Coal logistics park production management and control system based on operation video identification technology

Abstract

The invention is suitable for the technical field of safety production management, and provides a coal logistics park production management and control system based on an operation video recognition technology, and the system comprises a video collection module which is used for obtaining a monitoring image related to a key region through monitoring equipment disposed in a park; the video processing and data analysis module is used for carrying out risk identification on the monitoring image by utilizing an intelligent video analysis technology; the control warning module is used for controlling early warning equipment arranged on the site to work based on the risk identification result; and the terminal display module is used for processing the risk identification result into display information and sending the display information to digital screen equipment. Through the control warning module and the terminal display module, real-time early warning control can be carried out, risks in the park can be displayed in a digital screen mode, and the production operation management and control efficiency and timeliness of the coal logistics park are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of safe production management, and in particular to a coal logistics park production control system based on operation video recognition technology. Background Art

[0002] Coal logistics parks refer to comprehensive logistics centers dedicated to coal storage, loading and unloading, transportation and distribution. These parks are usually located in coal production areas, consumption areas or important transportation hubs, such as railway stations and ports.

[0003] Due to the particularity of the coal logistics industry, there are many risks in the process of transportation, storage, loading and unloading, such as fire, explosion, collapse and personnel operation violations. Once these risks occur, they will cause serious losses to people and property.

[0004] In reality, the production process of coal logistics parks is mostly controlled by manual inspections and traditional manual video surveillance. Manual inspections are not real-time and cannot detect problems in time. Manual video surveillance is impossible to observe all monitoring images in real time due to limited human energy, which easily leads to blind spots in monitoring and missed inspections, so there is insufficient control. Therefore, a coal logistics park production control system based on operation video recognition technology is proposed to solve the above problems. Summary of the invention

[0005] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a coal logistics park production control system based on operation video recognition technology to solve the problems existing in the above-mentioned background technology.

[0006] The present invention is implemented as follows: a coal logistics park production control system based on operation video recognition technology, the system comprising:

[0007] A video acquisition module, used to obtain monitoring images of key areas through monitoring equipment installed in the park, wherein the monitoring images are accompanied by area marking lines corresponding to the key areas;

[0008] A video processing and data analysis module, used for performing risk identification on the monitoring image using intelligent video analysis technology, wherein the scope of risk identification corresponds to the key area;

[0009] A control warning module controls the operation of the warning equipment installed on site based on the risk identification result, so that when risky operations occur in the key area, the voice equipment emits a warning sound;

[0010] The terminal display module is used to process the risk identification results into display information and send it to the digital screen device, which is a device in the control center.

[0011] As a further solution of the present invention: the video acquisition module includes:

[0012] The image collection unit is used to obtain real-time images taken by all monitoring devices;

[0013] The area division unit is used to frame the real-time image according to the set key areas in the coal logistics park to obtain the real-time image with area marking lines;

[0014] A picture simplification unit, which performs cropping processing on the picture of the real-time image based on the area marking line;

[0015] The pre-processing recognition unit is used to recognize the cropped real-time image. When an object or a person appears, the real-time image is recorded to obtain a monitoring image and upload it.

[0016] As a further solution of the present invention: the video processing and data analysis module includes:

[0017] A video separation unit, used to separate a static background from a target foreground in a surveillance image by using a background modeling technique, wherein the static background corresponds to the infrastructure in the key area, and the target foreground corresponds to other objects in the key area;

[0018] a target recognition unit, which determines based on the type of the target foreground in the monitoring image;

[0019] An object detection unit, used to detect the position and shape of an object or the moving speed of an object by using an object detection model or a multi-target tracking algorithm to perform recognition analysis when the target is an object;

[0020] A behavior detection unit is used to analyze the behavior of a person based on action sequence analysis technology when the target is a person;

[0021] The integration unit integrates the detection results and uploads and saves them.

[0022] As a further solution of the present invention: the object detection unit includes:

[0023] The static object detection subunit is used to identify the position and shape of the target foreground in the monitoring image using the deep learning target detection model when the target foreground is stationary;

[0024] The dynamic object detection subunit is used to continuously track the moving trajectory of the target foreground in the monitoring image using a multi-target tracking algorithm, and to monitor its moving speed in real time in combination with a speed estimation algorithm.

