[go: up one dir, main page]

CN118823882B - Personnel prone pedaling mine car behavior identification method - Google Patents

Personnel prone pedaling mine car behavior identification method Download PDF

Info

Publication number
CN118823882B
CN118823882B CN202411309116.3A CN202411309116A CN118823882B CN 118823882 B CN118823882 B CN 118823882B CN 202411309116 A CN202411309116 A CN 202411309116A CN 118823882 B CN118823882 B CN 118823882B
Authority
CN
China
Prior art keywords
target person
risk assessment
target
abnormal behavior
mine car
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202411309116.3A
Other languages
Chinese (zh)
Other versions
CN118823882A (en
Inventor
陈震
熊鹏
林炫男
张晶晶
刘定泉
廖志强
姚信江
汤世豪
林俊清
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan Guotian Liyan Technology Co ltd
Original Assignee
Hunan Guotian Liyan Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hunan Guotian Liyan Technology Co ltd filed Critical Hunan Guotian Liyan Technology Co ltd
Priority to CN202411309116.3A priority Critical patent/CN118823882B/en
Publication of CN118823882A publication Critical patent/CN118823882A/en
Application granted granted Critical
Publication of CN118823882B publication Critical patent/CN118823882B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20Movements or behaviour, e.g. gesture recognition
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/70Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/70Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/774Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Human Computer Interaction (AREA)
  • Image Analysis (AREA)

Abstract

本发明涉及行为识别技术领域,具体为一种人员趴蹬矿车行为识别方法,该方法包括:对矿车运行区域进行划定得到目标区域,将处于目标区域的人员标记为目标人员;对目标人员的行为动作数据和行动轨迹数据进行采集,经处理得到各目标人员异常行为特征重合度和相对位置风险评估指数,综合分析得到各目标人员异常行为风险评估指数,根据各目标人员异常行为风险评估指数对人员异常行为进行风险评估,并反馈评估结果。本发明从行为和位置两个维度进行综合分析,能够更全面地捕捉目标人员的异常行为特征,使得风险评估更加全面和准确,并将目标人员进行风险等级划分,便于采取相应的管理措施,有利于提高管理的针对性和效率。

The present invention relates to the field of behavior recognition technology, specifically to a method for identifying the behavior of people kicking a mine car, the method comprising: demarcating the mine car operation area to obtain a target area, marking the people in the target area as target people; collecting the behavior action data and action trajectory data of the target people, obtaining the overlap degree of abnormal behavior characteristics and the relative position risk assessment index of each target person through processing, comprehensively analyzing to obtain the abnormal behavior risk assessment index of each target person, conducting risk assessment on the abnormal behavior of the people according to the abnormal behavior risk assessment index of each target person, and feeding back the assessment results. The present invention conducts a comprehensive analysis from the two dimensions of behavior and position, can more comprehensively capture the abnormal behavior characteristics of the target people, make the risk assessment more comprehensive and accurate, and divide the target people into risk levels, so as to facilitate the adoption of corresponding management measures, which is conducive to improving the pertinence and efficiency of management.

