CN113408338A - Method, device and system for monitoring abnormal behavior of miner - Google Patents
Method, device and system for monitoring abnormal behavior of miner Download PDFInfo
- Publication number
- CN113408338A CN113408338A CN202110512973.3A CN202110512973A CN113408338A CN 113408338 A CN113408338 A CN 113408338A CN 202110512973 A CN202110512973 A CN 202110512973A CN 113408338 A CN113408338 A CN 113408338A
- Authority
- CN
- China
- Prior art keywords
- miners
- monitoring
- abnormal
- miner
- block chain
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 123
- 206010000117 Abnormal behaviour Diseases 0.000 title claims abstract description 118
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 238000003860 storage Methods 0.000 claims description 19
- 230000008569 process Effects 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 238000003708 edge detection Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 230000006399 behavior Effects 0.000 claims description 10
- 230000001681 protective effect Effects 0.000 claims description 7
- 238000007405 data analysis Methods 0.000 claims description 6
- 238000012806 monitoring device Methods 0.000 claims description 6
- 238000013500 data storage Methods 0.000 abstract description 4
- 239000003245 coal Substances 0.000 description 16
- 238000012545 processing Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000003909 pattern recognition Methods 0.000 description 3
- 238000000513 principal component analysis Methods 0.000 description 3
- 238000011410 subtraction method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/64—Protecting data integrity, e.g. using checksums, certificates or signatures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Computer Security & Cryptography (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Bioethics (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a method, a device and a system for monitoring abnormal behaviors of miners, wherein the method comprises the following steps: calling an identity registration contract deployed on the block chain to complete registration of identities of miners and affiliated enterprises; acquiring a monitoring video of a miner in an underground operation place; and identifying whether the miners have abnormal behaviors according to the monitoring video, and if the abnormal behaviors exist, calling an accident evidence contract deployed on the block chain to store corresponding information of the abnormal behaviors. The invention can improve the data storage safety, has small error rate of abnormal behavior detection and high stability, and reduces the manual monitoring cost and the possibility of accidents.
Description
Technical Field
The invention relates to the technical field of coal safety production monitoring, in particular to a method, a device and a system for monitoring abnormal behaviors of miners.
Background
In the operation process of miners of coal mine enterprises, due to the limitation of geographical distribution and work type specificity, dangerous conditions are easily caused by abnormal behaviors of the miners violating safety rules and the like.
At present, a centralized monitoring system is mainly used by coal mine enterprises to detect abnormal behaviors of miners, monitoring personnel are required to manually analyze a large amount of monitoring data, and due to limited energy of the monitoring personnel, the situations of abnormal behavior omission or dangerous misjudgment can occur. In addition, because the system is a centralized system, when a miner is injured by a human body, the difficulty of tampering the information related to the miner is low.
The monitoring efficiency and accuracy of the existing miner monitoring system on abnormal behaviors are not enough, and the information of the abnormal behaviors is easy to be tampered.
Disclosure of Invention
The invention solves the problems that the monitoring efficiency and the accuracy of the existing underground worker monitoring system for abnormal behaviors are insufficient, and the information of the abnormal behaviors is easy to be distorted.
In order to solve the above problems, the present invention provides a method for monitoring abnormal behavior of miners, comprising: calling an identity registration contract deployed on the block chain to complete registration of identities of miners and affiliated enterprises; acquiring a monitoring video of a miner in an underground operation place; and identifying whether the miner has abnormal behaviors according to the monitoring video, and calling an accident evidence contract deployed on the block chain to store information corresponding to the abnormal behaviors if the miner has the abnormal behaviors.
Optionally, the identifying whether the miners have abnormal behaviors according to the monitoring video includes: detecting a moving object according to the image frame of the monitoring video to obtain position information of a miner; and determining whether the miners enter the dangerous area or not according to the position information and the dangerous area divided in advance, and if so, determining that abnormal behaviors exist.
Optionally, the process of dividing the dangerous area includes: carrying out edge detection on the image frame of the monitoring video by adopting an edge detection algorithm to detect image edge pixels; determining the background of a monitoring area through a background learning algorithm, and dividing the background into a plurality of areas according to the image edge pixels; and receiving dangerous area setting information, and marking at least one area as a dangerous area according to the setting information.
Optionally, the identifying whether the miners have abnormal behaviors according to the monitoring video includes: detecting a moving object according to the image frame of the monitoring video to obtain an image of a miner; and identifying whether the miner has the abnormal wearing behavior of the protective article according to the image, and if so, determining that the abnormal behavior exists.
