CN114429677A - Coal mine scene operation behavior safety identification and assessment method and system - Google Patents
Coal mine scene operation behavior safety identification and assessment method and system Download PDFInfo
- Publication number
- CN114429677A CN114429677A CN202210105594.7A CN202210105594A CN114429677A CN 114429677 A CN114429677 A CN 114429677A CN 202210105594 A CN202210105594 A CN 202210105594A CN 114429677 A CN114429677 A CN 114429677A
- Authority
- CN
- China
- Prior art keywords
- behavior
- safety
- coal mine
- preset
- operator
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000003245 coal Substances 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000006399 behavior Effects 0.000 claims abstract description 141
- 238000012360 testing method Methods 0.000 claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 35
- 230000001815 facial effect Effects 0.000 claims description 18
- 238000012544 monitoring process Methods 0.000 claims description 12
- 230000036544 posture Effects 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 238000005422 blasting Methods 0.000 claims description 3
- 230000007123 defense Effects 0.000 claims description 3
- 238000005065 mining Methods 0.000 claims description 3
- 230000005641 tunneling Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 abstract description 8
- 238000007726 management method Methods 0.000 description 24
- 238000004422 calculation algorithm Methods 0.000 description 12
- 238000001514 detection method Methods 0.000 description 12
- 238000013461 design Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 8
- 238000013135 deep learning Methods 0.000 description 5
- 238000004088 simulation Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011897 real-time detection Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 238000013523 data management Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 241000282693 Cercopithecidae Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06398—Performance of employee with respect to a job function
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Mining & Mineral Resources (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a coal mine scene operation behavior safety identification and examination method, which is characterized in that a behavior identification device which is respectively arranged at each preset specified position in a coal mine scene and is used for detecting each preset specified type of non-safety behavior and an image capture device which is used for capturing images of each specified type of non-safety behavior are respectively based on triggering of non-safety behavior identification, character identification of operators on the non-safety behavior is executed based on corresponding captured images, and then corresponding test questions are selected to construct examination paper and pushed to corresponding operators to execute examination so as to improve the safety operation skills of the coal mine operators by combining with a test question library which is formed by presetting each test question corresponding to each mine operation label; and a corresponding system is designed, a network architecture with corresponding functions is constructed based on the designed method, and safety identification and assessment training of coal mine scene operation behaviors can be efficiently realized.
Description
Technical Field
The invention relates to a coal mine scene operation behavior safety identification and assessment method and a system, and belongs to the technical field of coal mine enterprise safety management.
Background
The traditional coal mine video monitoring system only has a recording function, is simple in system design and single in function, only meets the monitoring and storing requirements, and does not achieve the purpose of early warning analysis. When an abnormal condition occurs, monitoring personnel can only check through video recording, and can only punish the occurring unsafe behavior through manually issuing various punishment lists, but the personnel can not know where the personnel are wrong due to the fact that training of corresponding safety knowledge is not carried out, and the unsafe behavior is very easy to cause again.
With the rapid development of technologies such as internet, artificial intelligence, big data, image recognition and the like, the intelligent video recognition technology is gradually paid attention to and emphasized, so that subversion is brought to the traditional coal mine safety management, and the management of various unsafe behaviors in coal mine scenes is more humanized.
Disclosure of Invention
The invention aims to solve the technical problem of providing a coal mine scene operation behavior safety identification and assessment method, which is based on automatic intelligent monitoring, identifies non-safety behaviors in a coal mine scene, and pushes assessment test paper to related operators by combining with a test question library to realize safety assessment.