[0025] As a further solution of the present invention: the behavior detection unit includes:

[0026] The individual behavior detection subunit is used to process the surveillance image to obtain multiple continuous frames when the target foreground in the surveillance image is a person, and to perform sequence analysis on the person's actions in the continuous frames;

[0027] The group behavior detection subunit is used to perform action analysis on multiple persons using a group behavior analysis algorithm when the target foreground in the surveillance image is multiple persons.

[0028] As a further solution of the present invention: the system further includes a notification module, the notification module includes:

[0029] A location determination unit, used to determine the location information of the risk occurrence according to the risk identification result;

[0030] An information integration unit, used to integrate the location information and risk identification results to generate an information link;

[0031] A personnel selection unit, used to select the personnel with the highest priority from a personnel list according to the order of priority, wherein the personnel list is set according to the management personnel in the coal logistics park;

[0032] The information sending unit sends the information link to the communication terminal of the selected person.

[0033] As a further solution of the present invention: the system further includes a risk statistics module, which includes:

[0034] Risk collection unit, used to integrate all risk identification results to generate a risk database;

[0035] The data sorting unit prioritizes risks based on the risk database according to the location and number of times the risks occur.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The present invention effectively saves labor costs, reduces the consumption of human resources and workload of manual inspections and manual video observation; by controlling the warning module and the terminal display module, real-time early warning control can be performed and the risks in the park can be displayed in the form of a digital screen, thereby improving the efficiency and timeliness of production operation management and control in the coal logistics park; in addition, by utilizing intelligent video analysis technology, risk points and personnel violations in various operating activities can be accurately identified in real time, thus overcoming the limitation that traditional video surveillance systems can only be viewed after the fact; finally, because intelligent video analysis technology is used for identification and judgment, and the identification results are displayed on a digital screen, data trends and directions can be directly observed, thereby providing managers with decision-making data support in a timely and effective manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 The figure is a flow chart of a production control method for a coal logistics park based on operation video recognition technology.

[0039] Figure 2 The present invention is a flow chart of a method for production control of a coal logistics park based on operation video recognition technology, in which monitoring images of key areas are obtained through monitoring equipment arranged in the park.

[0040] Figure 3 The present invention is a flow chart of a method for production control of a coal logistics park based on operation video recognition technology, which uses intelligent video analysis technology to identify risks in the monitoring images.

[0041] Figure 4 This is a structural diagram of a coal logistics park production control system based on operation video recognition technology.

[0042] Figure 5 This is a structural diagram of a video acquisition module in a coal logistics park production control system based on operation video recognition technology.

[0043] Figure 6 This is a structural diagram of the video processing and data analysis module in a coal logistics park production control system based on operation video recognition technology.

[0044] Figure 7 This is a structural diagram of an object detection unit in a coal logistics park production control system based on operation video recognition technology.

[0045] Figure 8 This is a structural diagram of a behavior detection unit in a coal logistics park production control system based on operation video recognition technology.

[0046] Fig. 9 This is a structural diagram of a behavior detection unit in a coal logistics park production control system based on operation video recognition technology.

[0047] Fig.10 This is a structural diagram of a behavior detection unit in a coal logistics park production control system based on operation video recognition technology. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0049] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0050] like Figure 1 As shown, an embodiment of the present invention provides a coal logistics park production control method based on operation video recognition technology, and the method includes the following steps:

[0051] S100, obtaining a monitoring image of a key area through monitoring equipment installed in the park, wherein the monitoring image includes an area marking line corresponding to the key area;

[0052] S200, using intelligent video analysis technology to identify risks on the surveillance image, wherein the scope of risk identification corresponds to the key area;

[0053] S300, based on the risk identification result, controlling the operation of the early warning device set up on site, so that when a risk operation occurs in the key area, the voice device emits a warning sound;

[0054] S400, processing the risk identification result into display information and sending it to a digital screen device, wherein the digital screen device is a display device in a control center.

[0055] It should be noted that the present invention mainly utilizes intelligent video analysis technology to conduct real-time video monitoring of key areas within the coal logistics park. These key areas may be coal weighing areas, transportation channels, coal storage sheds, coal belt transmission areas, coal loading areas and other areas. It also conducts intelligent analysis on the monitoring videos of production operations in the above areas to timely and effectively discover potential risk points and personnel violations, thereby triggering the operation of early warning equipment, and displaying images and risk identification and judgment results on digital screen devices to achieve comprehensive control of the production process.