Optionally, the method further comprises: acquiring physiological data sent by wearable equipment; and identifying whether the miners have abnormal behaviors according to the physiological data, and calling an accident evidence contract deployed on the block chain to store information corresponding to the abnormal behaviors if the miners have the abnormal behaviors.
Optionally, the method further comprises: acquiring identity data sent by wearable equipment; and determining identity information of the miners according to the monitoring video and the identity data.
Optionally, the method further comprises: acquiring position data sent by wearable equipment; and verifying the position information of the miner according to the position data.
The invention provides a monitoring device for abnormal behavior of miners, which comprises: the registration module is used for calling an identity registration contract deployed on the block chain to complete registration of identities of miners and affiliated enterprises; the video acquisition module is used for acquiring a monitoring video of a miner on an underground operation place; and the abnormal monitoring module is used for identifying whether the miner has abnormal behaviors according to the monitoring video, and calling an accident evidence storage contract deployed on the block chain to store the information corresponding to the abnormal behaviors if the miner has the abnormal behaviors.
The invention provides a system for monitoring abnormal behaviors of miners, which comprises a video detection system and a block chain trusted background system, wherein the video detection system comprises a video acquisition module, a block chain trusted background system and a block chain trusted background system; the video detection system is used for collecting monitoring videos of miners in underground operation places; the block chain trusted background system comprises a big data analysis module and a block chain network; the block chain network is provided with an identity registration contract and an accident evidence storage contract; the big data analysis module is used for executing the monitoring method for the abnormal behavior of the miners.
Optionally, a miner wearable device is also included; the wearable equipment for the miners is connected with the block chain trusted background system and used for sending at least one of the following data of the miners to the block chain trusted background system: identity data, location data, physiological data.
The method and the device combine the block chain as the bottom storage, can improve the safety of data storage, adopt the automatic detection technology based on monitoring video identification, lead the system to have small error rate and high stability for detecting abnormal behaviors, reduce the manual monitoring cost, can more quickly and effectively discover risks and reduce the possibility of accidents of miners.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for monitoring abnormal behavior of miners in one embodiment of the invention;
FIG. 2 is a flow chart of the operation of a system for monitoring abnormal behavior of miners according to an embodiment of the present invention;
FIG. 3 is a flow chart of a background subtraction method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a monitoring device for abnormal behavior of miners according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
At present, centralized detection systems are mainly used in coal mine enterprises to detect abnormal behaviors of miners, and the systems need workers to manually analyze a large number of alarm signals, and some important alarm signals can be missed due to limited energy of the workers. In addition, since the above systems all use a centralized system, information related to a mineworker may be tampered with when the mineworker is injured.
The system provided by the invention mainly combines a block chain, image processing, pattern recognition and the like to construct a complete set of abnormal behavior monitoring system for miners, and the abnormal behavior of the miners is recognized and safely stored. When the abnormal behavior occurs, the system identifies the abnormal behavior and automatically sends alarm information. Specifically, a continuous video can be divided into a plurality of image frames according to time through an image recognition technology, each frame of image is used as input, the image is processed by combining with a background image generated in advance, information such as the position, abnormal behaviors and whether danger exists in the surrounding environment of a miner is analyzed, the danger possibly faced by the miner is analyzed through a series of images, and then alarm information is sent to the miner and a monitoring person. Specifically, the system for monitoring abnormal behavior of miners comprises a video detection system and a block chain trusted background system.
An embodiment of the present invention provides a method for monitoring abnormal behavior of miners, and fig. 1 is a schematic flow chart of a method for monitoring abnormal behavior of miners in an embodiment of the present invention, where the method is applicable to the above system for monitoring abnormal behavior of miners, and an identity authentication contract and an accident evidence saving contract are deployed on a block chain by a block chain trusted background system. The method comprises the following steps:
and S102, calling an identity registration contract deployed on the block chain to complete the registration of the identity of the miners and the affiliated enterprises.
The identity authentication contract deployed on the blockchain is used for managing the information of the user using the system, an enterprise user must register in a registry of the contract before using the system, and the registration information of the registered enterprise and the registered miners is stored in the identity authentication contract.
And S104, acquiring a monitoring video of the miner on the underground operation site.
The video detection system can collect the monitoring video of the underground operation place, and the monitoring video is sent to the block chain trusted background system after being collected. Alternatively,
and determining identity information of the miners according to the monitoring video. Optionally, the video detection system may execute a face recognition algorithm according to the image frames of the surveillance video, match the face images of a plurality of miners stored in advance, and determine identity information of the miners contained in the image frames based on matching results.
