Method and system for analyzing smelting hidden danger warning based on video data

Abstract

The invention discloses a method and a system for analyzing a smelting hidden danger warning based on video data, relates to the technical field of early warning management and control of a smelting factory, and particularly discloses a method for performing monitoring block division on a video image shot by a camera, and determining a monitoring strategy according to a monitoring object; analyzing the video image of the monitoring block, identifying an equipment state or a human body behavior, and evaluating an abnormal condition by using a monitoring strategy; constructing a smelting site plan, marking monitoring blocks, performing association analysis based on equipment linkage influence characteristics, monitoring abnormal conditions in real time, marking abnormal blocks, analyzing linkage influence of the abnormal blocks, and determining a hidden danger warning degree; determining a corresponding hidden danger alarm level according to the interval to which the hidden danger warning degree belongs; according to the technical scheme, through refined monitoring, real-time analysis, chain influence analysis and alarm level determination, the potential safety hazard identification capability and the emergency response speed of the smelting site are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of early warning control of smelting plants, and in particular to a smelting hidden danger warning method and system based on video data analysis. Background Art

[0002] Safety management is a crucial part of the production process of the smelting industry. However, the traditional smelting site monitoring system has many limitations and cannot meet the safety management needs of modern smelting sites.

[0003] Traditional monitoring systems often adopt global or fixed-area monitoring methods, lacking refined monitoring of specific equipment or personnel operation areas. This results in inaccurate monitoring range and inability to effectively capture the activities of key equipment and personnel. Summary of the invention

[0004] The object of the present invention is to provide a method and system capable of finely monitoring the equipment and personnel of a smelter.

[0005] The present invention discloses a smelting hidden danger warning method based on video data analysis, comprising: Divide the video images captured by each camera into monitoring blocks, and determine the monitoring strategy of the monitoring block based on the objects that need to be monitored in the monitoring block; Analyze the video images corresponding to each monitoring block to determine the state description of the device or the behavior description of the human body corresponding to the monitoring block, and use the monitoring strategy corresponding to each monitoring block to analyze the state description or behavior description to determine the abnormal situation assessment of the corresponding device or human body; A smelting site plan is constructed, and each monitoring block is marked on the smelting site plan. Based on the chain effect characteristics between equipment, different monitoring blocks are linked to each other through chain effects. The abnormal situation assessment of each monitoring block is monitored in real time. The monitoring blocks identified as abnormal in the abnormal situation assessment are marked as abnormal, and the chain effect relationship analysis is performed on the abnormally marked retrieval blocks. Based on the analysis results, the hidden danger warning level of the smelting site is determined; The hidden danger alarm level is determined based on the hidden danger warning level interval to which the hidden danger warning level belongs.

[0006] In some embodiments disclosed in the present invention, a method for dividing monitoring blocks in a video image includes: Determine the key equipment area and the personnel operation area in the video image, and divide the video image into blocks based on the key equipment area and the personnel operation area.

[0007] In some embodiments disclosed in the present invention, based on the objects that need to be monitored by the monitoring block, a method for determining a monitoring strategy for the monitoring block includes: Constructing several abnormal state types for the abnormal state of the key equipment area, and constructing several abnormal state levels for each abnormal state type, and each abnormal state level corresponds to several abnormal state judgment factor parameter intervals; Several personnel sub-operation areas are defined for the personnel operation area, and several abnormal behavior types are constructed for the abnormal human behavior in each personnel sub-operation area, and several abnormal behavior levels are constructed for each abnormal behavior type, and each abnormal behavior level corresponds to several abnormal behavior judgment factor parameter intervals.

[0008] In some embodiments disclosed in the present invention, a method for analyzing a video image corresponding to each monitoring block and determining a state description of a device corresponding to the monitoring block includes: Delineate the feature edges or mark the feature signs of key structures of equipment in the monitoring area; Based on the normal operation status of the equipment in the monitoring block, the motion ranges of different characteristic edges or characteristic marks are determined, and several levels of sub-motion ranges are delineated for the motion ranges, and a first abnormal motion parameter is configured for each sub-motion range; Based on the normal operation status of the equipment in the monitoring block, the motion speed intervals of different characteristic edges or characteristic marks are determined, and several levels of sub-motion speed intervals are delineated for the motion speed intervals, and a second abnormal motion parameter is configured for each sub-motion speed interval; The first abnormal motion parameter and the second abnormal motion parameter are identified as a state description of the device of the monitoring block.