Description

Personnel prone pedaling mine car behavior identification method
Technical Field
The invention relates to the technical field of behavior recognition, in particular to a method for recognizing behaviors of a personnel prone to pedal a mine car.
Background
In mining production environments such as coal mines, personnel prone to pedal a mine car is an extremely dangerous unsafe behavior, and not only can endanger personal life safety, but also serious production accidents can be caused. Therefore, the real-time monitoring and early warning of unsafe behaviors of miners are realized by identifying the behaviors of the personnel for kicking the mine car.
For example, the invention of CN102227616B is a behavior recognition device comprising a manual operation observation unit for outputting hand movement data indicating the movement of a user's hand, a speed change detection unit for detecting the time when the movement of the user's hand takes a predetermined behavior pattern based on the hand movement data, a feature selection unit for selecting the hand movement data outputted at the time detected by the speed change detection unit, a behavior standard pattern storage unit for storing a behavior pattern data sequence expressed by a sequence of hand movement data for each behavior of the user, and a behavior recognition unit for recognizing, as the behavior of the user, a behavior expressed by a behavior pattern data sequence having the highest similarity, which is obtained based on the behavior pattern data sequence and the hand movement data selected by the feature selection unit, for each of the behavior pattern data sequences stored in the behavior standard pattern storage unit.
The invention patent with the bulletin number of CN113405580B is an automatic cigarette ash flicking smoking behavior recorder, and comprises a recorder main body, a power module and a control module, wherein the power module and the control module are arranged in the recorder main body, a filter rod insertion channel is formed in the recorder main body, a vibration module is arranged on the outer wall of the filter rod insertion channel, the power module is connected with the vibration module through a power supply line, a switching device is arranged on a power supply line, the control module controls a control end connected with the switching device to realize on-off control of the switching device, the automatic cigarette ash flicking behavior recorder also comprises an image acquisition module and an image recognition module connected with the image acquisition module, an image acquisition area of the image acquisition module is overlapped with an orifice front area of the filter rod insertion channel, and the image recognition module is connected with the control module. When the cigarette ash is required to be flicked, the cigarette is not required to be touched by hands or the recorder is rocked, and the recorder can automatically vibrate the cigarette through the vibration device to enable the cigarette ash to fall off when required through image recognition.
However, in the process of realizing the technical scheme of the embodiment of the application, the technical problems of the prior behavior recognition method are at least found that the existing behavior recognition method generally carries out recognition analysis on the generated behaviors through image recognition, delay can exist between data acquisition and behavior recognition, dangerous behaviors cannot be prevented from being generated in time, and potential safety hazards exist.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a method for identifying the behaviors of a personnel prone pedaling mine car, which can effectively solve the problems related to the background art.
The invention provides a method for identifying behaviors of a personnel prone to pedal a mine car, which comprises the steps of demarcating a mine car running area to obtain a target area, and marking personnel in the target area as target personnel.
And acquiring behavior and action data of the target personnel, and processing to obtain the abnormal behavior feature coincidence degree of each target personnel.
And acquiring the action track data of the target personnel, and processing to obtain the relative position risk assessment index of each target personnel.
According to the feature coincidence degree of the abnormal behaviors of each target person and the risk assessment index of the relative position, comprehensively analyzing to obtain the risk assessment index of the abnormal behaviors of each target person, carrying out risk assessment on the abnormal behaviors of the person according to the risk assessment index of the abnormal behaviors of each target person, and feeding back the assessment result.
The method comprises the steps of obtaining a minimum safety distance between personnel and a mine car from a mine car database, dividing the region by taking the minimum safety distance between the personnel and the mine car as a radius with the mine car position point as the center, marking the obtained region as a target region, and marking the personnel in the target region as target personnel.
The method comprises the steps of acquiring real-time video image data of a target person in a preset time period, wherein the real-time video image data comprise action track data and action data of the target person in the preset time period, and the action data of the target person comprise action feature images of the target person at each instant recording point.
According to the behavior feature images of each target person at each instantaneous recording point, a plurality of key joint position points are deployed on the images, a two-dimensional coordinate system is constructed to mark each key joint position point, and the specific processing process is as follows: Extracting each reference abnormal behavior characteristic image from a mine car database, matching to obtain similar abnormal behavior characteristic images according to the behavior characteristic images of each target person at each instantaneous record point, collecting each key joint position point of the similar abnormal behavior characteristic images, and marking as And comprehensively analyzing to obtain the characteristic coincidence degree of the abnormal behaviors of each target person.
As a further method, the action track data of the target personnel comprises the distance between each target personnel and the mine car and the action speed of each target personnel in a preset time period.
The method comprises the specific processes of marking the distance between each target person and the mine car as the relative distance between each target person, extracting the relative distance between the previous adjacent instantaneous record point and each target person at the current time point from the action track data of each target person in the preset time period, and carrying out difference between the relative distances between the previous adjacent instantaneous record point and each target person at the current time point, wherein if the difference is larger than 0, the target person is gradually approaching the mine car, and if the difference is smaller than 0, the target person is gradually far away from the mine car.
And extracting the critical action speed and the critical relative distance from the mine car database according to the action speed and the relative distance of each target person in a preset time period, and comprehensively analyzing to obtain the risk assessment index of the relative position of each target person.
According to the method, the risk assessment index of the abnormal behaviors of each target person is obtained through comprehensive analysis, and the specific analysis process is that the risk assessment index of the abnormal behaviors of each target person is obtained through comprehensive analysis according to the feature coincidence degree and the relative position risk assessment index of the abnormal behaviors of each target person, wherein the risk assessment index of the abnormal behaviors of each target person is used for quantitatively assessing the risk degree of the abnormal behaviors of each target person.
According to the risk assessment method, risk assessment is carried out on the groveling mine car behaviors of all target personnel according to the risk assessment indexes of the abnormal behaviors of all target personnel, the risk assessment index threshold value of the abnormal behaviors of all target personnel is extracted from a mine car database, the risk assessment index of the abnormal behaviors of all target personnel is compared with the risk assessment index threshold value of the abnormal behaviors of the target personnel, if the risk assessment index of the abnormal behaviors of a certain target personnel is higher than the risk assessment index threshold value of the abnormal behaviors of the target personnel, the risk of the abnormal behaviors of the target personnel is indicated to be high risk personnel, if the risk assessment index of the abnormal behaviors of a certain target personnel is equal to the risk assessment index threshold value of the abnormal behaviors of the target personnel, the risk of the abnormal behaviors of the target personnel is indicated to be medium level, if the risk assessment index of the abnormal behaviors of a certain target personnel is lower than the risk assessment index threshold value of the abnormal behaviors of the target personnel, the abnormal behaviors of the target personnel is indicated to be small, and the assessment result is fed back.
As a further method, the relative position risk assessment index of each target person is expressed as follows:
;
