2019-08-23 湖南机电职业技术学院 Video monitoring system based on artificial intelligence
KR20190082692A (en) * 2019-06-21 2019-07-10 엘지전자 주식회사 System And Method For Safety Management

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
韦鹏程等: "《大数据巨量分析与机器学习的整合与开发》", 电子科技大学出版社 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113625603A (en) * 2021-07-27 2021-11-09 金鹏电子信息机器有限公司 Security monitoring management system and management method based on big data
CN114827561A (en) * 2022-03-07 2022-07-29 成都极米科技股份有限公司 Projection control method, projection control device, computer equipment and computer-readable storage medium
CN115240145A (en) * 2022-09-22 2022-10-25 深圳市睿拓新科技有限公司 Method and system for detecting illegal operation behaviors based on scene recognition
CN116895142A (en) * 2023-09-11 2023-10-17 关天建设工程有限公司 Global monitoring method and system for building construction
CN116895142B (en) * 2023-09-11 2023-11-24 关天建设工程有限公司 Global monitoring method and system for building construction

Similar Documents

Publication Publication Date Title
CN111401288A (en) Fixed scene monitoring system for engineering project operation
CN110826538B (en) Abnormal off-duty identification system for electric power business hall
CN110738127B (en) Helmet identification method based on unsupervised deep learning neural network algorithm
CN112785798A (en) Behavior analysis method for construction project constructors of electric power substation engineering
CN113411542A (en) Intelligent working condition monitoring equipment
CN209543514U (en) Monitoring and alarm system based on recognition of face
CN109560610A (en) A kind of transformer substation video and environmental monitoring system
CN111920129A (en) Intelligent safety helmet system
CN113762171A (en) Method and device for monitoring safety of railway construction site
CN211184122U (en) Intelligent video analysis system for linkage of railway operation safety prevention and control and large passenger flow early warning
CN112613361A (en) Intelligent behavior analysis system for security monitoring
CN213128247U (en) Intelligent safety helmet system
CN108776452B (en) Special equipment field maintenance monitoring method and system
CN107784649A (en) Plug test remote alarming system and method based on image recognition
CN210666820U (en) Pedestrian abnormal behavior detection system based on DSP edge calculation
CN115496640A (en) Intelligent safety system of thermal power plant
CN117255193B (en) Remote terminal state detection method and system of 5G network monitor
CN113470211A (en) Routing inspection track management method and device based on beacon identification
CN113327404A (en) Post fatigue state monitoring and warning system for air traffic controller
CN112528791A (en) Anti-intrusion system and method for railway station yard
CN117081917A (en) Intelligent gateway based on AI (advanced technology attachment) internet of things sewage treatment operation and maintenance management
CN116976865A (en) Ship maintenance device allocation management system based on big data analysis
CN111723725A (en) Multi-dimensional analysis system based on video AI
CN116912037A (en) Safety monitoring system and method for building construction based on image processing
CN214652802U (en) System for recognizing unfair elevator taking behavior of elevator passengers

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: 20200710

RJ01 Rejection of invention patent application after publication