[0009] In some embodiments disclosed in the present invention, the method for determining the behavior description of a human body in a monitoring area includes: Use human body recognition technology to identify the human body in the monitoring area in real time, and build a real-time human body expression model for the identified human body; Determine different personnel working areas in the monitoring block, and determine several normal human body postures in each personnel working area, build a normal human body expression model based on the normal human body postures, and record the combination of several normal human body expression models as a normal human body expression model group; The real-time human limb expression model is compared and analyzed using the normal human limb expression model group. If no matching normal human limb expression model is found in the normal human limb expression model group, the real-time human limb expression model is marked as abnormal. The number of abnormal behaviors of the real-time human body expression model marked as abnormal within a preset time period is counted, and the behavior description of the human body in the monitoring block is determined based on the number of abnormal behaviors.

[0010] In some embodiments disclosed in the present invention, a method for analyzing a state description or a behavior description using a monitoring strategy corresponding to each monitoring block to determine an abnormal condition assessment of a corresponding device or human body includes: Performing real-time motion analysis on characteristic edges or characteristic marks in the monitoring block to determine a first abnormal motion parameter and a second abnormal motion parameter of the device, and determining a comprehensive abnormal motion parameter of the device corresponding to the monitoring block based on the first abnormal motion parameter and the second abnormal motion parameter; Among them, the expression for calculating the comprehensive abnormal motion parameters is: ; in, is the comprehensive abnormal motion parameter, is the influence weight of the first abnormal motion parameter, is the first abnormal motion parameter, is the influence weight of the second abnormal motion parameter, is the second abnormal motion parameter, is the duration of the continuous abnormal state of the device, is the adjustment coefficient of the impact of the duration of the continuous abnormal state, c is the adjustment constant of the impact of the duration of the continuous abnormal state; According to the number of abnormal behaviors of the real-time human body expression model, several abnormal behavior frequency intervals are constructed, and human abnormal parameters are set corresponding to each abnormal behavior frequency interval. By judging the abnormal behavior frequency interval to which the abnormal behavior frequency belongs, the human abnormal parameters of the real-time human body expression model are determined.

[0011] In some embodiments disclosed in the present invention, a method for performing a chain effect relationship analysis on a search block with an abnormal mark and determining the hidden danger warning level of a smelting site based on the analysis result includes: Determine the comprehensive abnormal motion parameters of the equipment corresponding to different monitoring blocks, or the abnormal human body parameters of the human body. If the comprehensive abnormal motion parameters or the abnormal human body parameters are greater than or equal to the preset values, mark the monitoring blocks as abnormal. Determine the total number of abnormal blocks in the abnormal mark monitoring block, determine the number of chain abnormal blocks in the abnormal mark monitoring block affected by the chain relationship, and calculate the chain abnormal ratio of the number of chain abnormal blocks to the total number of abnormal blocks; Based on the comprehensive abnormal motion parameters of different monitoring blocks, or the abnormal parameters of the human body, as well as the chain abnormality ratio, the hidden danger warning level of the smelting site is determined.

[0012] In some embodiments disclosed in the present invention, the expression for determining the hidden danger warning level of the smelting site is: ; in, For the hidden danger warning level, is the number of chained abnormal blocks, is the total number of abnormal blocks, is the impact adjustment coefficient of the linkage anomaly ratio, is the adjustment constant for the effect of the linkage anomaly ratio, is the comprehensive abnormal motion parameter of the i-th abnormal marking monitoring block, is the human body abnormal parameter of the ith abnormal mark monitoring block, and n is the total number of abnormal mark monitoring blocks.

[0013] In some embodiments disclosed in the present invention, there is also disclosed a smelting hidden danger warning system based on video data analysis, including: The first module is used to divide the video images captured by each camera into monitoring blocks, and determine the monitoring strategy of the monitoring block based on the objects to be monitored in the monitoring block; The second module is used to analyze the video images corresponding to each monitoring block, determine the state description of the device or the behavior description of the human body corresponding to the monitoring block, and use the monitoring strategy corresponding to each monitoring block to analyze the state description or behavior description to determine the abnormal situation assessment of the corresponding device or human body; The third module is used to construct a smelting site plan and mark each monitoring block on the smelting site plan. Based on the chain effect characteristics between equipment, different monitoring blocks are linked to each other, and the abnormal situation assessment of each monitoring block is monitored in real time. The monitoring blocks identified as abnormal in the abnormal situation assessment are marked as abnormal, and the chain effect relationship analysis is performed on the abnormal marked search blocks. Based on the analysis results, the hidden danger warning level of the smelting site is determined; The fourth module is used to determine the hidden danger alarm level based on the hidden danger warning level interval to which the hidden danger warning level belongs.