And S106, identifying whether the miner has abnormal behaviors according to the monitoring video, and calling an accident evidence storage contract deployed on the block chain to store corresponding information of the abnormal behaviors if the miner has the abnormal behaviors.
And identifying whether the miner has abnormal behaviors according to the monitoring video, and calling the accident evidence contract to store the information corresponding to the abnormal behaviors if the miner has the abnormal behaviors. Since the blockchain network mainly has the characteristics of decentralization, non-falsification, traceability, openness, anonymity, democratization and the like, decentralization means that the processes of data storage, updating, maintenance, operation and the like are all based on a distributed ledger, and are not based on a general server in a centralization mechanism. Therefore, the abnormal behavior corresponding information is stored based on the block chain technology, and the problem that the traditional method is easy to tamper due to centralized storage can be solved.
The monitoring method for the abnormal behavior of the miners, provided by the embodiment of the invention, combines the block chain as the bottom layer for storage, can improve the safety of data storage, adopts an automatic detection technology based on monitoring video identification, so that the system has small detection error rate and high stability for the abnormal behavior, reduces the manual monitoring cost, can find risks more quickly and effectively, and reduces the possibility of accidents of the miners.
The method is combined with the safety requirements of coal mine underground operation, and can detect the following two types of abnormal behaviors based on the monitoring video:
(1) detecting a moving target according to the image frame of the monitoring video to obtain the position information of a miner; and determining whether the miners enter the dangerous area or not according to the position information and the dangerous area divided in advance, and if so, determining that abnormal behaviors exist.
The moving miners are separated from the image frame through moving object detection to obtain the specific positions of the miners in the image frame, and whether the miners enter the dangerous area or not can be determined by combining the dangerous area which is divided in the image frame in advance.
Because the camera device of the underground operation place is mostly arranged in a fixed shooting direction, the dangerous area in the image frame shot by the camera device can be jointly divided by combining the dangerous area setting information input by a user and the dangerous area obtained by machine learning. Optionally, firstly, performing edge detection on an image frame of a monitoring video by using an edge detection algorithm to detect image edge pixels; secondly, determining the background of the monitoring area through a background learning algorithm, and dividing the background into a plurality of areas according to the image edge pixels; then, dangerous area setting information is received, and at least one area is marked as a dangerous area according to the setting information.
The background learning algorithm can be used for carrying out background self-learning on the image frames of the monitoring area, finding out the dangerous boundary of the operation area, dividing the dangerous area according to the edge pixels of the image, dividing a plurality of boundaries in the image process of the image frames, and dividing each area.
(2) Detecting a moving target according to the image frame of the monitoring video to obtain an image of a miner; and identifying whether the miner has the abnormal wearing behavior of the protective article according to the image, and if so, determining that the abnormal behavior exists.
After the part of the miner who moves is separated from the image frame, the wearing detection of the protective articles is executed according to the image, for example, the mode identification and other modes are adopted to determine whether the miner wears the predetermined protective articles, including reflective clothing, safety boots, safety helmets, gas masks, dust masks, explosion-proof miner lamps, self-rescuer, flash lamps and the like.
In order to further improve the monitoring efficiency and accuracy of the abnormal behavior of the miners, the abnormal behavior monitoring system for the miners can further comprise wearable equipment worn by the miners. The wearable device is connected with the block chain trusted background system, and can send at least one of the following data of the downhole worker to the block chain trusted background system: identity data, location data, physiological data. The wearable device comprises a position sensor, a physiological data sensor and a memory; the memory stores identity data of the miners bound in advance. For example, the wearable device can integrate various sensors, a memory, a signal processing chip and a communication chip on a bracelet, and input personal information of a miner, so that the binding relationship between the miner and the bracelet is completed.
Optionally, the method may further include, based on the wearable device: acquiring physiological data sent by wearable equipment; and identifying whether the miners have abnormal behaviors according to the physiological data, and if so, calling an accident evidence contract deployed on the block chain to store corresponding information of the abnormal behaviors. The physiological data includes blood pressure, heart rate, body temperature, etc. The current physical condition of the miners can be determined by comparing the physiological data of the miners uploaded by the wearable equipment in real time with the physiological data of the normal level of the human body, and if the physical condition is abnormal, abnormal behaviors are determined, and corresponding information of the miners needs to be stored in time.