[0056] In the embodiments of the present invention, the present invention effectively saves labor costs, reduces the consumption of human resources and workload of manual inspections and manual video observations; at the same time, it can also perform real-time early warning control and display risks in the park in the form of a digital screen, thereby improving the efficiency and timeliness of production operation management and control in the coal logistics park; in addition, by using intelligent video analysis technology, it is possible to accurately identify risk points and personnel violations in various operating activities in real time, thus overcoming the limitation that traditional video surveillance systems can only be viewed after the fact; finally, because intelligent video analysis technology is used for identification and judgment, and the identification results are displayed on a digital screen, data trends and directions can be directly observed, thereby providing managers with timely and effective decision-making data support.

[0057] like Figure 2As shown, as a preferred embodiment of the present invention, the step of obtaining monitoring images of key areas by monitoring equipment arranged in the park specifically includes:

[0058] S101, obtaining real-time images captured by all monitoring devices;

[0059] S102, selecting a frame of the real-time image according to a set key area in the coal logistics park to obtain a real-time image with area marking lines;

[0060] S103, cropping the real-time image based on the area marking line;

[0061] S104, the cropped real-time image is identified, and when an object or a person appears, the real-time image is recorded to obtain a monitoring image and uploaded.

[0062] In the embodiments of the present invention, generally speaking, the key areas in the coal logistics park are fixed, and the scope of the site is also limited, such as the above-mentioned coal weighing area, transportation channel, coal storage shed, coal belt transmission area, etc., but the picture taken by the monitoring equipment is generally a large-scale image. In order to reduce the data processing amount of video recognition analysis, the real-time image can be cropped according to these key areas, so that the uploaded monitoring image only retains the information in the key area, making data transmission and processing more efficient, and the real-time image is not always uploaded. The monitoring equipment can be used to pre-judge whether there are objects or personnel in the key area. When one of the two appears, the real-time image segment can be uploaded as useful information.

[0063] like Figure 3 As shown, as a preferred embodiment of the present invention, the step of using intelligent video analysis technology to identify risks of the monitoring image specifically includes:

[0064] S201, separating a static background from a target foreground in a monitoring image by using a background modeling technology, wherein the static background corresponds to infrastructure in a key area, and the target foreground corresponds to other objects in the key area;

[0065] S202, determining based on the type of the target foreground in the monitoring image;

[0066] S203, when the target is an object, use a target detection model or a multi-target tracking algorithm to perform recognition analysis to detect the position and shape of the object or the moving speed of the object;

[0067] S204, when the target is a person, performing behavior analysis on the person based on the action sequence analysis technology;

[0068] S205, integrating the detection results and uploading and saving them.

[0069] In an embodiment of the present invention, whether a person or an object appears in the key area is completely random. For example, when coal is piled in the key area, in order to reduce the amount of data processing for later identification, the coal and the background of the key area can be distinguished first, which can make the identification more accurate. Then, the target detection model is used to determine the position and shape of the coal pile, so as to determine whether the coal pile is beyond the range. Of course, if there are moving work vehicles in the key area, a multi-target tracking algorithm is required for identification. In short, different target types also determine the different recognition technologies used.

[0070] like Figure 4 As shown, as an embodiment of the present invention, a coal logistics park production control system based on operation video recognition technology is also provided, and the system includes:

[0071] The video acquisition module 100 is used to obtain monitoring images of key areas through monitoring equipment installed in the park, and the monitoring images are accompanied by area marking lines corresponding to the key areas;

[0072] The video processing and data analysis module 200 is used to identify risks of the monitoring image using intelligent video analysis technology, and the scope of risk identification corresponds to the key area;

[0073] A control warning module 300 controls the operation of the warning device installed on site based on the risk identification result, so as to make the voice device emit a warning sound when a risk operation occurs in the key area;

[0074] The terminal display module 400 is used to process the risk identification result into display information and send it to a digital screen device, which is a display device in the control center.

[0075] In the embodiments of the present invention, the present invention effectively saves labor costs, reduces the consumption of human resources and workload of manual inspections and manual video observations; by controlling the warning module and the terminal display module, real-time early warning control can be performed and the risks in the park can be displayed in the form of a digital screen, thereby improving the efficiency and timeliness of production operation management and control in the coal logistics park; in addition, by using intelligent video analysis technology, the risk points of various operating activities and illegal operations of personnel can be accurately identified in real time, overcoming the limitation that traditional video surveillance systems can only be viewed after the fact; finally, because intelligent video analysis technology is used for identification and judgment, and the identification results are displayed on a digital screen, data trends and directions can be directly observed, thereby providing managers with decision-making data support in a timely and effective manner.