[0014] The present invention discloses a smelting hidden danger warning method and system based on video data analysis, which relates to the technical field of early warning control of smelting plants, and specifically discloses dividing the video images taken by a camera into monitoring blocks, and determining the monitoring strategy according to the monitored objects; analyzing the video images of the monitoring blocks, identifying the equipment status or human behavior, and using the monitoring strategy to evaluate abnormal situations; constructing a smelting site plan, marking the monitoring blocks, and performing correlation analysis based on the chain influence characteristics of the equipment, monitoring abnormal situations in real time, marking the abnormal blocks, and analyzing their chain influence to determine the degree of hidden danger warning; determining the corresponding hidden danger alarm level according to the interval to which the hidden danger warning degree belongs; the above-mentioned technical scheme of the present invention effectively improves the safety hidden danger identification capability and emergency response speed of the smelting site through refined monitoring, real-time analysis, chain influence analysis and alarm level determination.

[0015] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a method step diagram of a smelting hidden danger warning method based on video analysis disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0018] The following will be combined with the accompanying drawings and specific embodiments to clearly and completely describe the technical solution of the present invention. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and cannot be understood as limiting the scope of protection of the present invention. Those skilled in the art in this field can make some non-essential improvements and adjustments based on the content of the present invention described below. In the present invention, unless otherwise clearly specified and limited, the technical terms used in the present invention should be the common meanings understood by the technical personnel described in the present invention.

[0019] Example:

[0020] The present invention discloses a smelting hidden danger warning method based on video data analysis, see Figure 1 ,include: Step S100, dividing the video images captured by each camera into monitoring blocks, and determining the monitoring strategy of the monitoring blocks based on the objects to be monitored in the monitoring blocks.

[0021] In smelting sites, due to the large number of equipment and frequent personnel flow, a single camera often cannot cover all key areas. Therefore, it is necessary to first divide the shooting range of each camera into several monitoring blocks. These monitoring blocks can be determined based on factors such as equipment location, personnel activity area, or potential safety hazards. Then, formulate corresponding monitoring strategies based on the objects that need to be monitored in each monitoring block (such as equipment operation status, personnel behavior, etc.). Monitoring strategies may include monitoring frequency, analysis algorithms, abnormality judgment criteria, etc., to ensure that abnormal situations in the monitoring blocks can be captured accurately and efficiently.

[0022] In some embodiments disclosed in the present invention, a method for dividing monitoring blocks in a video image includes: Step S101 : determining key equipment areas and personnel operation areas in a video image, and dividing the video image into blocks based on the key equipment areas and personnel operation areas.

[0023] In complex environments such as smelting sites, video images contain a large amount of equipment and personnel information. In order to monitor more effectively, it is first necessary to determine the key equipment areas and personnel operation areas in the video images. Key equipment areas usually refer to those areas where equipment that is critical to the production process and may cause serious consequences if a failure occurs is located. Personnel operation areas refer to areas where personnel often work, operate or move.

[0024] Based on these key equipment areas and personnel operation areas, the video images can be divided into blocks. The principle of division can be based on the type, location, function of the equipment or the scope of personnel activities, work content, etc. Through block division, the video image can be divided into several relatively independent areas with clear monitoring targets, providing a basis for the subsequent monitoring strategy formulation.

[0025] In some embodiments disclosed in the present invention, based on the objects that need to be monitored by the monitoring block, a method for determining a monitoring strategy for the monitoring block includes: Step S102, constructing a plurality of abnormal state types for the abnormal state of the key equipment area, and constructing a plurality of abnormal state levels for each abnormal state type, and each abnormal state level corresponds to a plurality of abnormal state judgment factor parameter intervals.

[0026] In the present invention, special attention is paid to the abnormality of the movement range and movement speed of the equipment as the abnormal state type of the key equipment area. The abnormality of the movement range may refer to the equipment exceeding its normal working range or movement trajectory, while the abnormality of the movement speed may refer to the movement speed of the equipment being too fast or too slow, which does not meet its normal working speed.

[0027] Several abnormal status levels are further constructed for these two abnormal status types. Abnormal status levels can be divided according to the severity of the abnormality, the impact on production, or the possible consequences. For example, a slight range of motion may only be a small deviation of the equipment, while a serious range of motion may cause equipment damage or production accidents.