In the formula, Represents the relative position risk assessment index of the nth target person, n represents the number of each target person,M represents the total number of target persons,Indicating the speed of action of the nth target person,Indicating the relative distance of the nth target person,The critical speed of action is indicated by the speed of the action,Indicating the critical relative distance to each other,Representing the relative distance of the nth target person from the previous adjacent instantaneous entry point,Representing the relative distance of the nth target person at the current point in time,The risk assessment influence factor of the relative position corresponding to the action speed at the preset approaching time is represented,Representing a relative position risk assessment influence factor corresponding to the preset relative distance when approaching,Indicating a relative position risk assessment influence factor corresponding to the preset action speed at the time of keeping away,And representing a relative position risk assessment influence factor corresponding to the preset relative distance away.
As a further method, the risk assessment index of the abnormal behavior of each target person has the following specific numerical expression:
;
In the formula, Represents the risk assessment index of abnormal behaviors of the nth target person,Indicating the abnormal behavior feature coincidence degree of the nth target person,Representing an n-th target person relative position risk assessment index,Representing an abnormal behavior risk assessment influence factor corresponding to the preset abnormal behavior feature coincidence degree,And representing an abnormal behavior risk assessment influence factor corresponding to the preset relative position risk assessment index.
Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects:
(1) According to the method for identifying the behaviors of the prone pedaling mine car, the risk assessment index of the abnormal behaviors of each target person is obtained through analysis, comprehensive analysis is carried out from two dimensions of behaviors and positions, the abnormal behavior characteristics of the target person can be more comprehensively captured, risk assessment is more comprehensive and accurate, the target person is subjected to risk classification, management staff can conveniently take corresponding management measures according to the risk classification, and management pertinence and management efficiency are improved. Meanwhile, reasonable resource allocation can be realized, and more attention and resource investment of high-risk areas and high-risk personnel are ensured. Thereby being beneficial to reducing the risk of abnormal behaviors of target personnel and improving the safety and efficiency of mine operation;
(2) The invention can ensure that no personnel can access the dangerous distance without permission in the mine car running area by defining the target area. Is beneficial to reducing the risk of accidental injury caused by too close to the mine car. Once the system identifies the target person, an early warning mechanism can be immediately triggered to remind relevant persons of paying attention to safety, and the instant feedback mechanism is beneficial to quick response and prevents potential dangerous behaviors;
(3) According to the invention, the behavior characteristic image of the target person is matched with the reference abnormal behavior characteristic image in the mine car database, so that similar or identical abnormal behavior modes are automatically identified. The method is beneficial to improving the accuracy and efficiency of identification and reducing subjectivity and uncertainty of human judgment. And comprehensively analyzing to obtain the coincidence ratio of the abnormal behavior characteristics of each target person, and further determining whether the risk of prone to pedal the mine car exists. The higher the overlap ratio is, the more similar the behavior of the target person is to the behavior characteristics of the known groveling mine car, so that the reliability and the accuracy of identification are improved;
(4) According to the method, the action track data of each target person in the preset time period are continuously monitored, the relative position risk assessment index of each target person is obtained through analysis, and dynamic tracking of the person behaviors can be achieved. The real-time performance is helpful for timely finding and early warning possible risk behaviors, and meanwhile, the risk states of all target personnel relative to the mine car can be accurately estimated, so that the dangerous behaviors of which personnel are likely to be carrying out or are ready to carry out the groveling and pedaling of the mine car can be identified.
Drawings
The invention will be further described with reference to the accompanying drawings, in which embodiments do not constitute any limitation of the invention, and other drawings can be obtained by one of ordinary skill in the art without inventive effort from the following drawings;
FIG. 1 is a schematic flow chart of the method of the present invention;
Fig. 2 is a schematic diagram of a functional relationship between feature overlap ratio of abnormal behaviors of a target person and an abnormal behavior risk assessment index according to an embodiment of the present invention.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art without making creative efforts based on the embodiments of the present invention are included in the protection scope of the present invention.
Referring to fig. 1, the invention provides a method for identifying behaviors of a person riding on a mine car, which comprises the steps of demarcating a mine car running area to obtain a target area and marking the person in the target area as a target person.
The method comprises the specific steps of extracting a minimum safety distance between personnel and a mine car from a mine car database, demarcating the area by taking the mine car position point as the center and the minimum safety distance between the personnel and the mine car as the radius, marking the demarcating area as a target area, and marking the personnel in the target area as target personnel.
In one particular embodiment, by setting the minimum safe distance between the person and the mine car as a criterion for demarcating the area, it is ensured that no person is unauthorized to access within this dangerous distance in the mine car operating area. This directly reduces the risk of accidental injury to personnel due to too close proximity to the mine car, particularly the highly dangerous act of riding over the mine car. Once the system recognizes that a person exists in the target area, namely the target person, an early warning mechanism can be triggered immediately to remind the target person of paying attention to safety, and the instant feedback mechanism is beneficial to quick response and prevents potential dangerous behaviors, such as groveling and pushing a mine car. By clearly defining the mine car running area, personnel and mine cars can be guided to run according to the established path and rule, and confusion and conflict are reduced. The working efficiency is improved, and a more orderly and safe working environment is created. By continuously collecting and analyzing the data, the security policy can be further optimized, and the accuracy and the effectiveness of risk identification are improved. By long-term implementation of the safety management measure based on the delimited area, staff can gradually develop habits conforming to safety standards, and overall safety consciousness is improved, so that dangerous behaviors such as groveling and stepping a mine car and the like are actively avoided. In emergency situations, such as out of control or failure of a mine car, the system can quickly determine the distribution of personnel in the target area and provide important information for emergency response. This helps to evacuate personnel quickly, reducing accident losses.
And acquiring behavior and action data of the target personnel, and processing to obtain the abnormal behavior feature coincidence degree of each target personnel.
The method comprises the steps of collecting real-time video image data of a target person in a preset time period, wherein the real-time video image data comprise motion track data and behavior action data of the target person in the preset time period, and the behavior action data of the target person comprise behavior feature images of the target person at each instant recording point.
It should be explained that the behavioral action data of the target person also includes a thermal imaging image of the target person.
Further, the abnormal behavior feature coincidence ratio of each target person is obtained through processing, and the specific processing process is that according to the behavior feature images of each target person of each instantaneous recording point, a plurality of key joint position points are deployed on the images, a two-dimensional coordinate system is constructed to mark each key joint position point, and the key joint position points are marked as follows:
Extracting each reference abnormal behavior characteristic image from a mine car database, matching to obtain similar abnormal behavior characteristic images according to the behavior characteristic images of each target person of each instantaneous record point, and collecting each key joint position point of the similar abnormal behavior characteristic images, and marking as follows: comprehensively analyzing to obtain the characteristic coincidence degree of abnormal behaviors of each target person;
It should be noted that the key joint location points refer to the locations of joints playing a key role in connection and movement in the human body, and specifically include the location points of shoulder joints, elbow joints, ankle joints, knee joints, hip joints, wrist joints, and the like.