The invention adopts the following technical scheme for solving the technical problems: the invention designs a coal mine scene operation behavior safety identification and assessment method, which is based on a behavior identification device and an image capture device, wherein the behavior identification device is arranged at each preset designated position in a coal mine scene and is used for detecting each preset designated type of non-safety behavior, and the image capture device is used for capturing images of each designated type of non-safety behavior, and each designated position is respectively executed according to the following steps:
step A, detecting whether a specified type of non-safety behavior occurs or not by a behavior recognition device aiming at a specified position where the behavior recognition device is located, and if so, entering step B; otherwise, the behavior recognition device continues to detect;
b, obtaining a face image containing an operator who executes the specified type of non-safety behavior by the image capturing device, and then entering step C;
c, according to the facial image of the operator with the specified type of non-safety behavior, applying a trained facial recognition model with the facial image as input and the identity information of the operator corresponding to the facial image as output to obtain the identity information of the operator with the specified type of non-safety behavior, and then entering the step D;
d, according to the specified type of non-safety behavior, combining with the preset corresponding relation between each specified type of non-safety behavior and each mine operation label, randomly selecting each test question with the preset test quantity corresponding to the specified type of non-safety behavior from a test question library formed by each test question preset to respectively correspond to each mine operation label to form an examination paper, and entering the step E;
and E, pushing the examination paper to the operator of the specified type of non-safety behavior according to the identity information of the operator of the specified type of non-safety behavior, and executing examination.
As a preferred technical scheme of the invention: in the step E, the test paper is pushed to the process that the operator of the specified type of non-safety behavior executes the examination, and if the examination is passed, the operator of the specified type of non-safety behavior passes the examination; and if the assessment is not passed, returning to the step D.
As a preferred technical scheme of the invention: the face recognition model in the step C is obtained according to the following steps C1 to C2;
step C1, for each preset designated operator, collecting the face images of each operator corresponding to each preset face posture respectively, constructing the corresponding relation between each face image and the identity information of the corresponding operator, and then entering the step C2;
and step C2, training aiming at a preset classification network according to each face image and the identity information of the operator corresponding to each face image, taking the face image as input and the identity information of the operator corresponding to the face image as output to obtain a face recognition model.
As a preferred technical scheme of the invention: the preset facial postures in the step C1 comprise preset facial angles, a face covering surface, a face cleaning surface, a safety helmet and a safety helmet which is not worn.
As a preferred technical scheme of the invention: and if the specified types of non-safety behaviors comprise that the preset specified area is forbidden to enter, the behavior recognition device for detecting the forbidden entering of the preset specified area is an image capture device with an image capture area covering the preset specified area, and whether the type of non-safety behaviors appear is detected by comparing whether images of operators exist in the images captured by the image capture device.
As a preferred technical scheme of the invention: and the behavior identification device aiming at the specified type of non-safe behavior is the sensors arranged on the specified operated objects and is used for detecting the sensing data corresponding to the specified operated objects and detecting whether the type of non-safe behavior occurs or not by comparing whether the obtained sensing data respectively exceeds the range of the preset corresponding threshold value or not.
As a preferred technical scheme of the invention: the mine operation labels corresponding to the test questions in the test question library comprise coal mining operation labels, tunneling operation labels, blasting operation labels, lifting transportation electromechanical equipment operation labels, defense operation labels, auxiliary transportation operation labels, ground test operation labels, monitoring operation labels, comprehensive operation labels and general operation labels.
Correspondingly, the invention also solves the technical problem of providing a system of the coal mine scene operation behavior safety identification and assessment method, which constructs a network architecture with corresponding functions based on a designed method and can efficiently realize the safety identification and assessment of the coal mine scene operation behavior.
The invention adopts the following technical scheme for solving the technical problems: the invention designs a system of a coal mine scene operation behavior safety identification and assessment method, which comprises an access layer, a network layer, a data layer, an application layer, a presentation layer and a user layer, wherein the access layer is used for realizing video monitoring access of each image capturing device in a coal mine scene; the network layer is used for providing a channel for the transmission of the data received by the access layer; the data layer is used for analyzing and identifying the data transmitted by the network layer, namely executing the steps A to C; the application layer is used for realizing the construction of the test question bank and executing the step D; the presentation layer is used for displaying the operation of the system; and E, the user layer is used for examination question assessment of coal mine operators, namely the step E is executed.