[0028] Each abnormal state level corresponds to a number of abnormal state judgment factor parameter intervals. For abnormal range of motion, the judgment factor parameter may be the deviation between the actual position of the device and its normal working range; for abnormal speed of motion, the judgment factor parameter may be the difference or ratio between the actual speed of motion of the device and its normal working speed.

[0029] In step S103, the personnel operation area is delineated into several personnel sub-operation areas, and several abnormal behavior types are constructed for the abnormal human behavior in each personnel sub-operation area, and several abnormal behavior levels are constructed for each abnormal behavior type, and each abnormal behavior level corresponds to several abnormal behavior judgment factor parameter intervals.

[0030] After determining the abnormal state type and abnormal state level, this information will be incorporated into the monitoring strategy. For key equipment areas, the monitoring system will monitor the movement range and movement speed of the equipment in real time and compare them with the preset abnormal state judgment factor parameter range.

[0031] Once the movement range or movement speed of the equipment exceeds the preset parameter range, the monitoring system will immediately trigger an abnormal alarm and take corresponding countermeasures according to the abnormal state level. For example, for a minor movement range exceeding, it may only issue a warning signal to remind the operator to pay attention; while for a serious movement range exceeding or abnormal movement speed, it may be necessary to stop the equipment immediately to prevent the situation from further deteriorating.

[0032] Step S200, analyze the video image corresponding to each monitoring block, determine the state description of the device or the behavior description of the human body corresponding to the monitoring block, use the monitoring strategy corresponding to each monitoring block to analyze the state description or behavior description, and determine the abnormal situation assessment of the corresponding device or human body.

[0033] After determining the monitoring blocks and monitoring strategies, the next step is to perform real-time analysis on the video images corresponding to each monitoring block. This step mainly relies on computer vision technology and image processing algorithms. By analyzing video images, you can extract the status description of the equipment in the monitoring block (such as whether the equipment is operating normally, whether there is abnormal vibration, etc.) or the behavior description of the human body (such as whether the personnel are operating illegally, whether they are in a dangerous area, etc.). Then, use the previously determined monitoring strategy to analyze these status descriptions or behavior descriptions to evaluate whether there are any abnormalities. If the evaluation results show that there are abnormalities, further processing is required.

[0034] In some embodiments disclosed in the present invention, a method for analyzing a video image corresponding to each monitoring block and determining a state description of a device corresponding to the monitoring block includes: Step S201, perform feature edge delineation or feature mark marking on key structures of equipment in the monitoring block.

[0035] Step S202, based on the normal operation status of the equipment in the monitoring block, determine the movement range of different characteristic edges or characteristic marks, and define several levels of sub-motion ranges for the movement range, and configure a first abnormal movement parameter for each sub-motion range.

[0036] When the device is in normal operation, the motion range of its characteristic edge or characteristic mark is relatively stable. Therefore, by observing and analyzing the motion trajectory of the device during normal operation, its motion range can be determined. In order to describe the motion state of the device more finely, we divide this motion range into several sub-motion ranges, each of which represents a specific area that the device may reach during normal operation. At the same time, a first abnormal motion parameter is configured for each sub-motion range to describe the abnormal motion of the device within the range. When the movement of the device exceeds a certain sub-motion range, the first abnormal motion parameter is triggered, indicating that the device may have an abnormal motion range, thereby promptly triggering an alarm in the monitoring system.

[0037] Step S203, based on the normal operation status of the equipment in the monitoring block, the movement speed intervals of different characteristic edges or characteristic marks are determined, and several levels of sub-movement speed intervals are delineated for the movement speed intervals, and a second abnormal movement parameter is configured for each sub-movement speed interval.

[0038] When the device is in normal operation, the movement speed of its characteristic edge or characteristic mark is relatively stable. By observing and analyzing the movement speed of the device during normal operation, its movement speed range can be determined. In order to more accurately describe the movement state of the device, we divide this movement speed range into several sub-movement speed ranges, each of which represents a specific speed range that the device may reach during normal operation. At the same time, a second abnormal movement parameter is configured for each sub-movement speed range to describe the abnormal movement of the device within the speed range. When the movement speed of the device exceeds a certain sub-movement speed range, the second abnormal movement parameter is triggered, indicating that the device may have an abnormal movement speed, thereby promptly triggering an alarm in the monitoring system.

[0039] Step S204: identifying the first abnormal motion parameter and the second abnormal motion parameter as a status description of the device in the monitoring block.

