A method, apparatus, and medium for monitoring personnel intrusion in a flight zone of a dragline

Abstract

The application relates to the field of safety monitoring, and discloses a method and device for monitoring personnel intrusion into a running area of a scraper and a medium, wherein the method comprises the following steps: acquiring image data sets in a preset area at a fixed frame rate; determining scraper areas corresponding to each image and a preset torso area of personnel by identifying the image data sets; superimposing the scraper areas corresponding to each frame of image in a first preset number of frames before a target frame to obtain a superimposed scraper area corresponding to the target frame image; obtaining an intrusion state marking value corresponding to the target frame image based on the preset torso area of personnel and the superimposed scraper area of the target frame image; and judging whether there is personnel intrusion into the running area of the scraper by the intrusion state marking values corresponding to each image in a second preset number of frames. By superimposing the scraper areas corresponding to multiple images, the misjudgment of the scraper area caused by temporary shielding of personnel and other factors can be effectively avoided, so that the accuracy of monitoring is improved.

Description

Technical Field

[0001] This application relates to the field of safety monitoring, specifically to a method, equipment, and medium for monitoring personnel intrusion into the operating area of ​​a scraper conveyor. Background Technology

[0002] In industrial production, scraper conveyors are common conveying equipment, but their operating area is inherently dangerous, so personnel are usually prohibited from entering the scraper conveyor operating area.

[0003] Currently, monitoring of personnel intrusion into the scraper conveyor operating area mainly relies on manual inspections or simple physical protective devices. However, manual inspections are time-sensitive and cannot be monitored in real time, allowing personnel to enter during inspection intervals and potentially causing safety incidents. Simple physical protective devices cannot prevent personnel from climbing over or damaging them, nor can they promptly issue alarms to notify relevant personnel. Therefore, existing monitoring methods suffer from insufficient timeliness and accuracy, necessitating a more efficient monitoring method. Summary of the Invention

[0004] To address the aforementioned problems, this application proposes a method, equipment, and medium for monitoring personnel intrusion into the operating area of ​​a scraper conveyor, wherein the method includes:

[0005] An image dataset within a preset area is acquired at a fixed frame rate. The image dataset is then identified to determine the scraper machine area and the preset torso area of ​​a person corresponding to each image. The scraper machine areas corresponding to each frame within a first preset number of frames before the target frame are superimposed to obtain the scraper machine superimposed area corresponding to the target frame image. Based on the preset torso area of ​​the person in the target frame image and the scraper machine superimposed area, an intrusion status marker value corresponding to the target frame image is obtained. The intrusion status marker values ​​corresponding to each image within a second preset number of frames are used to determine whether a person has intruded into the scraper machine operating area.

[0006] In one example, the preset torso region of the person is the foot region. The preset torso region corresponding to each image is determined by identifying the image dataset. Specifically, this includes: identifying the bounding box of the person region corresponding to each image; using the lower boundary of the bounding box of the person region as the centerline of the foot region; multiplying the height of the bounding box of the person region by a preset ratio to obtain the height of the foot region bounding box; using the width of the bounding box of the person region as the width of the foot region bounding box; and determining the foot region corresponding to each image based on the height and width of the foot region bounding box.

[0007] In one example, the step of superimposing the scraper machine regions corresponding to each frame image within a first preset frame number before the target frame to obtain the scraper machine superimposed region corresponding to the target frame image specifically includes: determining the first preset frame number and the scraper machine superimposed region corresponding to the current frame; determining the frame number difference between the current frame and the target frame; determining the expected removal frame and the expected addition frame through the first preset frame number and the frame number difference; removing the scraper machine regions corresponding to the expected removal frames from the scraper machine superimposed region corresponding to the current frame to obtain an intermediate scraper machine region; and adding the scraper machine regions corresponding to the expected addition frames to the intermediate scraper machine region to obtain the scraper machine superimposed region corresponding to the target frame image.

[0008] In one example, obtaining the intrusion status marker value corresponding to the target frame image based on the preset torso region of the person in the target frame image and the superimposed region of the scraper machine specifically includes: calculating the intersection-union ratio (IUGR) of the preset torso region of the person in the target frame image and the superimposed region of the scraper machine; and determining the intrusion status marker value corresponding to the target frame image based on the IUGR.