Optionally, the method may further include, based on the wearable device: acquiring identity data sent by wearable equipment; and determining identity information of the miners according to the monitoring video and the identity data. As mentioned above, the video detection system may determine identity information of the miners based on a face recognition algorithm, and the wearable device may verify and recognize the determined identity information based on the identity data of the miners due to the fact that the wearable device is pre-bound with personal information of the miners. For example, set up the entrance guard in the key region, the miner passes through the video monitoring system when entrance guard and gathers miner's surveillance video and discern and obtain its identity information, and the collection equipment who matches with wearable equipment gathers miner's wearable equipment's identity data, and the identity is confirmed jointly in both verification each other, can improve system identification accuracy.
After the identity information is determined, if the corresponding miner has abnormal behavior, the accident evidence saving contract can be called to store the identity information and the information corresponding to the abnormal behavior together. Further, if abnormal behavior exists, alarm information can be sent to the underground workers and/or monitoring personnel corresponding to the identity information.
Optionally, the method may further include, based on the wearable device: acquiring position data sent by wearable equipment; and verifying the position information of the miner according to the position data. In a downhole environment, an indoor positioning method can be generally adopted, a plurality of signal sources are preset, and the wearable device can determine the actual position of the wearable device by calculating signals between the wearable device and the plurality of signal sources. Since the position information obtained based on the image frame of the surveillance video is the image coordinates in the image coordinate system, when the coordinates in the image coordinate system are verified according to the position data determined by the wearable device, the actual position needs to be converted into the image coordinates in the image coordinate system and then compared.
Specifically, after the camera device of the video monitoring system is fixedly installed, the position calibration can be performed, that is, the corresponding relationship between the actual position and the image coordinate is calibrated in advance. For example, the wearable device is moved according to a certain rule to traverse the whole acquisition range of the camera device, and the actual position determined by the wearable device at the same time is correspondingly stored with the image coordinate obtained by image frame recognition, so as to obtain the corresponding relation between the actual position and the image coordinate. Due to the positioning accuracy problem of the wearable device, a certain error may exist after the actual position is converted into the image coordinate, and the coordinate obtained through conversion and the image coordinate obtained based on the image frame can be determined to be verified within a certain error range.
The embodiment of the invention also provides a system for monitoring the abnormal behavior of the miners, which comprises a video detection system and a block chain trusted background system.
The video detection system is used for collecting monitoring videos of miners in underground operation places; the block chain trusted background system comprises a big data analysis module and a block chain network; the block chain network is provided with an identity registration contract and an accident evidence storage contract; the big data analysis module is used for executing the monitoring method for the abnormal behavior of the miners.
Optionally, the miner abnormal behavior monitoring system further comprises a miner wearable device; the wearable equipment for the miners is connected with the block chain trusted background system and used for sending at least one of the following data of the miners to the block chain trusted background system: identity data, location data, physiological data.
For example, in the system for monitoring abnormal behavior of miners provided in the embodiment of the present invention, the participating parties may include a coal enterprise, miners, and monitoring departments (security monitoring departments, fire protection departments, and other institutions), all nodes of the block chain are maintained by the monitoring departments and the coal enterprise together, and any party cannot tamper with information stored in the block chain. Referring to the operation flow chart of the system for monitoring the abnormal behavior of the miners shown in fig. 2, the system comprises the miners, the coal enterprises, the supervision department, the monitoring personnel, the video detection system and the block chain trusted background system, and the operation flow is as follows:
1. and deploying the identity authentication contract and the accident deposit contract.
The block chain trusted background system deploys identity authentication contracts and accident prevention contracts on the block chain. The accident evidence contract is used for storing the abnormal behavior information of miners on the chain; the identity authentication contract is responsible for the management of information about users using the system, and enterprise users must register in the registry of the contract before using the system. The identity authentication contract stores the registration information of the registered enterprises and the registered miners. The enterprise registry is shown in table 1, the worker registry is shown in table 2, and the information stored in the tables mainly includes: enterprise public key, identity information, service status, and registration time. In addition, the authentication and verification information of the requester is also maintained by the table, and the registry mainly comprises the following information: public key: maintaining public key information of enterprises or miners; unit information: maintaining detailed unit information of enterprises; service state: marking the business operation state; registration time: marking the time of the business registration.