[0040] In the monitoring system, the status description of the equipment is an important basis for judging whether the equipment is operating normally. By combining the first abnormal motion parameter and the second abnormal motion parameter, we can get a comprehensive description of the equipment status. These two parameters reflect the abnormal conditions of the equipment in terms of motion range and motion speed respectively. When the equipment triggers any abnormal motion parameter, it means that the motion state of the equipment is abnormal. The monitoring system can send out an alarm signal to remind the operator to take timely measures to deal with it. Therefore, identifying the first abnormal motion parameter and the second abnormal motion parameter as the status description of the equipment in the monitoring block is a key step to achieve timely discovery and processing of abnormal equipment status.

[0041] In some embodiments disclosed in the present invention, the method for determining the behavior description of a human body in a monitoring area includes: Step S205, using human body recognition technology, real-time recognition of the human body in the monitoring area is performed, and a real-time human body expression model is constructed for the recognized human body.

[0042] In order to accurately describe and analyze human behavior in the monitoring system, it is first necessary to use human body recognition technology to identify the human body in the monitoring area in real time. Through image processing and machine learning algorithms, the system can automatically detect and track the human body in the video and extract the key feature points of the human body, such as joint position, limb direction, etc. Based on these feature points, the system builds a real-time human body expression model, which can reflect the posture and movement of the human body in real time, providing a basis for subsequent behavior analysis.

[0043] Step S206, determining the working areas of different personnel in the monitoring block, and determining several normal human body postures in each personnel working area, constructing a normal human body expression model based on the normal human body postures, and recording the combination of several normal human body expression models as a normal human body expression model group.

[0044] In the monitoring block, different personnel may have different working areas and responsibilities, so their normal human postures may also be different. In order to accurately describe the normal behavior of the human body, the system first needs to determine the working areas of different personnel in the monitoring block, and observe and record the normal human postures in each working area. Based on these normal postures, the system constructs a normal human body expression model, which can reflect the posture and movement of the human body under normal working conditions. At the same time, the system combines several normal human body expression models to form a normal human body expression model group for subsequent behavior comparison and analysis.

[0045] Step S207, using the normal human limb expression model group to compare and analyze the real-time human limb expression model, if no matching normal human limb expression model is found in the normal human limb expression model group, the real-time human limb expression model is marked as abnormal.

[0046] After obtaining the real-time human limb expression model and the human body normal limb expression model group, the system needs to compare and analyze them. By calculating the similarity between the real-time human limb expression model and each model in the human body normal limb expression model group, the system can determine whether the real-time human body posture is normal. If no model matching the real-time human limb expression model is found in the human body normal limb expression model group, that is, the similarity is lower than a certain threshold, then the system considers the real-time human body posture to be abnormal and marks it.

[0047] Step S208, counting the number of abnormal behaviors of the real-time human body expression model marked as abnormal within a preset time period, and determining the behavior description of the human body in the monitoring block based on the number of abnormal behaviors.

[0048] In order to fully describe the behavior of the human body in the monitoring block, the system needs to count the number of abnormal behaviors of the real-time human body expression model that are marked as abnormal within a preset time period. By recording and analyzing these abnormal behavior times, the system can understand the abnormal behavior of the human body in the monitoring block. Based on these abnormal behavior times, the system can determine the behavior description of the human body in the monitoring block, such as "frequent abnormal behavior", "occasionally abnormal behavior" or "normal behavior". Such behavior descriptions help the monitoring system to promptly detect and handle abnormal behavior of the human body and ensure the safety and order of the monitoring area.

[0049] In some embodiments disclosed in the present invention, a method for analyzing a state description or a behavior description using a monitoring strategy corresponding to each monitoring block to determine an abnormal condition assessment of a corresponding device or human body includes: Step S209, performing real-time motion analysis on the characteristic edges or characteristic marks in the monitoring block, determining the first abnormal motion parameter and the second abnormal motion parameter of the device, and based on the first abnormal motion parameter and the second abnormal motion parameter, determining the comprehensive abnormal motion parameter of the device corresponding to the monitoring block.

[0050] Among them, the expression for calculating the comprehensive abnormal motion parameters is: .

[0051] in, is the comprehensive abnormal motion parameter, is the influence weight of the first abnormal motion parameter, is the first abnormal motion parameter, is the influence weight of the second abnormal motion parameter, is the second abnormal motion parameter, is the duration of the continuous abnormal state of the device, is the adjustment coefficient of the impact of the duration of the continuous abnormal state, and c is the adjustment constant of the impact of the duration of the continuous abnormal state.