[0076] like Figure 5 As shown, as a preferred embodiment of the present invention, the video acquisition module 100 includes:

[0077] The image collection unit 101 is used to obtain real-time images taken by all monitoring devices;

[0078] The area division unit 102 is used to frame the real-time image according to the set key area in the coal logistics park to obtain the real-time image with area marking lines;

[0079] The image simplification unit 103 performs cropping processing on the image of the real-time image based on the area marking line;

[0080] The pre-processing and identifying unit 104 is used to identify the cropped real-time image. When an object or a person appears, the real-time image is recorded to obtain a monitoring image and upload it.

[0081] like Figure 6 As shown, as a preferred embodiment of the present invention, the video processing and data analysis module 200 includes:

[0082] The video separation unit 201 is used to separate the static background and the target foreground in the monitoring image by using the background modeling technology, wherein the static background corresponds to the infrastructure in the key area, and the target foreground corresponds to other objects in the key area;

[0083] A target recognition unit 202 determines the type of the target foreground in the monitoring image;

[0084] The object detection unit 203 is used to detect the position and shape of the object or the moving speed of the object by using the target detection model or the multi-target tracking algorithm to perform recognition analysis when the target belongs to the object;

[0085] A behavior detection unit 204, used for performing behavior analysis on the person based on action sequence analysis technology when the target is a person;

[0086] The integration unit 205 integrates the detection results and uploads and saves them.

[0087] like Figure 7 As shown, as a preferred embodiment of the present invention, the object detection unit 203 includes:

[0088] The static object detection subunit 2031 is used to identify the position and shape of the target foreground in the monitoring image using the deep learning target detection model when the target foreground in the monitoring image is in a static state;

[0089] The dynamic object detection subunit 2032 is used to continuously track the moving trajectory of the target foreground in the monitoring image using a multi-target tracking algorithm when the target foreground in the monitoring image is in motion, and to monitor the moving speed in real time in combination with a speed estimation algorithm.

[0090] In the embodiment of the present invention, there will be different identification methods for different motion states of objects. For example, when the target in the key area is a pile of coal mines, it is only necessary to use the target detection model to identify its shape and position to determine whether there are any violations in the coal mine stacking. When the object is a moving object, such as a work vehicle, a multi-target tracking algorithm is generally used to measure its moving speed, so as to determine whether the work vehicle has a speeding problem. Therefore, the object detection unit 203 mainly has the functions of detecting dynamic and static aspects.

[0091] like Figure 8 As shown, as a preferred embodiment of the present invention, the behavior detection unit 204 includes:

[0092] The individual behavior detection subunit 2041 is used to process the monitoring image to obtain multiple continuous frames and perform sequence analysis on the person's actions in the continuous frames when the target foreground in the monitoring image is a person;

[0093] The group behavior detection subunit 2042 is used to perform action analysis on the multiple persons using a group behavior analysis algorithm when the target foreground in the monitoring image is multiple persons.

[0094] In an embodiment of the present invention, when a person appears in the key area, there are two situations for identifying the behavior of the person. When there is only one person, abnormal behavior can be identified by simply using the action sequence analysis of continuous frames. For example, if people frequently enter and exit an area, there may be safety hazards or illegal operations. Using a group behavior analysis algorithm will detect gathered crowds, which may also pose a safety hazard.

[0095] like Fig. 9 As shown, as a preferred embodiment of the present invention, the coal logistics park production control system based on the operation video recognition technology also includes a notification module 500, and the notification module 500 includes:

[0096] A location determination unit 501 is used to determine the location information of the risk occurrence according to the risk identification result;

[0097] An information integration unit 502, used to integrate the location information and the risk identification result to generate an information link;

[0098] A personnel selection unit 503, for selecting a person with the highest priority from a personnel list according to the order of priority, wherein the personnel list is set according to the management personnel in the coal logistics park;

[0099] The information sending unit 504 sends the information link to the communication terminal of the selected person.

[0100] In the embodiment of the present invention, because the location of the monitoring equipment is determined and the key area is unique in the park, when a risk is identified in a certain area, it is easy to obtain the specific location of the area. The personnel list includes multiple managers, and the priority can be determined by distance. The manager's location can be obtained through his communication terminal, thereby judging the distance between the manager and the risky area. Therefore, the information link can be sent to the manager who is closest to the risky area, so as to facilitate timely processing of the risky area.