| Enterprise public key | Unit information | Service status | Registration time |
| Enterprise public key 1 | Unit 1 | Is normal | 2020/1/13 14:12 |
| Enterprise public key 2 | Unit 2 | Abnormality (S) | 2020/3/7 11:40 |
| Enterprise public key 3 | Unit 3 | Is normal | 2020/6/17 6:20 |
TABLE 1
| Worker's public key | Unit information | Registration time |
| Enterprise public key 1 | Unit 1 | 2020/3/13 14:12 |
| Enterprise public key 2 | Unit 2 | 2020/3/19 11:40 |
| Enterprise public key 3 | Unit 3 | 2020/8/17 6:20 |
TABLE 2
2. And (5) performing identity registration by the coal enterprises.
3. And the identity registration is carried out by the miners.
4. The behavior of the coal enterprise is monitored.
5. The behavior of the miners is monitored. The video detection system monitors the behaviors of coal enterprises and workers in real time. The system can process appearance information, behavior and action information, abnormal operation information and the like of miners, and upload the primarily processed information to the block chain trusted background system.
The video detection system can be composed of a camera, a video coding and decoding chip, an audio coding and decoding chip and a network transmission module. The collected audio video information was processed using a TMS320DM6437 digital media processor. The communication transmission between the monitoring detection system and the background PC adopts a mode of combining wired transmission and wireless transmission, so that the advantages of wired communication and wireless communication are complementary, and the stability and timeliness of the communication between the systems are ensured. The functions of the video detection system may include: the wearable equipment is linked to determine the environment position of a worker, confirm identity information of the worker and the like; and transmitting the collected audio and video, dangerous area division, worker identification and record and the like to the block chain trusted background system.
6. And sending the monitoring video.
The video detection system sends monitoring videos and the like to the block chain credible background system, the state of miners and surrounding environment information are monitored in real time, and if violation or abnormal phenomena are found, an accident evidence storage contract is called to complete accident evidence storage.
7. And calling an accident evidence contract.
The block chain credible background system can collect data from the wearable device and the video detection system, process and analyze the data, and can store abnormal behaviors to the block chain by calling an intelligent contract when the abnormal behaviors of miners occur, and the block chain can be maintained by a supervisor, a coal enterprise, a system developer and the like together, so that the data can be prevented from being tampered by a centralized server.
If the system is processed and analyzed to find that the miners have abnormal behaviors (such as no safety helmet is worn, the miners enter a dangerous area and the like), alarm information can be sent to monitoring personnel through a bracelet and a display device worn by the miners, and the information is stored in a block chain.
The block chain trusted background system can comprise three parts, namely big data analysis software, a block chain network, an alarm device and the like. The block chain network is responsible for credibly storing the abnormal behaviors of miners; the big data analysis software is responsible for processing, analyzing and judging whether abnormal behaviors occur or not, whether potential risks exist or not, whether physical conditions are good or not and the like. If abnormal behaviors are found, the miner is judged to be in a dangerous environment, and warning information needs to be sent to the corresponding miner and the monitoring personnel in time.
8. And sending alarm information by the wearable equipment of the miner.
The physical condition information of the miners can be collected through the wearable device, and the collected physical state information is uploaded to the block chain credible background system and alarm information is sent out.
9. And acquiring abnormal behavior information.
Monitoring personnel receive abnormal behavior information from the block chain trusted background system and need to perform on-site troubleshooting on the abnormal behavior to eliminate potential safety hazards. Optionally, the block chain trusted background system further includes a display device for displaying the monitoring video and the alarm information for the monitoring personnel to view.
10. And (5) real-time supervision.
And the supervision department supervises the behaviors of coal enterprises and miners in real time through the block chain storage information. The monitoring mechanism synchronizes the information on the chain in real time, thereby effectively carrying out monitoring work on coal mine enterprises.
11. And (5) punishing after the fact. The supervision department carries out post-event punishment on the illegal behaviors of coal enterprises and miners.
The following describes in detail the process of processing the monitoring video by the block chain trusted background system through the video recognition technology. The specific process is as follows:
firstly, calling an API (Application Programming Interface) built in an Opencv open source library to generate a series of image frames from continuous videos according to a time sequence, wherein the image frames can be used as a basis for intelligent identification. And carrying out gray level and filtering processing on the acquired image frame, converting the RGB color image into a gray level image, and removing noise information in the image.
And the image with the noise removed is enhanced by using an enhancement algorithm, the enhancement algorithm can show the points with the obviously changed neighborhood intensity, and the edge information of the image is obtained by carrying out edge detection. And (5) carrying out edge detection on the image by using a Canny edge detection operator, and detecting edge points of the image by using the gradient amplitude of the image. The gradient is the intensity of the change of the image in both horizontal and vertical directions, and the gradient of the continuous function f (x, y) is represented by Δ f (x).