[0052] Step S2010, constructing a number of abnormal behavior frequency intervals for the real-time human body expression model, and setting a human body abnormality parameter corresponding to each abnormal behavior frequency interval, and determining the human body abnormality parameter of the real-time human body expression model by judging the abnormal behavior frequency interval to which the abnormal behavior frequency belongs.

[0053] Step S300, construct a smelting site plan, and mark each monitoring block on the smelting site plan, based on the chain effect characteristics between equipment, link different monitoring blocks with chain effects, conduct real-time monitoring of abnormal situation assessment of each monitoring block, mark the monitoring blocks that are identified as abnormal in the abnormal situation assessment as abnormal, and perform chain effect relationship analysis on the retrieval blocks marked as abnormal, and determine the hidden danger warning level of the smelting site based on the analysis results.

[0054] First, you need to build a floor plan of the smelting site and mark each monitoring block on the floor plan. Doing so helps to intuitively understand the distribution and location relationship of the monitoring blocks. Then, based on the chain effect characteristics between equipment (such as the failure of a certain equipment may cause the shutdown or damage of other equipment), different monitoring blocks are linked for chain effects. Next, the abnormal situation assessment of each monitoring block is monitored in real time. Once a monitoring block is assessed as abnormal, it is immediately marked as abnormal and the chain effect relationship analysis is triggered. By analyzing the chain effect relationship between the abnormal monitoring block and other monitoring blocks, the hidden danger warning level of the entire smelting site is evaluated. This step helps to discover potential safety hazards in advance and avoid accidents.

[0055] In some embodiments disclosed in the present invention, a method for performing a chain effect relationship analysis on a search block with an abnormal mark and determining the hidden danger warning level of a smelting site based on the analysis result includes: Step S301, determine the comprehensive abnormal motion parameters of the equipment corresponding to different monitoring blocks, or the abnormal human body parameters. If the comprehensive abnormal motion parameters or the abnormal human body parameters are greater than or equal to the preset value, the monitoring block is marked as abnormal.

[0056] Step S302, determining the total number of abnormal blocks in the abnormality mark monitoring block, determining the number of chain abnormal blocks in the abnormality mark monitoring block affected by the chain relationship, and calculating the chain abnormality ratio of the number of chain abnormal blocks to the total number of abnormal blocks.

[0057] Step S303, based on the comprehensive abnormal motion parameters of different monitoring blocks, or the abnormal parameters of the human body, and the chain abnormality ratio, determine the hidden danger warning level of the smelting site.

[0058] In some embodiments disclosed in the present invention, the expression for determining the hidden danger warning level of the smelting site is: ; in, For the hidden danger warning level, is the number of chained abnormal blocks, is the total number of abnormal blocks, is the impact adjustment coefficient of the linkage anomaly ratio, is the adjustment constant for the effect of the linkage anomaly ratio, is the comprehensive abnormal motion parameter of the i-th abnormal marking monitoring block, is the human body abnormal parameter of the ith abnormal mark monitoring block, and n is the total number of abnormal mark monitoring blocks.

[0059] Step S400: determining the hidden danger alarm level based on the hidden danger warning level interval to which the hidden danger warning level belongs.

[0060] According to the hidden danger warning level determined in step S300, it is compared with the preset hidden danger warning level interval. These intervals are usually determined based on historical data and expert experience, and each interval corresponds to a specific hidden danger alarm level. The level of hidden danger alarm directly reflects the current safety risk level of the smelting site. Once the hidden danger warning level falls into a certain interval, the corresponding alarm mechanism is immediately triggered so that relevant personnel can be notified in time to take measures to deal with it. By setting different alarm levels, hierarchical management of safety hazards in smelting sites can be achieved, and the efficiency and effectiveness of emergency response can be improved.

[0061] In some embodiments disclosed in the present invention, there is also disclosed a smelting hidden danger warning system based on video data analysis, including: The first module is used to divide the video images captured by each camera into monitoring blocks, and determine the monitoring strategy of the monitoring block based on the objects that need to be monitored in the monitoring block.

[0062] The second module is used to analyze the video images corresponding to each monitoring block, determine the status description of the equipment or the behavior description of the human body corresponding to the monitoring block, use the monitoring strategy corresponding to each monitoring block to analyze the status description or behavior description, and determine the abnormal situation assessment of the corresponding equipment or human body.

[0063] The third module is used to construct a plan of the smelting site and mark each monitoring block on the plan of the smelting site. Based on the chain effect characteristics between equipment, different monitoring blocks are linked by chain effects, and the abnormal situation assessment of each monitoring block is monitored in real time. The monitoring blocks that are assessed as abnormal are marked as abnormal, and the chain effect relationship analysis is performed on the retrieval blocks marked as abnormal. Based on the analysis results, the degree of hidden danger warning of the smelting site is determined.