The process of obtaining similar abnormal behavior characteristic images by matching according to the behavior characteristic images of each target person at each instantaneous record point comprises constructing joint connecting lines of each target person according to key joint position points of each target person, further performing overlapping comparison with reference joint connecting lines corresponding to various abnormal behavior categories stored in a mine car database, and extracting the lengths of the overlapping joint connecting linesSimultaneously extracting the length of the joint line of the reference joint corresponding to various abnormal behavior categoriesCalculating the matching degree of the target person and each behavior classThe calculation formula is as follows: Extracting a behavior characteristic image of a target person of an abnormal behavior class with the highest matching degree, and marking the behavior characteristic image as a similar abnormal behavior characteristic image;
It should be understood that the abnormal behavior feature overlap ratio of each target person is quantitative evaluation data obtained by comprehensively analyzing key joint position points of each target person, and is used for quantitatively evaluating the similarity between the behavior features of each target person and similar abnormal behavior features, so as to provide a basis for evaluating the risk of the behavior of the person.
In a specific embodiment, the numerical expression of the abnormal behavior feature coincidence degree of each target person is:
;
In the formula, Indicating the abnormal behavior feature overlap ratio of the nth target person, n indicating the number of each target person,M represents the total number of target persons, i represents the number of each key joint,S represents the total number of key joints, r represents the number of each instantaneous recording point,H represents the total number of instantaneous recording points,The abscissa representing the ith key joint location point of the nth target person at the nth instant record point,Representing the ordinate of the ith key joint position point of the nth target person at the nth instant record point,Represents the abscissa of the reference standard ith key joint location point,The ordinate of the reference standard i-th key joint position point is shown.
It should be explained that, as the difference between the abscissa and the ordinate of the key joint position point of the target person and the abscissa and the ordinate of the key joint position point of the reference standard is smaller, the feature overlap ratio of the abnormal behavior of the target person is larger, which means that the abnormal behavior of the target person is closer to the similar abnormal behavior, and the risk of the abnormal behavior of the target person is larger.
It should be noted that in this embodiment, by extracting and marking key joint position points of each target person and performing accurate representation in a two-dimensional coordinate system, fine behavior changes can be captured. The high-precision method enables the system to more accurately identify abnormal behavior characteristics related to the groveling and pedaling of the mine car, such as body inclination, abnormal leg positions and the like. The behavior characteristic images of the instantaneous recording points are analyzed, and the process can monitor the behaviors of target personnel in real time. This helps in timely finding and stopping dangerous actions such as kicking down the mine car, and reduces potential safety risks. By matching the behavioral characteristic images of the target person with the reference abnormal behavioral characteristic images in the mine car database, the system can automatically identify similar or identical abnormal behavioral patterns. The intelligent matching and comparison technology improves the accuracy and efficiency of identification and reduces subjectivity and uncertainty of human judgment. The coincidence degree of the abnormal behavior characteristics of each target person is comprehensively analyzed, and whether the risk of prone to pedal the mine car exists can be further confirmed. The higher the overlap ratio is, the more similar the behavior of the target person is to the behavior characteristics of the known groveling mine car, so that the reliability and the accuracy of identification are improved. The whole process is based on data analysis and machine learning technology, can automatically extract useful information from a large amount of data, and provides powerful support for security management decision. Based on the analysis results provided by the system, the system can quickly respond and take corresponding safety measures.
It should be explained that, the image feedback is inaccurate due to the influence of environmental factors when the real-time video image data of the target person in the preset time period is collected, the environmental data and the image quality feedback data of the image quality influenced by each instantaneous recording point are collected, and the image quality evaluation value of the target area is obtained through comprehensive analysis.
The process of comprehensively analyzing and obtaining the image quality evaluation value of the target area comprises the steps of deploying a plurality of environment monitoring points, extracting environment data of a current time point from environment data of the image quality affected by each instantaneous recording point, including illumination intensity and dust concentration, extracting reference standard illumination intensity, allowable deviation illumination intensity, critical dust concentration, reference standard pixel value and allowable deviation pixel value from a mine car database, extracting pixel values of each pixel point of the image of the current time point from image quality feedback data of each instantaneous recording point, and comprehensively analyzing and obtaining the image quality evaluation value of the target area.
It should be understood that the target area image quality evaluation value is quantized evaluation data obtained by comprehensively analyzing the illumination intensity, dust concentration, and image pixel value at the present point in time and the previous instantaneous recording point image pixel value, for quantitatively evaluating image quality.
In a specific embodiment, the numerical expression of the target area image quality evaluation value is:
;
In the formula, An image quality evaluation value of the target area is represented, e represents a natural constant, j represents the number of each environmental monitoring point,F represents the total number of environmental monitoring points,Representing the illumination intensity of the jth environmental monitoring point,Indicating the dust concentration of the jth environmental monitoring point,The reference standard illumination intensity is shown with reference to,Indicating that the illumination intensity is allowed to deviate,Represents critical dust concentration, k represents the number of each pixel point,Q represents the total number of pixel points,A pixel value representing the kth pixel of the current point-in-time image,Representing the reference standard pixel values with which,Representing the allowable deviation pixel value of the pixel,Representing the image quality assessment impact factor corresponding to the preset illumination intensity,Representing an image quality evaluation influence factor corresponding to a preset dust concentration,And representing the image quality evaluation influence factors corresponding to the preset image pixel values.
It should be understood that, as is available from the above embodiment, the smaller the difference between the illumination intensity at the present time point and the reference standard illumination intensity, the smaller the dust concentration, and the smaller the difference between the image pixel value at the present time point and the reference standard image pixel value, the larger the image quality evaluation value, indicating that the image quality is better.
It should be explained that, in this embodiment, the range of values of the image quality evaluation influence factor corresponding to the illumination intensity, the image quality evaluation influence factor corresponding to the dust concentration, and the image quality evaluation influence factor corresponding to the image pixel value is between 0 and 1, and the mapping set of the illumination intensity, the dust concentration, the image pixel value, and the image quality evaluation influence factor corresponding to the image pixel value is established by the relationship between the illumination intensity, the dust concentration, and the image pixel value in the history data and the image quality evaluation value of the target area, and the image quality evaluation influence factor corresponding to the illumination intensity, the image quality evaluation influence factor corresponding to the dust concentration, and the image quality evaluation influence factor corresponding to the image pixel value are obtained from the mapping set in real time. The above influencing factors are extracted from mine car databases.
It should be explained that the pixel value refers to the brightness of each pixel point in the image. The whole brightness distribution, contrast ratio and whether overexposure or underexposure problems exist or not can be known through analysis. Proper illumination intensity helps to ensure proper exposure of the image, avoiding over-bright or over-dark conditions. Different light sources can affect the color appearance of an image, e.g., colors under natural light are generally more natural than under fluorescent light. Good illumination can reduce unnecessary shadows and make the image clearer. Dust particles in the air scatter light and reduce the definition of the image. When the dust concentration is high, the contrast of the image may be lowered. Dust can also cause image color shifts, especially when exposed for long periods of time or when light of a particular wavelength is used. By analyzing the intensity of the ambient illumination, the exposure time and gain of the image can be adjusted to achieve better brightness and color balance. The change in dust concentration affects the sharpness of the image, and measures can be taken to reduce or eliminate the effect of dust on the image quality by analyzing the dust concentration. Statistical analysis of pixel values can help identify and reduce noise in the image.