Compared with the prior art, the coal mine scene operation behavior safety identification and assessment method and the system have the following technical effects:
(1) the invention relates to a coal mine scene operation behavior safety identification and assessment method, which is characterized in that a behavior identification device for detecting preset appointed types of non-safety behaviors and an image capture device for capturing images of the appointed types of non-safety behaviors are respectively arranged on the basis of preset appointed positions in a coal mine scene, through triggering of the non-safety behavior identification, character identification of operators related to the non-safety behaviors is executed on the basis of corresponding captured images, and then corresponding test questions are selected to construct assessment test paper and pushed to corresponding operators to execute the assessment by combining with a test question library formed by the preset test questions respectively corresponding to mine operation labels, so that the safety operation skills of the coal mine operators are improved; a corresponding system is designed, and based on the designed method, a network architecture with corresponding functions is constructed, so that the safety identification and assessment of the operation behaviors of the coal mine scene can be efficiently realized;
(2) the coal mine scene operation behavior safety identification and assessment method and the system correlate the unsafe behavior of the video identification personnel with training, apply the video identification technology, enable the camera to replace eyes of people, enable the computer to replace brains of people, realize 24-hour real-time detection, identify the unsafe behavior of the personnel, and solve the problems of insufficient staring and prevention of the personnel and safety management blind spots; the training question bank is automatically generated according to the severity and type classification of unsafe behaviors of the personnel for the user to learn, simulate and test, so that accurate and effective training of the user is realized, the training efficiency and precision of the personnel are effectively improved, and the coal mine safety production is ensured to be smoothly carried out.
Drawings
FIG. 1 is a system architecture diagram of a coal mine scene operation behavior safety identification and assessment method designed by the invention;
FIG. 2 is a block diagram of the present invention;
FIG. 3 is a schematic diagram of the classification and labeling of the entry of the test question library according to the present invention;
FIG. 4 is a schematic flow chart of a system designed according to this invention;
fig. 5 is a flow chart illustrating the identification of unsafe operator behavior in accordance with the present invention.
Detailed Description
The following description will explain embodiments of the present invention in further detail with reference to the accompanying drawings.
The invention designs a coal mine scene operation behavior safety identification and assessment method, which is based on a behavior identification device and an image capture device, wherein the behavior identification device is arranged at each preset specified position in a coal mine scene and is used for detecting each preset specified type of non-safety behavior, and the image capture device is used for capturing images of each specified type of non-safety behavior, and each specified position is executed according to the following steps.
Step A, detecting whether a specified type of non-safety behavior occurs or not by a behavior recognition device aiming at a specified position where the behavior recognition device is located, and if so, entering step B; otherwise, the behavior recognition device continues to detect.
Step b. obtaining, by the image capturing apparatus, a face image containing an operator who performs the specified type of non-safety action, and then proceeding to step C.
And C, according to the facial image of the operator with the specified type of non-safety behavior, applying a trained facial recognition model with the facial image as input and the identity information of the operator corresponding to the facial image as output to obtain the identity information of the operator with the specified type of non-safety behavior, and then entering the step D.
In practical applications, the face recognition model in step C is obtained as follows in steps C1 to C2.
Step C1, for each preset designated operator, collecting the face images of each operator corresponding to each preset face posture respectively, constructing the corresponding relation between each face image and the identity information of the corresponding operator, and then entering the step C2; wherein, the preset facial postures comprise preset facial angles, and mask, clean face, safety helmet and safety helmet which are not worn.
And step C2, training aiming at a preset classification network according to each face image and the identity information of the operator corresponding to each face image, taking the face image as input and the identity information of the operator corresponding to the face image as output to obtain a face recognition model.
The detection algorithm based on deep learning, the computer vision target detection algorithm and the intelligent recognition algorithm package are used for detecting and recognizing a moving target in real time, a computer is used for analyzing and extracting specific behaviors of people in a visual field range, a series of personnel behaviors such as safety helmet detection, work clothes detection, call making detection, safety belt detection, personnel leaving a post, sleeping a post, entering a forbidden area, chasing monkey cars and the like are detected for the people through the technologies such as computer vision, artificial intelligence, deep learning and the like, and when the underground illumination is insufficient, the mine lamp and the safety helmet are interfered and the face appearance is unstable, the illumination normalization of a face image under an over-strong condition is adopted, the personnel characteristics are extracted on the basis, and the identification is further carried out; and a convolutional neural network and a video compensation technology optimization algorithm are particularly adopted, so that the most effective effect of the design purpose of the invention is achieved.