[0101] like Fig.10 As shown, as a preferred embodiment of the present invention, the coal logistics park production control system based on operation video recognition technology also includes a risk statistics module 600, and the risk statistics module 600 includes:

[0102] The risk collection unit 601 is used to integrate all risk identification results to generate a risk database;

[0103] The data sorting unit 602 performs priority sorting based on the risk database according to the location where the risk occurs and the number of times the risk occurs.

[0104] In the embodiment of the present invention, the number of key areas in the coal mine logistics park is limited. Risks occurring in each key area can be detected through monitoring and identification, and the risk database retains all data. These data can be the corresponding videos and the results of intelligent video analysis. After sorting, it can be more intuitive to understand which key areas are high-risk areas, thereby facilitating the management personnel to focus on control and giving direction to the safety supervision work in the coal mine logistics park.

[0105] The above only describes in detail the preferred embodiments of the present invention, which is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0106] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0107] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0108] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the disclosure in the specification and examples. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A coal logistics park production control system based on operation video recognition technology, characterized in that: The system comprises: A video acquisition module, used to obtain monitoring images of key areas through monitoring equipment installed in the park, wherein the monitoring images are accompanied by area marking lines corresponding to the key areas; A video processing and data analysis module, used for performing risk identification on the monitoring image using intelligent video analysis technology, wherein the scope of risk identification corresponds to the key area; A control warning module controls the operation of the warning equipment installed on site based on the risk identification result, so that when risky operations occur in the key area, the voice equipment emits a warning sound; The terminal display module is used to process the risk identification results into display information and send it to the digital screen device, which is the display device in the control center.

2. The coal logistics park production control system based on operation video recognition technology according to claim 1 is characterized in that: The video acquisition module comprises: The image collection unit is used to obtain real-time images taken by all monitoring devices; The area division unit is used to frame the real-time image according to the set key areas in the coal logistics park to obtain the real-time image with area marking lines; A picture simplification unit, which performs cropping processing on the picture of the real-time image based on the area marking line; The pre-processing recognition unit is used to recognize the cropped real-time image. When an object or a person appears, the real-time image is recorded to obtain a monitoring image and upload it.

3. The coal logistics park production control system based on operation video recognition technology according to claim 1 is characterized in that: The video processing and data analysis module includes: A video separation unit, used to separate a static background from a target foreground in a surveillance image by using a background modeling technique, wherein the static background corresponds to the infrastructure in the key area, and the target foreground corresponds to other objects in the key area; a target recognition unit, which determines based on the type of the target foreground in the monitoring image; An object detection unit, used to detect the position and shape of an object or the moving speed of an object by using an object detection model or a multi-target tracking algorithm to perform recognition analysis when the target is an object; A behavior detection unit is used to analyze the behavior of a person based on action sequence analysis technology when the target is a person; The integration unit integrates the detection results and uploads and saves them.

4. The coal logistics park production control system based on operation video recognition technology according to claim 3 is characterized in that: The object detection unit comprises: The static object detection subunit is used to identify the position and shape of the target foreground in the monitoring image using the deep learning target detection model when the target foreground is stationary; The dynamic object detection subunit is used to continuously track the moving trajectory of the target foreground in the monitoring image using a multi-target tracking algorithm, and to monitor its moving speed in real time in combination with a speed estimation algorithm.

5. The coal logistics park production control system based on operation video recognition technology according to claim 3 is characterized in that: The behavior detection unit comprises: The individual behavior detection subunit is used to process the surveillance image to obtain multiple continuous frames when the target foreground in the surveillance image is a person, and to perform sequence analysis on the person's actions in the continuous frames; The group behavior detection subunit is used to perform action analysis on multiple persons using a group behavior analysis algorithm when the target foreground in the surveillance image is multiple persons.

6. The coal logistics park production control system based on operation video recognition technology according to claim 1 is characterized in that: The system further includes a notification module, which includes: A location determination unit, used to determine the location information of the risk occurrence according to the risk identification result; An information integration unit, used to integrate the location information and risk identification results to generate an information link; A personnel selection unit, used to select the personnel with the highest priority from a personnel list according to the order of priority, wherein the personnel list is set according to the management personnel in the coal logistics park; The information sending unit sends the information link to the communication terminal of the selected person.

7. The coal logistics park production control system based on operation video recognition technology according to claim 1 is characterized in that: The system also includes a risk statistics module, which includes: Risk collection unit, used to integrate all risk identification results to generate a risk database; The data sorting unit prioritizes risks based on the risk database according to the location and number of times the risks occur.

Images