The image is further evaluated according to the target area image quality evaluation value, and the specific process comprises the steps of extracting a target area image quality evaluation threshold value from a mine car database, comparing the target area image quality evaluation value with the target area image quality evaluation threshold value, if the target area image quality evaluation value is higher than or equal to the target area image quality evaluation threshold value, the target area image quality is qualified, and if the target area image quality evaluation value is lower than the target area image quality evaluation threshold value, the target area image quality is unqualified.
It should be understood that, in the above embodiment, the real-time video image data of the target person is obtained by real-time image analysis of the target area acquired by using the high-definition camera deployed in the mining area, and if the acquired image quality of the target area is not qualified, a thermal imaging device is required to acquire a thermal imaging image of the target person.
And acquiring the action track data of the target personnel, and processing to obtain the relative position risk assessment index of each target personnel.
Specifically, the action track data of the target personnel comprises the distance between each target personnel and the mine car in a preset time period and the action speed of each target personnel.
The method comprises the specific processes of marking the distance between each target person and the mine car as the relative distance between each target person, extracting the relative distance between each target person at the previous adjacent instantaneous recording point and the current time point from the action track data of each target person in the preset time period, and differencing the relative distance between each target person at the previous adjacent instantaneous recording point and the current time point, wherein if the difference is larger than 0, the target person is gradually approaching the mine car, and if the difference is smaller than 0, the target person is gradually far away from the mine car.
And extracting the critical action speed and the critical relative distance from the mine car database according to the action speed and the relative distance of each target person in a preset time period, and comprehensively analyzing to obtain the risk assessment index of the relative position of each target person.
It should be understood that the risk assessment index of the relative position of each target person is quantitative assessment data obtained by comprehensively analyzing the action speed and the relative distance of each target person in a preset time period, and is used for quantitatively assessing the potential risk degree of the relative position of each target person, so as to provide a basis for assessing the risk of the behavior of the person.
In one specific embodiment, the numerical expression of each target person's relative position risk assessment index is:
;
In the formula, Representing an n-th target person relative position risk assessment index,Indicating the speed of action of the nth target person,Indicating the relative distance of the nth target person,The critical speed of action is indicated by the speed of the action,Indicating the critical relative distance to each other,Representing the relative distance of the nth target person from the previous adjacent instantaneous entry point,Representing the relative distance of the nth target person at the current point in time,The risk assessment influence factor of the relative position corresponding to the action speed at the preset approaching time is represented,Representing a relative position risk assessment influence factor corresponding to the preset relative distance when approaching,Indicating a relative position risk assessment influence factor corresponding to the preset action speed at the time of keeping away,And representing a relative position risk assessment influence factor corresponding to the preset relative distance away.
It should be noted that in this embodiment, the relative position risk assessment influence factor corresponding to the approaching movement speed is set to 0.5, the relative position risk assessment influence factor corresponding to the approaching relative distance is set to 1, the relative position risk assessment influence factor corresponding to the moving speed away from the moving speed is set to 0.8, the relative position risk assessment influence factor corresponding to the moving distance away from the moving speed is set to 0.5, the critical movement speed is set to 1 m/s, and the critical relative distance is set to 10 m.
It should be explained that, in the above embodiment: this can be achieved by adjusting the value of the influencing factor.
It should be explained that, in this embodiment, the range of values of the relative position risk assessment influence factors corresponding to the approaching action speed and the relative position risk assessment influence factors corresponding to the approaching relative distance is between 0 and 1, and the map set of the approaching action speed and the approaching relative distance and the relative position risk assessment influence factors corresponding to the approaching action speed and the approaching relative distance is established by the relation between the approaching action speed and the relative position risk assessment index in the history data, and the relative position risk assessment influence factors corresponding to the approaching action speed and the relative position risk assessment influence factors corresponding to the approaching relative distance are obtained from the map set in real time. The above influencing factors are extracted from mine car databases.
It should be explained that, in this embodiment, the range of values of the relative position risk assessment influence factor corresponding to the moving speed at the moving away time and the relative position risk assessment influence factor corresponding to the moving away time is between 0 and 1, and the mapping set of the moving speed at the moving away time and the relative distance at the moving away time and the relative position risk assessment influence factor corresponding to the moving away time is established by the relation between the moving speed at the moving away time and the relative distance at the moving away time and the relative position risk assessment index in the history data, and the relative position risk assessment influence factor corresponding to the moving speed at the moving away time and the relative position risk assessment influence factor corresponding to the relative distance at the moving away time are obtained from the mapping set. The above influencing factors are extracted from mine car databases.
It should be appreciated that, according to the above embodiment, as the target person gradually approaches the mine car, the relative position is smaller, indicating that the closer to the mine car, the faster the movement speed is, the greater the relative position risk assessment index is, indicating that the potential risk level of the target person is located, and as the target person gradually approaches the mine car, the faster the movement speed is, the greater the relative position is, indicating that the potential risk level of the target person is located, the smaller the relative position risk assessment index is.
It should be explained that the positions of the target person and the mine car can be obtained by the receiver of the global positioning system, the action speed of the target person can be obtained by calculating the ratio of the moving distance of the target person to the time period in a preset time period, and the moving distance of the target person can be obtained by calculating the difference between the positions of the starting time point and the ending time point.
In a specific embodiment, dynamic tracking of personnel behaviors can be achieved by continuously monitoring the movement track data of each target personnel in a preset time period and calculating the distance change of each target personnel relative to the mine car in real time. The real-time performance is helpful for timely finding and early warning possible risk behaviors, such as behaviors that personnel gradually approach the mine car, especially behaviors that the personnel intends to prone to pedal the mine car. By comparing the relative distance differences between the previous adjacent instantaneous record point and the current time point, it can be precisely determined whether the target person is approaching or moving away from the mine car. By combining the preset critical action speed and the critical relative distance, the risk state of each target person relative to the mine car can be more accurately estimated, so that the dangerous behaviors of which persons are likely to be carrying out or are ready to carry out the groveling and pedaling of the mine car can be identified. Once the trend that the target person approaches the mine car and possibly performs the groveling action is identified, the system can immediately send out an early warning signal to remind the supervision manager to pay attention to and take necessary measures, such as adding monitoring, carrying out safety education or implementing physical isolation, so as to effectively prevent dangerous actions such as groveling the mine car.