And carrying out background self-learning on the image by utilizing a background learning algorithm to find out the dangerous boundary of the operation area. Then, dangerous areas are divided according to image edge pixels, a plurality of boundaries are defined in the process of previewing the image of the frame, and each dangerous area is divided.
And detecting whether miners appear in the image by using a Support Vector Machine (SVM), detecting a moving object of the video, and separating the moving miners from the image.
The identity information of the miners is confirmed by performing face recognition based on Principal Component Analysis (PCA) on the part of the moving miners. The principal component analysis algorithm is a data dimension reduction algorithm, and dimension reduction processing of data characteristics can be achieved.
And the identity information matching is carried out on the collected videos in the processes and the wearable equipment of the miners. The method comprises the steps of detecting the appearance of the dressing of the miner, storing information to a chain if the miner is found not to be working underground according to regulations by wearing protective tools such as a safety helmet and the like, and meanwhile pushing the information to an alarm system to warn the miner.
Tracking and identifying a moving target appearing in the video, recording the moving position of the moving target, extracting a moving part in the image by using a background subtraction method, and carrying out difference identification on the background image and the input current image to identify a moving area. Referring to the flow diagram of the background subtraction method shown in fig. 3, the method includes the following steps: 1. inputting a current image frame, 2 inputting a background image, 3 executing a difference operation, 4 binarizing calculation, 5 morphologically filtering, and 6 extracting a motion region.
After the motion area is extracted, a series of operations such as filtering and corrosion are required to obtain the motion target. When the system detects that a miner crosses a boundary and enters a possibly existing dangerous area, the collected information is analyzed in multiple directions, and the danger is graded and then reported to monitoring personnel.
According to the monitoring system for the abnormal behaviors of miners, a set of complete monitoring system for the abnormal behaviors of the miners is constructed by utilizing image processing, pattern recognition and the like, the block chain is used as a bottom-layer storage facility, once data are linked, anyone can not tamper the data, the credibility of the system is enhanced, and a supervision department can effectively implement supervision work on coal enterprises according to the data on the chain; by adopting automatic detection technologies such as image processing, pattern recognition and the like, the system has the characteristics of small error rate and high stability when detecting abnormal behaviors, the monitoring cost is reduced, the danger of miners can be prompted more quickly and effectively, and the possibility of accidents is greatly reduced.
An embodiment of the present invention further provides a monitoring device for abnormal behavior of miners, and fig. 4 is a schematic structural diagram of the monitoring device for abnormal behavior of miners in an embodiment of the present invention, where the monitoring device includes:
the registration module 401 is configured to invoke an identity registration contract deployed on the blockchain to complete registration of identities of miners and affiliated enterprises;
a video acquisition module 402, configured to acquire a monitoring video of a miner at an underground operation site;
and the abnormal monitoring module 403 is configured to identify whether an abnormal behavior exists for a miner according to the monitoring video, and if the abnormal behavior exists, call an accident evidence storage contract deployed on the block chain to store information corresponding to the abnormal behavior.
Optionally, the anomaly monitoring module 403 is specifically configured to: detecting a moving object according to the image frame of the monitoring video to obtain position information of a miner; and determining whether the miners enter the dangerous area or not according to the position information and the dangerous area divided in advance, and if so, determining that abnormal behaviors exist.
Optionally, the anomaly monitoring module 403 is specifically configured to: carrying out edge detection on the image frame of the monitoring video by adopting an edge detection algorithm to detect image edge pixels; determining the background of a monitoring area through a background learning algorithm, and dividing the background into a plurality of areas according to the image edge pixels; and receiving dangerous area setting information, and marking at least one area as a dangerous area according to the setting information.
Optionally, the anomaly monitoring module 403 is specifically configured to: detecting a moving object according to the image frame of the monitoring video to obtain an image of a miner; and identifying whether the miner has the abnormal wearing behavior of the protective article according to the image, and if so, determining that the abnormal behavior exists.
Optionally, the anomaly monitoring module 403 is further configured to: acquiring physiological data sent by wearable equipment; and identifying whether the miners have abnormal behaviors according to the physiological data, and calling an accident evidence contract deployed on the block chain to store information corresponding to the abnormal behaviors if the miners have the abnormal behaviors.
Optionally, the apparatus further comprises a verification module configured to: acquiring identity data sent by wearable equipment; and determining identity information of the miners according to the monitoring video and the identity data.