[0009] In one example, determining the intrusion status marker value corresponding to the target frame image based on the cross-union ratio (CUP) specifically includes: if the CUP is higher than a preset CUP threshold, then a first preset value is used as the intrusion status marker value corresponding to the target frame image; if the CUP is not higher than the preset CUP threshold, then a second preset value is used as the intrusion status marker value corresponding to the target frame image.

[0010] In one example, determining the intrusion status marker value corresponding to the target frame image based on the cross-union ratio specifically includes: using the cross-union ratio as the intrusion status marker value corresponding to the target frame image.

[0011] In one example, determining whether a person has entered the scraper conveyor operating area by using the intrusion status marker values ​​corresponding to each image within a second preset frame number specifically includes: determining the sum of the intrusion status marker values ​​corresponding to each image within the second preset frame number; if the ratio of the sum of the intrusion status marker values ​​to the second preset frame number is higher than a preset ratio, then a person has entered the scraper conveyor operating area.

[0012] In one example, after determining whether a person has entered the scraper conveyor operating area by using the intrusion status marker values ​​corresponding to each image within a second preset frame number, the method further includes: determining that a person has entered the scraper conveyor operating area; determining a corresponding preset warning method based on the ratio of the sum of the intrusion status marker values ​​to the second preset frame number; issuing a warning according to the preset warning method, and caching video frames within a third preset alarm time period before and after the warning time.

[0013] This application also provides a personnel intrusion monitoring device for a scraper conveyor operating area, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform: acquiring an image dataset within a preset area at a fixed frame rate; identifying the scraper conveyor area and a preset torso area of ​​a person corresponding to each image by recognizing the image dataset; superimposing the scraper conveyor areas corresponding to each frame image within a first preset number of frames before the target frame to obtain a scraper conveyor superimposed area corresponding to the target frame image; obtaining an intrusion status marker value corresponding to the target frame image based on the preset torso area of ​​the person and the scraper conveyor superimposed area; and determining whether a person has intruded into the scraper conveyor operating area by using the intrusion status marker values ​​corresponding to each image within a second preset number of frames.

[0014] This application also provides a non-volatile computer storage medium storing computer-executable instructions, the computer-executable instructions being configured to: acquire an image dataset within a preset area at a fixed frame rate; identify the scraper machine area and a preset torso area of ​​a person corresponding to each image by recognizing the image dataset; superimpose the scraper machine areas corresponding to each frame image within a first preset number of frames before the target frame to obtain a scraper machine superimposed area corresponding to the target frame image; obtain an intrusion status marker value corresponding to the target frame image based on the preset torso area of ​​the person and the scraper machine superimposed area of ​​the target frame image; and determine whether a person has intruded into the scraper machine operating area by using the intrusion status marker values ​​corresponding to each image within a second preset number of frames.

[0015] The method proposed in this application offers the following advantages: By overlaying the scraper conveyor areas corresponding to multiple frames of images, misjudgments of the scraper conveyor area caused by factors such as temporary obstruction by personnel can be effectively avoided, thereby improving the accuracy of monitoring. Calculations based on intrusion status marker values ​​corresponding to multiple frames of images avoid potential misjudgments that may occur with single-frame analysis. Furthermore, by adjusting the preset parameter values, real-time monitoring is possible, allowing staff to respond promptly and reducing accident casualties and property damage. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 This is a flowchart illustrating a method for monitoring personnel intrusion into the operating area of ​​a scraper conveyor, as described in an embodiment of this application.

[0018] Figure 2 This is a schematic diagram of a personnel intrusion monitoring device in the operating area of ​​a scraper conveyor according to an embodiment of this application;

[0019] Figure 3 This is a schematic diagram of a personnel intrusion monitoring device in the operating area of ​​a scraper conveyor according to an embodiment of this application. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0022] Figure 1 This is a flowchart illustrating a method for monitoring unauthorized entry into a scraper conveyor operating area, provided in one or more embodiments of this specification. This method can be applied to monitoring unauthorized entry into a scraper conveyor operating area. The process can be executed by a corresponding computing device (e.g., a computing device located near the scraper conveyor, or a cloud server). Certain input parameters or intermediate results in the process can be manually adjusted to help improve accuracy.