According to the characteristic coincidence degree of the abnormal behaviors of each target person and the risk assessment index of the relative positions, comprehensively analyzing to obtain the risk assessment index of the abnormal behaviors of each target person, carrying out risk assessment on the behaviors of the person on the prone mining car according to the risk assessment index of the abnormal behaviors of each target person, and feeding back the assessment result.
The method comprises the steps of comprehensively analyzing and obtaining the risk assessment index of the abnormal behaviors of each target person, wherein the specific analysis process is to comprehensively analyze and obtain the risk assessment index of the abnormal behaviors of each target person according to the feature coincidence degree and the relative position risk assessment index of the abnormal behaviors of each target person, and the risk assessment index of the abnormal behaviors of each target person is used for quantitatively assessing the risk degree of the abnormal behaviors of each target person.
In a specific embodiment, the numerical expression of the abnormal behavior risk assessment index of each target person is:
;
In the formula, Represents the risk assessment index of abnormal behaviors of the nth target person,Indicating the abnormal behavior feature coincidence degree of the nth target person,Representing an n-th target person relative position risk assessment index,Representing an abnormal behavior risk assessment influence factor corresponding to the preset abnormal behavior feature coincidence degree,And representing an abnormal behavior risk assessment influence factor corresponding to the preset relative position risk assessment index.
It should be explained that, in the above embodiment, the risk assessment influence factor of the abnormal behavior corresponding to the feature overlap ratio and the risk assessment influence factor of the abnormal behavior corresponding to the relative position risk assessment index are both set to 1, and when the feature overlap ratio of the abnormal behavior of the target person is larger, the risk assessment index of the abnormal behavior of the target person is also larger, which indicates that the risk degree of the abnormal behavior of the target person is larger.
It should be understood that, as shown in fig. 2, a curve a represents a relationship between the target person abnormal behavior feature overlap ratio and the abnormal behavior risk assessment index when the target person relative position risk assessment index is 0.64, a curve b represents a relationship between the target person abnormal behavior feature overlap ratio and the abnormal behavior risk assessment index when the target person relative position risk assessment index is 0.89, and a curve c represents a relationship between the target person abnormal behavior feature overlap ratio and the abnormal behavior risk assessment index when the target person relative position risk assessment index is 1.03.
It should be explained that, in this embodiment, the value range of the abnormal behavior risk assessment influence factor corresponding to the feature overlap ratio and the abnormal behavior risk assessment influence factor corresponding to the relative position risk assessment index is between 0 and 1, and a mapping set of the feature overlap ratio, the relative position risk assessment index and the abnormal behavior risk assessment influence factor corresponding to the feature overlap ratio and the relative position risk assessment index is established through the relationship between the feature overlap ratio, the relative position risk assessment index and the abnormal behavior risk assessment index in the historical data, and the abnormal behavior risk assessment influence factor corresponding to the feature overlap ratio and the abnormal behavior risk assessment influence factor corresponding to the relative position risk assessment index are obtained from the mapping set by inputting the real-time feature overlap ratio and the relative position risk assessment index. The above influencing factors are extracted from mine car databases.
It should be appreciated that, in the above embodiment, by combining the abnormal behavior feature coincidence degree and the relative position risk assessment index, the abnormal behavior feature of the target person can be more comprehensively captured by comprehensively analyzing the two dimensions of the behavior and the position. By comparing the behavior characteristics of the target personnel with the preset abnormal behavior characteristic images, the characteristics similar to the behaviors of the groveling and pedaling mine car can be accurately identified, and misjudgment and missed judgment are reduced. The system can process the behavior data and the position data of the target personnel in real time and calculate the risk assessment index of the abnormal behavior in time. When the risk assessment index of the abnormal behavior of the target personnel exceeds a preset threshold, the system can immediately send out an early warning signal to remind the management personnel to take corresponding measures. In the embodiment, not only the behavior characteristics of the target personnel are considered, but also the position information of the target personnel relative to the mine car is combined, so that the risk assessment is more comprehensive and accurate. And based on the risk assessment results obtained by the big data analysis and the intelligent algorithm, powerful support is provided for the decision of the manager. Management personnel can adjust the management strategy according to the risk assessment result, strengthen supervision and education of high risk personnel, and reduce the occurrence probability of dangerous behaviors such as prone to pedal a mine car.
In a specific embodiment, the data of the mine car database includes the data extracted from the mine car database in the above embodiments, such as the minimum safe distance between the personnel and the mine car, the images of the abnormal behavior characteristics of each reference, the relative position risk assessment influence factors corresponding to the action speed and the relative position risk assessment influence factors corresponding to the relative distance, etc., and the data of the mine car database may be collected through various sensors installed on the mine car, such as a global positioning system locator, an accelerometer, a temperature sensor, etc., and may be obtained through analysis after managing and monitoring the running state of the mine car by using specially designed software and hardware systems.
Further, according to the risk assessment indexes of the abnormal behaviors of each target person, the risk assessment is carried out on the groveling mine car behaviors of the person, wherein the specific assessment process is that according to the risk assessment indexes of the abnormal behaviors of each target person, the risk assessment index threshold of the abnormal behaviors of each target person is extracted from a mine car database, the risk assessment indexes of the abnormal behaviors of each target person are compared with the risk assessment index threshold of the abnormal behaviors of the target person, if the risk assessment index of the abnormal behaviors of a certain target person is higher than the risk assessment index threshold of the abnormal behaviors of the target person, the risk assessment index of the abnormal behaviors of the target person is indicated to be high risk person, if the risk assessment index of the abnormal behaviors of the certain target person is equal to the risk assessment index threshold of the abnormal behaviors of the target person, the risk assessment index of the abnormal behaviors of the target person is indicated to be medium risk person, if the risk assessment index of the abnormal behaviors of the certain target person is lower than the risk assessment index threshold of the abnormal behaviors of the target person is indicated to be low risk person, and assessment results are fed back.
In a specific embodiment, the specific feedback process of the evaluation result is that the risk level of each target person is recorded and associated with the personal information of the target person, so as to facilitate subsequent tracking and processing. Once a person is marked as a high risk or risk person, the targeted person itself and other relevant persons should be immediately notified by means of a short message, email, or live broadcast, etc. For high risk personnel, in addition to immediate notification, personalized safety training programs or interventions should be provided to help the targeted personnel alter unsafe behavioral habits. The assessment results are used to generate detailed assessment reports including, but not limited to, lists of people marked as high risk, medium risk and low risk, statistics of the number of people at each risk level, specific behavioral descriptions of high risk and medium risk people and their possible resulting risks, recommended safety measures and improvement advice.
It should be understood that, in the above embodiment, by setting different risk assessment index thresholds, the target personnel are classified into high risk, medium risk and low risk levels, so that the management personnel can conveniently take corresponding management measures according to the risk levels, and the pertinence and the efficiency of management are improved. Reasonable resource allocation can be realized according to the risk level, so that more attention and resource investment are ensured to the high-risk area and the high-risk personnel. The method is beneficial to reducing the risk of abnormal behaviors of the target personnel and improving the safety and efficiency of mining operation.
The foregoing is merely illustrative of the structures of this invention and various modifications, additions and substitutions for those skilled in the art can be made to the described embodiments without departing from the scope of the invention or from the scope of the invention as defined in the accompanying claims.