And D, according to the specified type of non-safety behavior, combining the preset corresponding relation between each specified type of non-safety behavior and each mine operation label, randomly selecting the test questions with the preset test quantity corresponding to the specified type of non-safety behavior from a test question library formed by the test questions preset to respectively correspond to each mine operation label to form an examination paper, and entering the step E.
In application, as shown in fig. 3, each mine operation label corresponding to each test question in the test question library includes a coal mining operation label, a tunneling operation label, a blasting operation label, a lifting transportation electromechanical device operation label, a defense operation label, an auxiliary transportation operation label, a ground test operation label, a monitoring and monitoring operation label, a comprehensive operation label and a general operation label.
Step E, pushing the examination paper to the operator of the specified type of non-safety behavior according to the identity information of the operator of the specified type of non-safety behavior, executing examination, and if the examination passes, indicating that the operator of the specified type of non-safety behavior passes the examination; and if the assessment is not passed, returning to the step D.
In practical applications, the behavior recognition device is respectively arranged at each designated position for detecting each preset designated type of non-safety behavior, for example, each designated type of non-safety behavior includes that a preset designated area is prohibited from entering, the behavior recognition device for detecting the preset designated area is an image capture device with an image capture area covering the preset designated area, and whether the type of non-safety behavior occurs is detected by comparing whether an image captured by the image capture device contains an image of an operator.
Or each appointed type of non-safety behavior comprises a non-safety behavior for alarming based on preset sensing data corresponding to each appointed operated object, the behavior recognition device aiming at the appointed type of non-safety behavior is the sensor arranged on each appointed operated object and is used for detecting the sensing data corresponding to each appointed operated object, and whether the type of non-safety behavior occurs is detected by comparing whether each obtained sensing data exceeds a preset corresponding threshold range.
Based on the designed coal mine scene operation behavior safety identification and assessment method, the invention further designs a corresponding system, as shown in fig. 1, which comprises an access layer, a network layer, a data layer, an application layer, a presentation layer and a user layer, wherein the access layer is used for realizing video monitoring access of each image capturing device in a coal mine scene, collecting coal mine video data required by system construction and providing data support; the network layer is used for providing a channel for the transmission of data received by the access layer and mainly relates to the Internet, a video private network and the like; the system is accessed to the ring network switch through Ethernet interface or RS 485/232; based on the security requirement, the data transmission security is ensured among the networks through a firewall and a security boundary; the data layer is used for analyzing and identifying data transmitted by the network layer, namely executing the steps A to C, intelligently analyzing video image data based on a big data platform, comprehensively analyzing various real-time personnel image data, identifying and classifying types and severity based on unsafe behaviors of personnel, and providing high-price value data through statistical analysis; the application layer is used for realizing the construction of the question bank, executing the step D, and specifically realizing the functions of real-time monitoring of personnel behaviors, inputting, inquiring, editing, automatic generation and the like of the training question bank; the presentation layer is used for displaying the operation of the system; and E, the user layer is used for examination question assessment of coal mine operators, namely the step E is executed.
In the application, the decoupling of the algorithm package and the video stream is realized, the algorithm resource scheduling layer is added, the large calculation resource database of each unsafe behavior event is formed according to the configuration options of the user, and then the data is classified and learned, so that the severity and type classification requirements of each unsafe behavior are realized. And then networking to perform online distributed computation, and dynamically allocating computing resources (GPU and RAM) for online video detection according to the severity and type of the event formed by pre-detection, thereby optimizing parallel computation, preventing the situations of computation congestion and resource exhaustion, and achieving the aim of quick real-time response.
Specifically, based on the network architecture, the design system comprises video identification management, training plan management, training data management, simulation question bank management, a training examination system and training record management.