[0023] The analysis method involved in the embodiments of this application can be implemented by a terminal device or a server, and this application does not impose any special limitations on it. For ease of understanding and description, the following embodiments are all described in detail using a server as an example.

[0024] It should be noted that the server can be a single device or a system composed of multiple devices, i.e., a distributed server. This application does not make any specific limitations in this regard.

[0025] like Figure 1 As shown in the figure, this application embodiment provides a method for monitoring personnel intrusion into the operating area of ​​a scraper conveyor, including:

[0026] S101: Obtain the image dataset within a preset area at a fixed frame rate.

[0027] An image acquisition device (such as a high-definition camera) positioned within the scraper conveyor's operating area captures omnidirectional images of the area at a fixed frame rate f (frames per second), thus generating an image dataset. The preset area can refer to the scraper conveyor's operating area itself, or it can encompass a larger area, such as the area including the scraper conveyor's operating area and the region near the image acquisition device. The image dataset contains images captured by different image acquisition devices at different times. The installation position and angle of the image acquisition device are optimized to ensure complete coverage of the scraper conveyor's operating area.

[0028] S102: By identifying the image dataset, the scraper machine area and the preset torso area of ​​the personnel corresponding to each image are determined.

[0029] After obtaining the image dataset within the preset area, the scraper machine and personnel can be detected in each image within the dataset. During monitoring, a deep neural network model can be used to quickly and accurately identify the scraper machine area and the preset torso area of ​​the personnel. It should be noted that the preset torso area of ​​the personnel here refers to preset parts on the torso, such as the head, hands, and feet. This application uses the feet as an example. In particular, for the scraper machine area, the output is presented in polygon form. This output method can more accurately depict the actual area range of the scraper machine, providing more accurate data for subsequent operations such as intersection and union calculations.

[0030] In one embodiment, image recognition can be performed using the YOLO target detection algorithm. Specifically, any image in the image dataset needs to be selected as the target image; the target image is segmented to obtain a preset number of image grids; target detection is performed on the preset number of image grids to determine the image grids containing the scraper machine and the preset torso of a person; based on the image grids containing the scraper machine, the scraper machine region corresponding to the target image is determined; based on the image grids containing the preset torso of a person, the preset torso region of a person within the target image is determined; by traversing any image in the image dataset, the scraper machine region and the preset torso region of a person corresponding to each image in the image dataset are obtained. When using the YOLO target detection algorithm, the positions of the scraper machine and the person, as well as the confidence level c (0≤C≤1, the closer C is to 1, the more reliable the detection result), can be quickly and accurately identified. When determining the image grids containing the scraper machine, grids with a scraper machine confidence level higher than a preset threshold can be used as image grids containing the scraper machine. The same applies to image grids containing the preset torso of a person, which will not be elaborated further here.

[0031] In one embodiment, besides directly detecting the pre-defined torso of a person in an image using the YOLO object detection algorithm, one can first detect the person region in the image and then process it to obtain the pre-defined torso region. For example, when the pre-defined torso region is the foot region, during detection, the image dataset can be identified first to determine the bounding box of the person region corresponding to each image. Then, the lower boundary of the person region bounding box is used as the center line of the foot region. The height of the person region bounding box is then multiplied by a preset ratio (e.g., 10%) to obtain the height of the foot region bounding box, and the width of the person region bounding box can be directly used as the width of the foot region bounding box. After obtaining the height and width of the foot region bounding box, the foot region corresponding to each image can be determined.

[0032] S103: Superimpose the scraper machine regions corresponding to each frame image within the first preset number of frames before the target frame to obtain the scraper machine superimposed region corresponding to the target frame image.

[0033] To accurately determine the scraper conveyor area and avoid misjudgment due to factors such as temporary obstruction by personnel, the scraper conveyor areas corresponding to each frame within a first preset number of frames preceding the target frame can be superimposed to obtain the superimposed scraper conveyor area corresponding to the target frame image. In subsequent judgment processes, the superimposed scraper conveyor area corresponding to the target frame image is used as the scraper conveyor operating area. It should be noted that the "frame image" mentioned in this application refers to the image corresponding to that frame, i.e., the image dataset acquired in that frame.