Claims (6)

1.一种人员趴蹬矿车行为识别方法,其特征在于,包括:1. A method for identifying the behavior of a person leaning on a mine car, characterized by comprising: 对矿车运行区域进行划定得到目标区域,将处于目标区域的人员标记为目标人员;The mine car operation area is delineated to obtain the target area, and the personnel in the target area are marked as target personnel; 对目标人员的行为动作数据进行采集,经处理得到各目标人员异常行为特征重合度;The behavioral action data of the target personnel are collected and processed to obtain the overlap of abnormal behavioral characteristics of each target personnel; 所述对目标人员的行为动作数据进行采集,具体过程为:The specific process of collecting the behavior data of the target person is as follows: 采集预设时间周期内目标人员的实时视频图像数据,包括目标人员在预设时间周期内的行动轨迹数据和行为动作数据,所述目标人员的行为动作数据,包括各瞬时记录点的目标人员的行为特征图像;Collecting real-time video image data of a target person within a preset time period, including the target person's movement trajectory data and behavior action data within the preset time period, wherein the target person's behavior action data includes the target person's behavior feature image at each instantaneous recording point; 所述经处理得到各目标人员异常行为特征重合度,具体处理过程为:The above processing results in the coincidence degree of abnormal behavior characteristics of each target person. The specific processing process is as follows: 根据各瞬时记录点的各目标人员的行为特征图像,在图像上部署若干关键关节位置点,构建二维坐标系标记各关键关节位置点,记为,其中,n表示各目标人员的编号,,m表示目标人员的总数,i表示各关键关节的编号,,s表示关键关节的总数,r表示各瞬时记录点的编号,,h表示瞬时记录点的总数,表示第n个目标人员在第r个瞬时记录点的第i个关键关节位置点的横坐标,表示第n个目标人员在第r个瞬时记录点的第i个关键关节位置点的纵坐标,表示第n个目标人员在第r个瞬时记录点的第i个关键关节位置点,从矿车数据库中提取得到各参照异常行为特征图像,根据各瞬时记录点的各目标人员的行为特征图像,匹配得到相似异常行为特征图像,并采集相似异常行为特征图像的各关键关节位置点,记为,其中,表示参照标准第i个关键关节位置点的横坐标,表示参照标准第i个关键关节位置点的纵坐标,表示第i个关键关节位置点,综合分析得到各目标人员异常行为特征重合度;According to the behavioral feature images of each target person at each instantaneous recording point, several key joint position points are deployed on the image, and a two-dimensional coordinate system is constructed to mark each key joint position point, which is recorded as , where n represents the number of each target person, , m represents the total number of target personnel, i represents the number of each key joint, , s represents the total number of key joints, r represents the number of each instantaneous recording point, , h represents the total number of instantaneous recording points, Represents the horizontal coordinate of the i-th key joint position point of the n-th target person at the r-th instantaneous recording point, It represents the ordinate of the i-th key joint position point of the n-th target person at the r-th instantaneous recording point, Represents the i-th key joint position point of the n-th target person at the r-th instantaneous recording point. The reference abnormal behavior feature images are extracted from the mine car database. According to the behavior feature images of each target person at each instantaneous recording point, similar abnormal behavior feature images are matched and the key joint position points of similar abnormal behavior feature images are collected, which are recorded as ,in, Represents the horizontal coordinate of the i-th key joint position point of the reference standard, Represents the ordinate of the i-th key joint position point of the reference standard, represents the i-th key joint position point, and the overlap degree of abnormal behavior characteristics of each target person is obtained by comprehensive analysis; 对目标人员的行动轨迹数据进行采集,经处理得到各目标人员相对位置风险评估指数;The target personnel's action trajectory data is collected and processed to obtain the relative position risk assessment index of each target personnel; 根据各目标人员异常行为特征重合度和相对位置风险评估指数,综合分析得到各目标人员异常行为风险评估指数,根据各目标人员异常行为风险评估指数对人员异常行为进行风险评估,并反馈评估结果;According to the overlap of abnormal behavior characteristics of each target person and the relative position risk assessment index, a comprehensive analysis is performed to obtain the abnormal behavior risk assessment index of each target person, and the risk assessment of the abnormal behavior of the personnel is conducted according to the abnormal behavior risk assessment index of each target person, and the assessment results are fed back; 所述各目标人员异常行为风险评估指数是用于量化评估各目标人员的异常行为的风险程度;The abnormal behavior risk assessment index of each target person is used to quantitatively assess the risk level of abnormal behavior of each target person; 所述各目标人员异常行为风险评估指数,具体数值表达式为:The specific numerical expression of the abnormal behavior risk assessment index of each target person is: ; 式中,表示第n个目标人员异常行为风险评估指数,表示第n个目标人员异常行为特征重合度,表示第n个目标人员相对位置风险评估指数,表示预设的异常行为特征重合度对应的异常行为风险评估影响因子,表示预设的相对位置风险评估指数对应的异常行为风险评估影响因子。In the formula, represents the abnormal behavior risk assessment index of the nth target person, Indicates the overlap degree of abnormal behavior characteristics of the nth target person, Represents the relative position risk assessment index of the nth target person, Indicates the abnormal behavior risk assessment impact factor corresponding to the preset abnormal behavior feature overlap, Indicates the abnormal behavior risk assessment impact factor corresponding to the preset relative position risk assessment index. 2.根据权利要求1所述一种人员趴蹬矿车行为识别方法,其特征在于:所述对矿车运行区域进行划定得到目标区域,具体过程为:2. According to the method for identifying the behavior of people kicking a mine car according to claim 1, it is characterized in that: the target area is obtained by demarcating the mine car operation area, and the specific process is as follows: 从矿车数据库中提取得到人员与矿车之间的最小安全距离,以矿车位置点为中心,人员与矿车之间的最小安全距离为半径进行区域划定,将划定得到的区域标记为目标区域,将处于目标区域内的人员标记为目标人员。The minimum safe distance between personnel and the mine car is extracted from the mine car database, and an area is delineated with the mine car location point as the center and the minimum safe distance between personnel and the mine car as the radius. The delineated area is marked as the target area, and the personnel in the target area are marked as target personnel. 3.根据权利要求1所述一种人员趴蹬矿车行为识别方法,其特征在于:所述目标人员的行动轨迹数据,包括预设时间周期内各目标人员与矿车的距离和各目标人员的行动速度。3. According to claim 1, a method for identifying the behavior of people kicking on a mine car is characterized in that the movement trajectory data of the target personnel include the distance between each target person and the mine car and the movement speed of each target person within a preset time period. 4.根据权利要求1所述一种人员趴蹬矿车行为识别方法,其特征在于:所述经处理得到各目标人员相对位置风险评估指数,具体过程为:4. According to the method for identifying the behavior of people leaning on a mine car as described in claim 1, it is characterized in that: the relative position risk assessment index of each target person is obtained by processing, and the specific process is: 将各目标人员与矿车的距离标记为各目标人员的相对距离,从预设时间周期内各目标人员的行动轨迹数据中提取得到前一个邻近瞬时记录点和当前时间点各目标人员的相对距离,并将前一个邻近瞬时记录点和当前时间点各目标人员的相对距离进行作差,若差值大于0,表明该目标人员逐渐在接近矿车,若差值小于0,则表明该目标人员逐渐在远离矿车;The distance between each target person and the mine car is marked as the relative distance of each target person, and the relative distance between the previous adjacent instantaneous recording point and the current time point is extracted from the action trajectory data of each target person within the preset time period, and the relative distance between the previous adjacent instantaneous recording point and the current time point is subtracted. If the difference is greater than 0, it indicates that the target person is gradually approaching the mine car, and if the difference is less than 0, it indicates that the target person is gradually moving away from the mine car; 根据预设时间周期内各目标人员的行动速度和相对距离,从矿车数据库中提取得到临界行动速度和临界相对距离,综合分析得到各目标人员相对位置风险评估指数。According to the movement speed and relative distance of each target person within a preset time period, the critical movement speed and critical relative distance are extracted from the mine car database, and the relative position risk assessment index of each target person is obtained through comprehensive analysis. 5.根据权利要求1所述一种人员趴蹬矿车行为识别方法,其特征在于:所述根据各目标人员异常行为风险评估指数对人员异常行为进行风险评估,具体评估过程为:5. According to the method for identifying the behavior of people kicking on a mine car as described in claim 1, it is characterized in that: the risk assessment of the abnormal behavior of the personnel is performed according to the abnormal behavior risk assessment index of each target personnel, and the specific assessment process is: 根据各目标人员异常行为风险评估指数,从矿车数据库中提取得到目标人员异常行为风险评估指数阈值,将各目标人员异常行为风险评估指数与目标人员异常行为风险评估指数阈值进行比对,若某目标人员异常行为风险评估指数高于目标人员异常行为风险评估指数阈值,则表明该目标人员异常行为的风险较大,将其标记为高风险人员,若某目标人员异常行为风险评估指数等于目标人员异常行为风险评估指数阈值,则表明该目标人员异常行为的风险为中等水平,将其标记为中风险人员,若某目标人员异常行为风险评估指数低于目标人员异常行为风险评估指数阈值,则表明该目标人员异常行为的风险较小,将其标记为低风险人员,并将评估结果进行反馈。According to the abnormal behavior risk assessment index of each target person, the threshold of the abnormal behavior risk assessment index of the target person is extracted from the mine car database, and the abnormal behavior risk assessment index of each target person is compared with the threshold of the abnormal behavior risk assessment index of the target person. If the abnormal behavior risk assessment index of a target person is higher than the threshold of the abnormal behavior risk assessment index of the target person, it indicates that the risk of abnormal behavior of the target person is relatively high, and the target person is marked as a high-risk person. If the abnormal behavior risk assessment index of a target person is equal to the threshold of the abnormal behavior risk assessment index of the target person, it indicates that the risk of abnormal behavior of the target person is at a medium level, and the target person is marked as a medium-risk person. If the abnormal behavior risk assessment index of a target person is lower than the threshold of the abnormal behavior risk assessment index of the target person, it indicates that the risk of abnormal behavior of the target person is relatively low, and the target person is marked as a low-risk person, and the assessment result is fed back. 6.根据权利要求4所述一种人员趴蹬矿车行为识别方法,其特征在于:所述各目标人员相对位置风险评估指数,具体数值表达式为:6. According to the method for identifying the behavior of people leaning on a mine car as described in claim 4, it is characterized in that: the relative position risk assessment index of each target person is specifically expressed as: ; 式中,表示第n个目标人员相对位置风险评估指数,n表示各目标人员的编号,,m表示目标人员的总数,表示第n个目标人员的行动速度,表示第n个目标人员的相对距离,表示临界行动速度,表示临界相对距离,表示前一个邻近瞬时记录点第n个目标人员的相对距离,表示当前时间点第n个目标人员的相对距离,表示预设的接近时行动速度对应的相对位置风险评估影响因子,表示预设的接近时相对距离对应的相对位置风险评估影响因子,表示预设的远离时行动速度对应的相对位置风险评估影响因子,表示预设的远离时相对距离对应的相对位置风险评估影响因子。In the formula, It represents the relative position risk assessment index of the nth target person, and n represents the number of each target person. , m represents the total number of target personnel, Indicates the action speed of the nth target person, Indicates the relative distance of the nth target person, represents the critical action speed, represents the critical relative distance, Indicates the relative distance of the nth target person at the previous adjacent instantaneous recording point, Indicates the relative distance of the nth target person at the current time point, Indicates the relative position risk assessment impact factor corresponding to the preset approach action speed, Indicates the relative position risk assessment impact factor corresponding to the preset relative distance when approaching. Indicates the relative position risk assessment impact factor corresponding to the preset moving speed when moving away. Indicates the relative position risk assessment impact factor corresponding to the preset relative distance.
CN202411309116.3A 2024-09-19 2024-09-19 Personnel prone pedaling mine car behavior identification method Active CN118823882B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411309116.3A CN118823882B (en) 2024-09-19 2024-09-19 Personnel prone pedaling mine car behavior identification method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411309116.3A CN118823882B (en) 2024-09-19 2024-09-19 Personnel prone pedaling mine car behavior identification method