The system adopts a B/S mode, consists of a foreground user training part and a background system management part, and an authorized user can log in the system through a browser without installing a client.
Foreground user training part: the user training application terminal comprises a data learning module, a simulation exercise module, a training examination module and an examination result inquiry module.
A background management part: the administrator application terminal has a plurality of functions such as video identification management, training plan management, training data management, simulation question bank management, training examination paper management, examination state management, user information management, administrator authority management and the like.
As shown in fig. 4, firstly, a system administrator uniformly enters a test question library, and each question is given to a label for registration according to unsafe behavior categories and risk categories. The method comprises the steps of collecting personnel information in advance, establishing a personnel image database including the states of covering, cleaning, wearing safety helmets, not wearing safety helmets and the like, and realizing video identification of unsafe behaviors of personnel based on an AI algorithm, a deep learning detection algorithm, a computer vision target detection algorithm and the like. And secondly, the system automatically generates a corresponding training test question according to the severity and the type of the unsafe behaviors identified by the video and pushes test information. And finally, the personnel push the information to take an examination through the received examination, the examination is finished after the training is passed, and the examination is not passed, so that the examination information is continuously pushed, and further closed-loop accurate training management is realized.
As shown in fig. 5, the intelligent video recognition and accurate training system for coal mine personnel unsafe behavior recognition is to collect personnel information and establish a personnel image database including a shading surface, a cleaning surface, a safety helmet and a safety helmet-free state. And secondly, comparing the human image with the human behavior based on an AI algorithm, a deep learning detection algorithm and a computer vision target detection algorithm to identify unsafe behaviors of the human. And finally comparing the results, and displaying/inquiring the severity and type of unsafe behaviors of the personnel.
The invention relates to a coal mine scene operation behavior safety identification and assessment method and a system, which are based on the analysis of the current coal mine safety management situation, apply an intelligent video identification technology, and specifically build based on a Windows operating system, an SQL Server database platform and a J2EE platform in practical implementation, so as to associate the unsafe behavior of video identification personnel with training.
The intelligent video identification can automatically detect, identify and track the moving target of the video image in real time, structurally analyze the video in real time through the technologies of artificial intelligence, deep learning and the like, understand the image picture, realize the real-time detection of unsafe behaviors of people, and form a corresponding question bank to push according to the severity and the type of the detected unsafe behaviors so as to realize accurate training. The system adopts a B/S mode, consists of a foreground user training part and a background system management part, and an authorized user can log in the system through a browser without installing a client. The system adopts an open structure, has good compatibility, and can be in butt joint with various application software as long as a database interface is provided. By combining the requirements of users, the system can realize the management of various question banks for learning, simulation and examination; the user can look up the historical training examination scores and examination papers; and the score recording management can support the examination student score filing, manage historical data and meet the requirements of learning, training, examination and record management in a network environment. The system realizes paperless, networked and automatic computer online learning and training examination of enterprises.
The whole design is based on a behavior recognition device which is respectively arranged at each preset specified position in a coal mine scene and is used for detecting each preset specified type of non-safety behavior and an image capture device which is used for capturing images of each specified type of non-safety behavior, character recognition of operators on the non-safety behavior is executed on the basis of corresponding captured images through triggering of the non-safety behavior recognition, then corresponding test questions are selected to construct examination paper in combination with a test question library which is formed by the test questions preset to respectively correspond to each mine operation label, and the examination paper is pushed to corresponding operators to execute examination, so that the safety operation skills of the coal mine operators are improved; and a corresponding system is designed, and based on the designed method, a network architecture with corresponding functions is constructed, so that the safety identification and assessment of the operation behaviors of the coal mine scene can be efficiently realized.
In the application, unsafe behaviors of video recognition personnel are associated with training, the video recognition technology is applied, the camera replaces eyes of a person, the computer replaces a brain of the person, real-time detection for 24 hours is realized, the unsafe behaviors of the personnel are recognized, and the problems of insufficient staring and safety management blind spots of the personnel are solved; the training question bank is automatically generated according to the severity and type classification of unsafe behaviors of the personnel for the user to learn, simulate and test, so that accurate and effective training of the user is realized, the training efficiency and precision of the personnel are effectively improved, and the coal mine safety production is ensured to be smoothly carried out.
The embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (8)
1. A coal mine scene operation behavior safety identification and examination method is characterized in that: based on a behavior recognition device which is respectively arranged at each preset designated position in a coal mine scene and is used for detecting each preset designated type of non-safety behavior and an image capturing device which is used for capturing images of each designated type of non-safety behavior, each designated position is respectively executed according to the following steps:
step A, detecting whether a specified type of non-safety behavior occurs or not by a behavior recognition device aiming at a specified position where the behavior recognition device is located, and if so, entering step B; otherwise, the behavior recognition device continues to detect;
b, obtaining a face image containing an operator who executes the specified type of non-safety behavior by the image capturing device, and then entering step C;
c, according to the facial image of the operator with the specified type of non-safety behavior, applying a trained facial recognition model with the facial image as input and the identity information of the operator corresponding to the facial image as output to obtain the identity information of the operator with the specified type of non-safety behavior, and then entering the step D;
d, according to the specified type of non-safety behavior, combining with the preset corresponding relation between each specified type of non-safety behavior and each mine operation label, randomly selecting each test question with the preset test quantity corresponding to the specified type of non-safety behavior from a test question library formed by each test question preset to respectively correspond to each mine operation label to form an examination paper, and entering the step E;
and E, pushing the examination paper to the operator of the specified type of non-safety behavior according to the identity information of the operator of the specified type of non-safety behavior, and executing examination.
2. The coal mine scene operation behavior safety identification and assessment method according to claim 1, characterized in that: the test paper is pushed to the operator of the specified type of non-safety behavior to execute the examination process, and if the examination is passed, the operator of the specified type of non-safety behavior passes the examination; and if the assessment is not passed, returning to the step D.
3. The coal mine scene operation behavior safety identification and assessment method according to claim 1, characterized in that: the face recognition model in the step C is obtained according to the following steps C1 to C2;
step C1, for each preset designated operator, collecting the face images of each operator corresponding to each preset face posture respectively, constructing the corresponding relation between each face image and the identity information of the corresponding operator, and then entering the step C2;
and step C2, training aiming at a preset classification network according to each face image and the identity information of the operator corresponding to each face image, taking the face image as input and the identity information of the operator corresponding to the face image as output to obtain a face recognition model.
4. The coal mine scene operation behavior safety identification and assessment method according to claim 3, characterized in that: the preset facial postures in the step C1 comprise preset facial angles, a face covering surface, a face cleaning surface, a safety helmet and a safety helmet which is not worn.
5. The coal mine scene operation behavior safety identification and assessment method according to claim 1, characterized in that: and if the specified types of non-safety behaviors comprise that the preset specified area is forbidden to enter, the behavior recognition device for detecting the forbidden entering of the preset specified area is an image capture device with an image capture area covering the preset specified area, and whether the type of non-safety behaviors appear is detected by comparing whether the image of an operator exists in the image captured by the image capture device.
6. The coal mine scene operation behavior safety identification and assessment method according to claim 1, characterized in that: and the behavior identification device aiming at the specified type of non-safe behavior is the sensors arranged on the specified operated objects and is used for detecting the sensing data corresponding to the specified operated objects and detecting whether the type of non-safe behavior occurs or not by comparing whether the obtained sensing data respectively exceeds the range of the preset corresponding threshold value or not.
7. The coal mine scene operation behavior safety identification and assessment method according to claim 1, characterized in that: the mine operation labels corresponding to the test questions in the test question library comprise coal mining operation labels, tunneling operation labels, blasting operation labels, lifting transportation electromechanical equipment operation labels, defense operation labels, auxiliary transportation operation labels, ground test operation labels, monitoring operation labels, comprehensive operation labels and general operation labels.