[0034] In one embodiment, when overlaying the scraper conveyor region, it is necessary to determine the size of a first preset frame number and the scraper conveyor overlay region corresponding to the current frame. Then, the frame number difference between the current frame and the target frame is determined. At this time, the expected removal frames and expected addition frames can be determined by the first preset frame number and the frame number difference. Then, the scraper conveyor regions corresponding to the expected removal frames are removed from the scraper conveyor overlay region corresponding to the current frame to obtain the intermediate scraper conveyor region. At the same time, the scraper conveyor regions corresponding to the expected addition frames are added to the intermediate scraper conveyor region to obtain the scraper conveyor overlay region corresponding to the target frame image.

[0035] The specific process is as follows: Let the current frame be the nth frame, and the scraper area in the current frame be M. n The historical scraper conveyor superposition area is U. n-1 The current frame scraper machine overlay area is U. n Assuming the initial preset frame count is N, it can be understood as the maximum number of frames to be stacked. When n ≤ N, it means that the current number of frames being processed has not yet reached the maximum number of frames to be stacked. In this case, the scraper region M of the current frame is directly... n Add to historical scraper conveyor stacking area U n-1 In, i.e., Un =U n-1 ∪{M n When n>N, and the target frame differs from the current frame by one frame, the expected number of frames to be removed and the expected number of frames to be added are both one. Specifically, the expected frame to be removed is the earliest frame in the scraper machine overlay area list of the current frame, and the expected frame to be added is the next frame after the current frame, which is the target frame. To ensure that the length of the historical scraper machine overlay area list does not exceed the first preset number of frames, the scraper machine area M corresponding to the earliest frame needs to be removed. n-N+1 Then, the scraper machine area M corresponding to the target frame. n+1 Add to list, that is, U n+1 =(U n \{M n-N+1})∪{M n+1 By using this multi-frame overlay method, the actual area of ​​the scraper conveyor can be depicted more comprehensively and accurately, effectively reducing interference caused by accidental factors such as personnel obstruction.

[0036] S104: Based on the preset torso region of the person in the target frame image and the superimposed region of the scraper machine, obtain the intrusion status marker value corresponding to the target frame image.

[0037] In one embodiment, an intrusion status marker value corresponding to the target frame image can be obtained by comparing the preset torso region of a person in the target frame image with the superimposed region of the scraper machine. This intrusion status marker value reflects the likelihood of a user intruding into a preset area.

[0038] In one embodiment, when determining the intrusion status flag value, the intersection-over-union ratio (IoU) of the preset torso region of the person in the target frame image and the overlapping region of the scraper machine is first calculated. The IoU reflects the degree of overlap between the person's foot region and the scraper machine overlapping region. If the IoU is large, it indicates that the overlap between the person's foot region and the scraper machine region is high, and the person in that frame is more likely to have intruded into the scraper machine region. If the IoU is small, it indicates that the overlap between the person's foot region and the scraper machine region is low, and the person in that frame is less likely to have intruded into the scraper machine region.

[0039] Specifically, when calculating the crossover-union ratio, let the target frame be the nth frame, and the target frame scraper overlay area be H. n The area of ​​the person's feet corresponding to the target frame is represented as P. n Then, in calculating the Intersection over Union (IoU) of the target frame... n When, the calculation formula is IoU n =P n ∪U n / P n ∩U n .

[0040] In one embodiment, after calculating the Intersection over Union (IoU), the IoU of the target frame can be compared with a preset IoU threshold. n >T IoU If the (preset intersection-overlap threshold) indicates that the overlap between the personnel's foot area and the scraper machine area exceeds the system's preset range, then it is determined that the personnel in this frame are suspected of intruding into the scraper machine area, and the intrusion status flag value S of this frame is set. n Set to the first preset value (e.g., set to 1); otherwise, S n If we set it to the second preset value (e.g., 0), then in the above case, it can be expressed by the formula: S n ={1,IoU n >T IoU ;0,IoU n ≤T IoU In addition to using the preset value as the intrusion status flag value corresponding to the intersection-union ratio (IURR), the IURR value can also be directly used as the intrusion status flag value.

[0041] These two judgment methods based on cross-union ratio can quantify the positional relationship between the person's feet and the scraper machine area, providing a clear single-frame basis for subsequent multi-frame judgments.

[0042] S105: Determine whether a person has entered the scraper conveyor operating area by using the intrusion status marker value corresponding to each image within the second preset frame number.