Optionally, the verification module is further configured to: acquiring position data sent by wearable equipment; and verifying the position information of the miner according to the position data.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements the processes of the foregoing embodiments, and can achieve the same technical effects, and in order to avoid repetition, details are not repeated here. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
Of course, it will be understood by those skilled in the art that all or part of the processes in the above embodiments may be implemented by instructing the control device through a computer program, where the program may be stored in a computer-readable storage medium, and the program may include the processes in the above embodiments when executed, where the storage medium may be a memory, a magnetic disk, an optical disk, and so on.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for monitoring abnormal behaviors of miners is characterized by comprising the following steps:
calling an identity registration contract deployed on the block chain to complete registration of identities of miners and affiliated enterprises;
acquiring a monitoring video of a miner in an underground operation place;
and identifying whether the miner has abnormal behaviors according to the monitoring video, and calling an accident evidence contract deployed on the block chain to store information corresponding to the abnormal behaviors if the miner has the abnormal behaviors.
2. The method for monitoring the abnormal behavior of the miners according to the claim 1, wherein the step of identifying whether the miners have the abnormal behavior according to the monitoring videos comprises the following steps:
detecting a moving object according to the image frame of the monitoring video to obtain position information of a miner; and the number of the first and second groups,
and determining whether miners enter the dangerous area or not according to the position information and the dangerous area which is divided in advance, and if so, determining that abnormal behaviors exist.
3. The abnormal behavior monitoring method for miners according to claim 2, wherein the process of dividing the dangerous area comprises:
carrying out edge detection on the image frame of the monitoring video by adopting an edge detection algorithm to detect image edge pixels;
determining the background of a monitoring area through a background learning algorithm, and dividing the background into a plurality of areas according to the image edge pixels;
and receiving dangerous area setting information, and marking at least one area as a dangerous area according to the setting information.
4. The method for monitoring the abnormal behavior of the miners according to the claim 1, wherein the step of identifying whether the miners have the abnormal behavior according to the monitoring videos comprises the following steps:
detecting a moving object according to the image frame of the monitoring video to obtain an image of a miner; and the number of the first and second groups,
and identifying whether the miner has the abnormal wearing behavior of the protective article according to the image, and if so, determining that the abnormal behavior exists.
5. The method for monitoring abnormal behavior of miners according to claim 1, further comprising:
acquiring physiological data sent by wearable equipment;
and identifying whether the miners have abnormal behaviors according to the physiological data, and calling an accident evidence contract deployed on the block chain to store information corresponding to the abnormal behaviors if the miners have the abnormal behaviors.
6. The method for monitoring abnormal behavior of miners according to claim 1, further comprising:
acquiring identity data sent by wearable equipment;
and determining identity information of the miners according to the monitoring video and the identity data.
7. The method for monitoring abnormal behavior of miners according to claim 2, further comprising:
acquiring position data sent by wearable equipment;
and verifying the position information of the miner according to the position data.
8. A miner abnormal behavior monitoring device is characterized by comprising:
the registration module is used for calling an identity registration contract deployed on the block chain to complete registration of identities of miners and affiliated enterprises;
the video acquisition module is used for acquiring a monitoring video of a miner on an underground operation place;
and the abnormal monitoring module is used for identifying whether the miner has abnormal behaviors according to the monitoring video, and calling an accident evidence storage contract deployed on the block chain to store the information corresponding to the abnormal behaviors if the miner has the abnormal behaviors.
9. A monitoring system for abnormal behavior of miners is characterized by comprising a video detection system and a block chain trusted background system;
the video detection system is used for collecting monitoring videos of miners in underground operation places;
the block chain trusted background system comprises a big data analysis module and a block chain network; the block chain network is provided with an identity registration contract and an accident evidence storage contract;
the big data analysis module is used for executing the abnormal behavior monitoring method for miners as claimed in any one of claims 1 to 7.