[0064] The fourth module is used to determine the hidden danger alarm level based on the hidden danger warning level interval to which the hidden danger warning level belongs.

[0065] The present invention discloses a smelting hidden danger warning method and system based on video data analysis, which relates to the technical field of early warning control of smelting plants, and specifically discloses dividing the video images taken by a camera into monitoring blocks, and determining the monitoring strategy according to the monitored objects; analyzing the video images of the monitoring blocks, identifying the equipment status or human behavior, and using the monitoring strategy to evaluate abnormal situations; constructing a smelting site plan, marking the monitoring blocks, and performing correlation analysis based on the chain influence characteristics of the equipment, monitoring abnormal situations in real time, marking the abnormal blocks, and analyzing their chain influence to determine the degree of hidden danger warning; determining the corresponding hidden danger alarm level according to the interval to which the hidden danger warning degree belongs; the above-mentioned technical scheme of the present invention effectively improves the safety hidden danger identification capability and emergency response speed of the smelting site through refined monitoring, real-time analysis, chain influence analysis and alarm level determination.

[0066] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.

[0067] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A smelting hidden danger warning method based on video data analysis, characterized in that: include: Divide the video images captured by each camera into monitoring blocks, and determine the monitoring strategy of the monitoring block based on the objects that need to be monitored in the monitoring block; Analyze the video images corresponding to each monitoring block to determine the state description of the device or the behavior description of the human body corresponding to the monitoring block, and use the monitoring strategy corresponding to each monitoring block to analyze the state description or behavior description to determine the abnormal situation assessment of the corresponding device or human body; A smelting site plan is constructed, and each monitoring block is marked on the smelting site plan. Based on the chain effect characteristics between equipment, different monitoring blocks are linked to each other through chain effects. The abnormal situation assessment of each monitoring block is monitored in real time. The monitoring blocks identified as abnormal in the abnormal situation assessment are marked as abnormal, and the chain effect relationship analysis is performed on the abnormally marked retrieval blocks. Based on the analysis results, the hidden danger warning level of the smelting site is determined; The hidden danger alarm level is determined based on the hidden danger warning level interval to which the hidden danger warning level belongs.

2. The smelting hidden danger warning method based on video data analysis according to claim 1 is characterized in that: The method for dividing the monitoring blocks in the video image includes: Determine the key equipment area and the personnel operation area in the video image, and divide the video image into blocks based on the key equipment area and the personnel operation area.

3. The smelting hidden danger warning method based on video data analysis according to claim 1 is characterized in that: Based on the object to be monitored by the monitoring block, the method for determining the monitoring strategy of the monitoring block includes: Constructing several abnormal state types for the abnormal state of the key equipment area, and constructing several abnormal state levels for each abnormal state type, and each abnormal state level corresponds to several abnormal state judgment factor parameter intervals; Several personnel sub-operation areas are defined for the personnel operation area, and several abnormal behavior types are constructed for the abnormal human behavior in each personnel sub-operation area, and several abnormal behavior levels are constructed for each abnormal behavior type, and each abnormal behavior level corresponds to several abnormal behavior judgment factor parameter intervals.

4. The smelting hidden danger warning method based on video data analysis according to claim 1 is characterized in that: The method of analyzing the video image corresponding to each monitoring block and determining the state description of the device corresponding to the monitoring block includes: Delineate the feature edges or mark the feature signs of key structures of equipment in the monitoring area; Based on the normal operation status of the equipment in the monitoring block, the motion ranges of different characteristic edges or characteristic marks are determined, and several levels of sub-motion ranges are delineated for the motion ranges, and a first abnormal motion parameter is configured for each sub-motion range; Based on the normal operation status of the equipment in the monitoring block, the motion speed intervals of different characteristic edges or characteristic marks are determined, and several levels of sub-motion speed intervals are delineated for the motion speed intervals, and a second abnormal motion parameter is configured for each sub-motion speed interval; The first abnormal motion parameter and the second abnormal motion parameter are identified as a state description of the device of the monitoring block.