[0043] To avoid potential misjudgments in single-frame analysis, the system will determine whether personnel have entered the scraper conveyor's operating area based on the intrusion status flag values ​​of each image within the second preset number of frames preceding the judgment time.

[0044] In one embodiment, the sum of the intrusion status marker values ​​corresponding to each image within a second preset frame number can be determined. If the ratio of the sum of the intrusion status marker values ​​to the second preset frame number is higher than a preset ratio, it is considered that a person has intruded into the scraper machine operating area.

[0045] Specifically, at this point, a queue Q of length K can be maintained. n Queue Q is used to store intrusion status flags for K consecutive frames. When n ≤ K, queue Q... n What is stored is the intrusion status flag from frame 1 to frame n, i.e., Q. n =[S1,…,S n When n>K, queue Q n It will be updated to store the intrusion status flag from frame n-K+1 to frame n, i.e., Q. n =[S n-K+1 ,…,S nThis queue update mechanism ensures that statistical analysis is always performed on the latest consecutive K frames.

[0046] Next, calculate the sum T of all intrusion status flags in the queue. n The calculation formula is:

[0047]

[0048] T n This reflects the total number of frames in a consecutive K-frame sequence where a person is suspected of intruding. Then, the intrusion rate R is calculated. n The formula is R n =T n / K represents the proportion of frames out of the total number of frames where a person is suspected of intruding within a consecutive K frames. If R n >R tg (Preset ratio) indicates that in consecutive K frames, the situation of suspected personnel intrusion is relatively frequent and exceeds the threshold set by the system. At this time, it is determined that there are indeed personnel who have intruded into the scraper conveyor operating area.

[0049] In one embodiment, after determining that personnel have entered the scraper conveyor's operating area, the current alarm count status can be plotted on the marked image to visually display the statistics of personnel intrusion status across multiple consecutive frames, facilitating real-time monitoring of abnormal situations by monitoring personnel. When an alarm is triggered, a corresponding preset warning method can be determined based on the ratio of the sum of the intrusion status marker values ​​to the second preset frame number, such as immediately issuing an audible and visual alarm signal to attract the attention of on-site personnel and monitoring personnel. Simultaneously, video frames from t1 seconds before the alarm and t2 seconds after the alarm (the number of cached frames is calculated as f×t1 and f×t2 based on the frame rate f) are cached. These cached video frames can provide detailed process records for subsequent accident analysis. Furthermore, the current alarm image can be saved as visual evidence of the personnel intrusion event.

[0050] It is understandable that the preset frame count mentioned above can refer to consecutive frames or frames at intervals of a certain number of frames. Taking a three-frame interval as an example, if the preset frame count is 5 frames and the target frame is the nth frame, then the preset frame counts before the target frame are the n-4th, n-8th, n-12th, n-16th, and n-20th frames, respectively.

[0051] In one embodiment, during the above calculation process, collaborative data processing can be performed based on multiple pre-deployed computing nodes. These computing nodes work together to improve the efficiency and speed of data processing, and the computing nodes communicate and share data with each other through a network.

[0052] This application offers the following technical advantages: Compared to traditional scraper conveyor personnel monitoring relying on manual inspections and simple physical protection, where manual inspections are time-sensitive and prone to oversights, and physical protections are insufficient to prevent unauthorized entry and lack real-time feedback, this application utilizes a multi-frame region overlay algorithm to fuse multi-frame information, accurately delineating the scraper conveyor area, avoiding occlusion-related misjudgments, and improving recognition accuracy. Furthermore, the personnel intrusion judgment combines intersection-union calculations with multi-frame statistics, reducing the false judgment rate and making the judgment more reliable.

[0053] Theoretically, the intrusion monitoring in this application is more real-time and efficient. The target detection module, based on the YOLO algorithm, can quickly identify targets and perform real-time data analysis. Once an intrusion is detected, an alarm can be triggered immediately, allowing staff to respond promptly and reducing accident casualties and property damage.

[0054] To verify the effectiveness, this application conducted a series of experiments using data from a scraper conveyor in the field, simulating complex scenarios such as personnel obstruction, sudden changes in lighting, and dust interference, while ensuring consistent conditions using the same equipment. The results show that the traditional method has a false alarm rate as high as 54% due to personnel obstruction, while the proposed solution, with its multi-frame region overlay algorithm, has a false alarm rate of only 5%. Under conditions of sudden changes in lighting and dust interference, the traditional method has a false alarm rate of 37%, while the proposed solution, through its multi-frame intrusion status statistical judgment mechanism, achieves a false alarm rate as low as 6%. The data strongly demonstrates the significant advantages of the proposed solution in terms of accuracy and reliability, providing a more reliable safety guarantee for the scraper conveyor area.