10. The system for monitoring the abnormal behavior of the miners as claimed in claim 9, further comprising a miner wearable device;
the wearable equipment for the miners is connected with the block chain trusted background system and used for sending at least one of the following data of the miners to the block chain trusted background system: identity data, location data, physiological data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110512973.3A CN113408338A (en) | 2021-05-11 | 2021-05-11 | Method, device and system for monitoring abnormal behavior of miner |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110512973.3A CN113408338A (en) | 2021-05-11 | 2021-05-11 | Method, device and system for monitoring abnormal behavior of miner |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113408338A true CN113408338A (en) | 2021-09-17 |
Family
ID=77678384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110512973.3A Pending CN113408338A (en) | 2021-05-11 | 2021-05-11 | Method, device and system for monitoring abnormal behavior of miner |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113408338A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115168489A (en) * | 2022-06-28 | 2022-10-11 | 杭州钛度科技有限公司 | Data evidence storage method and device based on block chain |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400117A (en) * | 2013-07-29 | 2013-11-20 | 电子科技大学 | Method for positioning and tracking personnel in well on basis of compute vision |
| CN111123782A (en) * | 2019-12-24 | 2020-05-08 | 精英数智科技股份有限公司 | Coal mine informatization comprehensive monitoring method, device and system |
| CN111310865A (en) * | 2020-04-09 | 2020-06-19 | 李化玉 | Mine worker management system based on image recognition |
| CN112235295A (en) * | 2020-10-14 | 2021-01-15 | 安徽理工大学 | Method for troubleshooting and early warning potential safety hazards of coal mine |
-
2021
- 2021-05-11 CN CN202110512973.3A patent/CN113408338A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400117A (en) * | 2013-07-29 | 2013-11-20 | 电子科技大学 | Method for positioning and tracking personnel in well on basis of compute vision |
| CN111123782A (en) * | 2019-12-24 | 2020-05-08 | 精英数智科技股份有限公司 | Coal mine informatization comprehensive monitoring method, device and system |
| CN111310865A (en) * | 2020-04-09 | 2020-06-19 | 李化玉 | Mine worker management system based on image recognition |
| CN112235295A (en) * | 2020-10-14 | 2021-01-15 | 安徽理工大学 | Method for troubleshooting and early warning potential safety hazards of coal mine |
Non-Patent Citations (4)
| Title |
|---|
| ANKITSINGH等: "IoT Based information and communication system for enhancing underground mines safety and productivity: Genesis, taxonomy and open issues", 《AD HOC NETWORKS》 * |
| 孟亦凡: "煤矿井下人员安全状况智能监控系统", 《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》 * |
| 孟亦凡等: "基于LSTM边缘计算与随机森林雾决策的矿工状态监测设备", 《煤矿机械》 * |
| 梁小康等: "基于区块链技术的煤矿职工安全信息管理研究", 《煤矿安全》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115168489A (en) * | 2022-06-28 | 2022-10-11 | 杭州钛度科技有限公司 | Data evidence storage method and device based on block chain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Park et al. | Hardhat-wearing detection for enhancing on-site safety of construction workers | |
| CN104318732B (en) | Transformer substation field worker monitoring and management system and method based on video analysis and RFID | |
| CN112785798B (en) | Behavior analysis method for constructors of power substation engineering construction project | |
| CN103106766A (en) | Forest fire identification method and forest fire identification system | |
| CN110070155B (en) | Comprehensive behavior recognition method and system for prisoner based on wearable equipment | |
| KR102398841B1 (en) | Method and system for determining danger in constuction sites based on image analysis | |
| KR101036947B1 (en) | The automatic guard system to prevent the crime and accident using computer video image analysis technology | |
| CN112112629A (en) | Safety business management system and method in drilling operation process | |
| CN113034826A (en) | Video-based abnormal event warning method and system, equipment and storage medium thereof | |
| CN110285801A (en) | The localization method and device of intelligent safety helmet | |
| CN109800715B (en) | Park entrance and exit monitoring method and system based on Internet of things | |
| CN110650322A (en) | Security and protection system based on cloud service, Internet of things and AR security and protection glasses | |
| CN112257494A (en) | Behavior recognition method based on intelligent video analysis technology and application | |
| WO2023061239A1 (en) | Intelligent power distribution room safety management system | |
| CN109243139A (en) | A kind of personnel safety monitoring method, terminal device, system and storage medium | |
| CN111652185A (en) | Safety construction method, system, device and storage medium based on violation behavior recognition | |
| CN112651642A (en) | Hydraulic engineering field personnel safety management system based on multi-device perception | |
| CN111553305B (en) | System and method for identifying illegal videos | |
| CN112132048A (en) | Community patrol analysis method and system based on computer vision | |
| CN115410354A (en) | Safety early warning method, device and system for industrial plant | |
| CN112381435A (en) | Gridding directional pushing management method for dynamic risk in hydropower station operation process | |
| CN115660297A (en) | Automatic AI early warning system and method for construction site safety | |
| CN113011263A (en) | Mine monitoring method, device, terminal equipment and medium | |
| CN113408338A (en) | Method, device and system for monitoring abnormal behavior of miner | |
| CN115880631A (en) | Power distribution station fault identification system, method and medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210917 |