5. The smelting hidden danger warning method based on video data analysis according to claim 4 is characterized in that: Methods for determining the behavior description of a human body in a monitoring area include: Use human body recognition technology to identify the human body in the monitoring area in real time, and build a real-time human body expression model for the identified human body; Determine different personnel working areas in the monitoring block, and determine several normal human body postures in each personnel working area, build a normal human body expression model based on the normal human body postures, and record the combination of several normal human body expression models as a normal human body expression model group; The real-time human limb expression model is compared and analyzed using the normal human limb expression model group. If no matching normal human limb expression model is found in the normal human limb expression model group, the real-time human limb expression model is marked as abnormal. The number of abnormal behaviors of the real-time human body expression model marked as abnormal within a preset time period is counted, and the behavior description of the human body in the monitoring block is determined based on the number of abnormal behaviors.

6. The smelting hidden danger warning method based on video data analysis according to claim 5 is characterized in that: The method of analyzing the state description or behavior description by using the monitoring strategy corresponding to each monitoring block to determine the abnormal situation assessment of the corresponding device or human body includes: Performing real-time motion analysis on characteristic edges or characteristic marks in the monitoring block to determine a first abnormal motion parameter and a second abnormal motion parameter of the device, and determining a comprehensive abnormal motion parameter of the device corresponding to the monitoring block based on the first abnormal motion parameter and the second abnormal motion parameter; Among them, the expression for calculating the comprehensive abnormal motion parameters is: ； in, is the comprehensive abnormal motion parameter, is the influence weight of the first abnormal motion parameter, is the first abnormal motion parameter, is the influence weight of the second abnormal motion parameter, is the second abnormal motion parameter, is the duration of the continuous abnormal state of the device, is the adjustment coefficient for the impact of the duration of the continuous abnormal state, and c is the adjustment constant for the impact of the duration of the continuous abnormal state; According to the number of abnormal behaviors of the real-time human body expression model, several abnormal behavior frequency intervals are constructed, and human abnormal parameters are set corresponding to each abnormal behavior frequency interval. By judging the abnormal behavior frequency interval to which the abnormal behavior frequency belongs, the human abnormal parameters of the real-time human body expression model are determined.

7. The smelting hidden danger warning method based on video data analysis according to claim 1 is characterized in that: The method of analyzing the chain effect relationship of the abnormally marked retrieval block and determining the hidden danger warning degree of the smelting site based on the analysis result includes: Determine the comprehensive abnormal motion parameters of the equipment corresponding to different monitoring blocks, or the abnormal human body parameters of the human body. If the comprehensive abnormal motion parameters or the abnormal human body parameters are greater than or equal to the preset values, mark the monitoring blocks as abnormal. Determine the total number of abnormal blocks in the abnormal mark monitoring block, determine the number of chain abnormal blocks in the abnormal mark monitoring block affected by the chain relationship, and calculate the chain abnormal ratio of the number of chain abnormal blocks to the total number of abnormal blocks; Based on the comprehensive abnormal motion parameters of different monitoring blocks, or the abnormal parameters of the human body, as well as the chain abnormality ratio, the hidden danger warning level of the smelting site is determined.

8. The smelting hidden danger warning method based on video data analysis according to claim 7 is characterized in that: The expression for determining the hidden danger warning level of the smelting site is: ； in, For the hidden danger warning level, is the number of chained abnormal blocks, is the total number of abnormal blocks, is the impact adjustment coefficient of the linkage anomaly ratio, is the adjustment constant for the effect of the linkage anomaly ratio, is the comprehensive abnormal motion parameter of the i-th abnormal marking monitoring block, is the human body abnormal parameter of the ith abnormal mark monitoring block, and n is the total number of abnormal mark monitoring blocks.

9. The smelting hidden danger warning system based on video data analysis is characterized by: include: The first module is used to divide the video images captured by each camera into monitoring blocks, and determine the monitoring strategy of the monitoring block based on the objects to be monitored in the monitoring block; The second module is used to analyze the video images corresponding to each monitoring block, determine the state description of the device or the behavior description of the human body corresponding to the monitoring block, and use the monitoring strategy corresponding to each monitoring block to analyze the state description or behavior description to determine the abnormal situation assessment of the corresponding device or human body; The third module is used to construct a smelting site plan and mark each monitoring block on the smelting site plan. Based on the chain effect characteristics between equipment, different monitoring blocks are linked to each other, and the abnormal situation assessment of each monitoring block is monitored in real time. The monitoring blocks identified as abnormal in the abnormal situation assessment are marked as abnormal, and the chain effect relationship analysis is performed on the abnormal marked search blocks. Based on the analysis results, the hidden danger warning level of the smelting site is determined; The fourth module is used to determine the hidden danger alarm level based on the hidden danger warning level interval to which the hidden danger warning level belongs.

Images