[0055] like Figure 2 As shown in the illustration, this application also provides a personnel intrusion monitoring device for the operating area of ​​a scraper conveyor, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0056] An image dataset within a preset area is acquired at a fixed frame rate. The image dataset is then identified to determine the scraper machine area and the preset torso area of ​​a person corresponding to each image. The scraper machine areas corresponding to each frame within a first preset number of frames before the target frame are superimposed to obtain the scraper machine superimposed area corresponding to the target frame image. Based on the preset torso area of ​​the person in the target frame image and the scraper machine superimposed area, an intrusion status marker value corresponding to the target frame image is obtained. The intrusion status marker values ​​corresponding to each image within a second preset number of frames are used to determine whether a person has intruded into the scraper machine operating area.

[0057] like Figure 3 As shown in the illustration, this application embodiment also provides a personnel intrusion monitoring device for the operating area of ​​a scraper conveyor, comprising:

[0058] The image acquisition module 301 acquires an image dataset within a preset area at a fixed frame rate.

[0059] The image recognition module 302 identifies the scraper machine area and the preset torso area of ​​the personnel corresponding to each image by recognizing the image dataset.

[0060] The region overlay module 303 overlays the scraper machine regions corresponding to each frame image within a first preset number of frames before the target frame to obtain the scraper machine overlay region corresponding to the target frame image.

[0061] The status marking module 304 obtains the intrusion status mark value corresponding to the target frame image based on the preset torso region of the person in the target frame image and the superimposed region of the scraper machine.

[0062] The event determination module 305 determines whether a person has entered the scraper conveyor operating area by using the intrusion status marker value corresponding to each image within the second preset frame number.

[0063] This application embodiment also provides a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows:

[0064] An image dataset within a preset area is acquired at a fixed frame rate. The image dataset is then identified to determine the scraper machine area and the preset torso area of ​​a person corresponding to each image. The scraper machine areas corresponding to each frame within a first preset number of frames before the target frame are superimposed to obtain the scraper machine superimposed area corresponding to the target frame image. Based on the preset torso area of ​​the person in the target frame image and the scraper machine superimposed area, an intrusion status marker value corresponding to the target frame image is obtained. The intrusion status marker values ​​corresponding to each image within a second preset number of frames are used to determine whether a person has intruded into the scraper machine operating area.

[0065] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the description of the method embodiments.

[0066] The devices and media provided in this application are one-to-one with the methods. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0067] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0068] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0069] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0070] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0071] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0072] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0073] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0074] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0075] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A method for monitoring unauthorized entry into the operating area of ​​a scraper conveyor, characterized in that, include: Acquire image datasets within a preset area at a fixed frame rate; By identifying the image dataset, the scraper machine area and the preset torso area of ​​the personnel corresponding to each image can be determined; The scraper machine regions corresponding to each frame image within the first preset number of frames before the target frame are superimposed to obtain the scraper machine superimposed region corresponding to the target frame image. Based on the preset torso region of the person in the target frame image and the superimposed region of the scraper machine, the intrusion status marker value corresponding to the target frame image is obtained; By using the intrusion status marker value corresponding to each image within the second preset frame number, it is determined whether a person has intruded into the scraper conveyor operating area. The torso area of ​​the personnel is pre-defined as the foot area; By identifying the image dataset, a preset torso region corresponding to each image is determined, specifically including: By identifying the image dataset, the bounding boxes of the personnel regions corresponding to each image are determined; The lower boundary of the personnel area boundary frame is used as the center line of the foot area; Multiply the height of the personnel area boundary frame by a preset ratio to obtain the height of the foot area boundary frame; The width of the personnel area bounding box is used as the width of the foot area bounding box; Based on the height and width of the bounding box of the foot region, the foot region corresponding to each image is determined; The step of superimposing the scraper machine regions corresponding to each frame image within a first preset number of frames before the target frame to obtain the scraper machine superimposed region corresponding to the target frame image specifically includes: Determine the first preset frame number and the scraper conveyor overlay area corresponding to the current frame; Determine the frame number difference between the current frame and the target frame; The expected frames to be removed and the expected frames to be added are determined by the difference between the first preset frame number and the frame number. Remove the scraper machine regions corresponding to the expected removal frames from the scraper machine overlay region corresponding to the current frame to obtain the intermediate scraper machine region; The scraper machine regions corresponding to the expected added frames are added to the intermediate scraper machine region to obtain the scraper machine overlay region corresponding to the target frame image; The method of obtaining the intrusion status marker value corresponding to the target frame image based on the preset torso region of the person and the superimposed region of the scraper machine in the target frame image specifically includes: Calculate the intersection-over-union ratio (IoU) between the preset torso region of the person in the target frame image and the superimposed region of the scraper machine; Based on the intersection-over-union ratio, the intrusion status marker value corresponding to the target frame image is determined; The crossover ratio reflects the degree of overlap between the personnel's foot area and the scraper machine's superimposed area.