8. A coal mine scene operation behavior safety identification and assessment method based on any one of claims 1 to 7 is characterized in that: the system comprises an access layer, a network layer, a data layer, an application layer, a presentation layer and a user layer, wherein the access layer is used for realizing video monitoring access of each image capturing device in a coal mine scene; the network layer is used for providing a channel for the transmission of the data received by the access layer; the data layer is used for analyzing and identifying the data transmitted by the network layer, namely executing the steps A to C; the application layer is used for realizing the construction of the test question bank and executing the step D; the presentation layer is used for displaying the operation of the system; and E, the user layer is used for examination question assessment of coal mine operators, namely the step E is executed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210105594.7A CN114429677A (en) | 2022-01-28 | 2022-01-28 | Coal mine scene operation behavior safety identification and assessment method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210105594.7A CN114429677A (en) | 2022-01-28 | 2022-01-28 | Coal mine scene operation behavior safety identification and assessment method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114429677A true CN114429677A (en) | 2022-05-03 |
Family
ID=81312732
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210105594.7A Pending CN114429677A (en) | 2022-01-28 | 2022-01-28 | Coal mine scene operation behavior safety identification and assessment method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114429677A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117095465A (en) * | 2023-10-19 | 2023-11-21 | 华夏天信智能物联(大连)有限公司 | Coal mine safety supervision method and system |
-
2022
- 2022-01-28 CN CN202210105594.7A patent/CN114429677A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117095465A (en) * | 2023-10-19 | 2023-11-21 | 华夏天信智能物联(大连)有限公司 | Coal mine safety supervision method and system |
CN117095465B (en) * | 2023-10-19 | 2024-02-06 | 华夏天信智能物联(大连)有限公司 | Coal mine safety supervision method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110674772B (en) | Intelligent safety control auxiliary system and method for electric power operation site | |
CN112396658B (en) | Indoor personnel positioning method and system based on video | |
CN109145789A (en) | Power supply system safety work support method and system | |
CN109298785A (en) | A kind of man-machine joint control system and method for monitoring device | |
CN110139067A (en) | A kind of wild animal monitoring data management information system | |
CN113807240A (en) | Intelligent transformer substation personnel dressing monitoring method based on uncooperative face recognition | |
CN110543866A (en) | Safety management system and method for capital construction engineering constructors | |
KR20200052418A (en) | Automated Violence Detecting System based on Deep Learning | |
CN112528860A (en) | Safety tool management method and system based on image recognition | |
CN108776452B (en) | Special equipment field maintenance monitoring method and system | |
CN116416281A (en) | Grain depot AI video supervision and analysis method and system | |
CN113269039A (en) | On-duty personnel behavior identification method and system | |
CN111860187A (en) | High-precision worn mask identification method and system | |
CN114429677A (en) | Coal mine scene operation behavior safety identification and assessment method and system | |
CN116682162A (en) | Robot detection algorithm based on real-time video stream | |
CN115860979A (en) | Artificial intelligence management system for field operation of power grid | |
CN115829324A (en) | Personnel safety risk silent monitoring method | |
CN115240277A (en) | Security check behavior monitoring method and device, electronic equipment and storage medium | |
CN115147777A (en) | Method for identifying illegal behaviors of crews | |
CN114241400A (en) | Monitoring method and device of power grid system and computer readable storage medium | |
CN114937308A (en) | Intelligent security system based on human body dynamic behavior feature recognition and implementation method thereof | |
CN113420711A (en) | Service industry worker service behavior recognition algorithm and system | |
Suhirja et al. | Adopting Haar Cascade Algorithm on Mask Detection System Based on Distance | |
CN112418055A (en) | Scheduling method based on video analysis and personnel trajectory tracking method | |
CN109544855A (en) | Track traffic synthetic monitoring fire closed-circuit television system and implementation method based on computer vision |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 210000 room 110-80, Building 29, No. 5, Gaoke fifth road, Jiangbei new area, Nanjing, Jiangsu Province Applicant after: Nanjing Yehengda Intelligent System Co.,Ltd. Address before: 210031 No. 20, Pudong Road, Pukou District, Jiangsu, Nanjing Applicant before: Nanjing Yihengda Intelligent Systems Co.,Ltd. |