Publications (2)

Publication Number Publication Date
CN118823882A CN118823882A (en) 2024-10-22
CN118823882B true CN118823882B (en) 2024-12-20

Family

ID=93071228

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411309116.3A Active CN118823882B (en) 2024-09-19 2024-09-19 Personnel prone pedaling mine car behavior identification method

Country Status (1)

Country Link
CN (1) CN118823882B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119849913A (en) * 2024-11-12 2025-04-18 湖北金盛兰冶金科技有限公司 Converter smelting stokehold safety risk monitoring and early warning system based on AI discernment

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112580449A (en) * 2020-12-06 2021-03-30 江苏集萃未来城市应用技术研究所有限公司 Method for judging abnormal behaviors of personnel on intelligent construction site
CN116012939A (en) * 2022-12-22 2023-04-25 浙江大华技术股份有限公司 Method and device for determining illegal behaviors, storage medium and electronic device

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3953864A4 (en) * 2019-04-09 2023-05-17 Motorola Solutions, Inc. ANOMALY DETECTION METHOD, SYSTEM AND COMPUTER READABLE MEDIA
KR20230091736A (en) * 2021-12-16 2023-06-23 삼성전자주식회사 Apparatus and method for providing intelligent image analysis
CN118116068A (en) * 2023-12-28 2024-05-31 绍兴市北大信息技术科创中心 Climbing behavior detection method and system based on visual algorithm

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112580449A (en) * 2020-12-06 2021-03-30 江苏集萃未来城市应用技术研究所有限公司 Method for judging abnormal behaviors of personnel on intelligent construction site
CN116012939A (en) * 2022-12-22 2023-04-25 浙江大华技术股份有限公司 Method and device for determining illegal behaviors, storage medium and electronic device

Also Published As

Publication number Publication date
CN118823882A (en) 2024-10-22

Similar Documents

Publication Publication Date Title
CN111598040B (en) Construction worker identity recognition and safety helmet wearing detection method and system
CN118823882B (en) Personnel prone pedaling mine car behavior identification method
CN112347943A (en) An anchor-optimized helmet detection method based on YOLOV4
CN111488799B (en) Falling object identification method and system based on image identification
CN113052125B (en) Construction site violation image recognition and alarm method
CN116778192B (en) Fire safety early warning system based on air-ground equipment cooperation
CN119296239A (en) Anti-theft monitoring and early warning method based on video remote monitoring
CN119048981B (en) Monitoring and early warning method, device, equipment and storage medium
CN119005711A (en) Underground coal mine fire monitoring and analyzing method based on image recognition
CN112597903B (en) Electric power personnel safety state intelligent identification method and medium based on stride measurement
CN116206253B (en) Method and system for detecting and judging site fire behavior based on deep learning
CN119445751A (en) Fire risk judgment method and device based on visible light and infrared detection
CN117649736A (en) Video management method and system based on AI video management platform
CN113314230A (en) Intelligent epidemic prevention method, device, equipment and storage medium based on big data
CN110718071B (en) Verification method and device for image acquisition equipment, computer equipment and storage medium
CN119280783B (en) Middle-long distance running evaluation method and system based on human face and human body re-identification
CN114529869A (en) Training method of illegal fire detection model and detection method using model
CN118195582B (en) Operation and maintenance abnormal state prediction method applied to pollution source operation and maintenance platform
CN118570960A (en) Intelligent alarm triggering device and fireproof door
CN116013024B (en) A mine fire monitoring method based on visible light visual feature fusion
CN116757422A (en) Building engineering safety supervision early warning method and monitoring system
CN114023034A (en) Electric vehicle charging monitoring system based on visible light and infrared monitoring
CN118172798B (en) Embedded real-time humanoid target automatic monitoring and recognition method
CN119068469B (en) Firework detection and analysis method based on YOLO algorithm and dynamic analysis
CN119889008B (en) Remote video monitoring early warning method, system and device for emergency rescue scenes

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

Country or region after: China

Address after: Room 04, 05, 06, 07, 10th Floor, Building A1, Hunan Inspection and Testing Characteristic Industrial Park, No. 336 Bachelor Road, Bachelor Street, Yuelu District, Changsha City, Hunan Province, 410208

Applicant after: Hunan Guotian Liyan Technology Co.,Ltd.

Address before: Room 04, 05, 06, 07, 10th Floor, Building A1, Hunan Inspection and Testing Characteristic Industrial Park, No. 336 Bachelor Road, Bachelor Street, Yuelu District, Changsha City, Hunan Province, 410208

Applicant before: Hunan Liyan Optoelectronic Technology Co.,Ltd.

Country or region before: China

GR01 Patent grant
GR01 Patent grant