2. The method according to claim 1, characterized in that, The step of determining the intrusion status marker value corresponding to the target frame image based on the intersection-over-union ratio specifically includes: If the cross-union ratio is higher than the preset cross-union ratio threshold, then the first preset value is used as the intrusion status marker value corresponding to the target frame image; If the cross-union ratio is not higher than the preset cross-union ratio threshold, then the second preset value is used as the intrusion status marker value corresponding to the target frame image.

3. The method according to claim 1, characterized in that, The step of determining the intrusion status marker value corresponding to the target frame image based on the intersection-over-union ratio specifically includes: The cross-union ratio is used as the intrusion status marker value corresponding to the target frame image.

4. The method according to claim 1, characterized in that, The step of determining whether a person has entered the scraper conveyor operating area by using the intrusion status marker values ​​corresponding to each image within a second preset frame number specifically includes: Determine the sum of the intrusion status flag values ​​corresponding to each image within the second preset frame number; If the ratio of the sum of the intrusion status flag values ​​to the second preset frame number is higher than the preset ratio, then a person has intruded into the scraper conveyor operating area.

5. The method according to claim 4, characterized in that, After determining whether a person has entered the scraper conveyor operating area by using the intrusion status marker values ​​corresponding to each image within a second preset frame number, the method further includes: It has been confirmed that someone has entered the scraper conveyor's operating area; Based on the ratio of the sum of the intrusion status flag values ​​to the second preset frame number, a corresponding preset warning method is determined; The warning is issued according to the preset warning method, and video frames within the third preset alarm time period before and after the warning time are cached.

6. A personnel intrusion monitoring device for a scraper conveyor operating area, implemented using the personnel intrusion monitoring method for a scraper conveyor operating area as described in claim 1, characterized in that, include: At least one processor; And, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform: Acquire image datasets within a preset area at a fixed frame rate; By identifying the image dataset, the scraper machine area and the preset torso area of ​​the personnel corresponding to each image can be determined; The scraper machine regions corresponding to each frame image within the first preset number of frames before the target frame are superimposed to obtain the scraper machine superimposed region corresponding to the target frame image. Based on the preset torso region of the person in the target frame image and the superimposed region of the scraper machine, the intrusion status marker value corresponding to the target frame image is obtained; By using the intrusion status marker values ​​corresponding to each image within the second preset frame number, it can be determined whether a person has intruded into the scraper conveyor's operating area.

7. A non-volatile computer storage medium, implemented using the personnel intrusion monitoring method for the operating area of ​​a scraper conveyor as described in claim 1, storing computer-executable instructions, characterized in that... The computer-executable instructions are set as follows: Acquire image datasets within a preset area at a fixed frame rate; By identifying the image dataset, the scraper machine area and the preset torso area of ​​the personnel corresponding to each image can be determined; The scraper machine regions corresponding to each frame image within the first preset number of frames before the target frame are superimposed to obtain the scraper machine superimposed region corresponding to the target frame image. Based on the preset torso region of the person in the target frame image and the superimposed region of the scraper machine, the intrusion status marker value corresponding to the target frame image is obtained; By using the intrusion status marker values ​​corresponding to each image within the second preset frame number, it can be determined whether a person has intruded into the scraper conveyor's operating area.

Images