A material detection method, system, medium and product for a material deposit area

Abstract

The application provides a material detection method and system for a material stacking area, a medium and a product, and relates to the technical field of image equipment. First, a monitoring image of a test paper storage area is collected and subjected to differential definition processing. This operation makes the test paper bag area stand out in the image because the definition is higher than that of the non-test paper bag area, and the definition of different parts inside the test paper bag is also distinguished. The test paper bag outline is the highest because the distinction of the test paper bag and the distinction of the boundary need to be increased. Then, the test paper bag outline is sampled at different resolutions according to the structural complexity. The resolution of the simple structure area is increased to capture the outline more finely, and the resolution of the complex area is reduced to reduce resource consumption and interference because the distinction is already obvious. The two are mutually coordinated to optimize the acquisition of outline information and reduce the risk of missed detection and false detection.

Description

Technical Field

[0001] This application relates to the field of image equipment technology, and in particular to a material detection method, system, medium, and product for a material stacking area. Background Technology

[0002] In the education sector, mass-printed products like test papers and exercise books have specific distribution requirements. They need to be packaged according to various factors such as different regions, schools, and specific classes to ensure accurate supply to the corresponding usage scenarios. For example, primary schools of different sizes have different numbers of classes, and the number of students in each class varies. For instance, Primary School A has a total of 4 classes: A1 with 28 students, A2 with 32 students, A3 with 31 students, and A4 with 25 students. Primary School B has a total of 3 classes: B1 with 22 students, B2 with 32 students, and B3 with 28 students. Moreover, these test papers often need to be sealed and transported to designated locations such as examination venues. Therefore, after printing, they must be strictly sealed and packaged according to the class situation for transportation. The packaged and verified test paper bags and test papers are stored in designated areas, and the detection system monitors the materials in the designated areas in real time to prevent the loss or omission of the verified test paper bags.

[0003] However, in the process of detecting these test paper bags, the use of uniformly sized kraft paper for packaging all the test papers presents the following technical difficulties: 1) There is a lack of significant visual differences between the test paper bags. The use of the same kraft paper material makes all the test paper bags appear uniformly beige, and the identical packaging specifications result in the test paper bags having almost identical volume and shape, making it difficult for image recognition systems to extract reliable distinguishing information from appearance features; 2) When multiple batches of test papers are stacked, the boundaries between the test paper bags become blurred. Coupled with the interference of lighting and shadows, the image segmentation algorithm based on contour detection performs poorly and cannot accurately define the spatial range of each test paper bag. These problems prevent the relevant image recognition technology from accurately identifying batches of test papers, posing a risk of missed detections and false detections. In educational examinations, where the tolerance for missed detections and false detections is relatively high, the impact is more pronounced. Summary of the Invention

[0004] This application provides a material detection method, system, medium, and product for material storage areas to reduce the risk of missed detections and false detections.

[0005] Firstly, this application provides a material detection method for a material stacking area, comprising: acquiring monitoring images of a test paper storage area, and performing differential clarity processing on the monitoring images to obtain a feature map sequence, wherein the image clarity of the test paper bag area is higher than that of the non-test paper bag area, and within the test paper bag area, the clarity of the test paper bag outline, other areas, and the test paper bag body area decreases sequentially; increasing the resolution sampling for areas with simple test paper bag outline structures and decreasing the resolution sampling for areas with complex test paper bag outline structures; and, when a change in the position of a test paper bag is detected, performing spatial registration calculation between the feature map sequence from before the last position change to the current moment and a dynamic reference model to obtain the position of different test paper bags. The process involves: 1) Displacement measurement; 2) Establishing a three-dimensional spatial mapping of the initial stacking state of the test papers upon entry into the storage area using a dynamic baseline model; 3) Determining the target test paper bags to be reduced or increased based on their displacement; 4) Collecting interaction data between personnel activity trajectories and the test paper bag area, and matching and analyzing this data with preset operating procedures; 5) Classifying the corresponding behavior as a normal event when the interaction data conforms to the preset operating procedures; 6) Classifying the corresponding behavior as an abnormal event when the interaction data does not conform to the preset operating procedures; 7) Judging the target test paper bag corresponding to the normal event against the preset operating procedures; 8) Changing the corresponding normal event to an abnormal event when the test paper bag specified in the preset operating procedures does not correspond to the target test paper bag; and 9) Marking the abnormal events.

[0006] By adopting the above technical solution, the first step is to acquire monitoring images of the test paper storage area and perform differential clarity processing. This operation makes the test paper bag area stand out in the image because its clarity is higher than that of non-test paper bag areas. Furthermore, the clarity of different parts within the test paper bag is also differentiated, with the test paper bag outline having the highest clarity. This is because it is necessary to increase the distinguishability of the test paper bags and their boundaries. Simultaneously, the test paper bag outlines are sampled at different resolutions according to their structural complexity. In simple structural areas, higher resolution allows for more precise outline capture, while in complex areas, where the distinctions are already obvious, lower resolution reduces resource consumption and interference. These two approaches work together to optimize outline information acquisition. Then, a dynamic benchmark model is used for spatial registration to calculate displacement. Based on the three-dimensional spatial mapping of the initial state of the test papers upon entering the storage area, the current positional changes of the test paper bags are accurately compared. Finally, a series of rigorous judgment steps are used to determine the target test paper bag, overcoming problems such as similar appearance and blurred boundaries of test paper bags. Ultimately, this effectively improves the ability to accurately identify batches of test papers and reduces the risk of missed and false detections.

[0007] In conjunction with some embodiments of the first aspect, in some embodiments, the step of determining the target test paper bag to be reduced or increased based on the displacement of the test paper bag specifically includes: determining the relative positional relationship between test paper bag areas; establishing the association strength of different test paper bag piles, wherein the association strength decreases as the spacing between test paper bag piles increases; the test paper bag pile is all test paper bags within the test paper bag area; determining the change in distance between the reduced or increased test paper bag in the test paper bag pile and its corresponding test paper bag pile; determining a group behavior consistency index based on all the change amounts; if the change in distance between the reduced or increased test paper bag in the test paper bag pile and its corresponding test paper bag pile is greater than a preset threshold and deviates from the corresponding group behavior consistency index; it is determined as the target test paper bag.

[0008] By employing the aforementioned technical solution, the relative positional relationships between test paper bag areas are determined, clarifying the spatial layout of each test paper bag stack. Next, the correlation strength between different test paper bag stacks is established, with the correlation strength decreasing as the distance increases. This allows for the measurement of the closeness of the correlation between each test paper bag stack based on distance. Subsequently, the changes in distance between the test paper bags that are added or removed from the stack and their respective stacks are analyzed, and a comprehensive judgment is made in conjunction with group behavior consistency indicators. When a test paper bag stack shows an increase or decrease and meets the corresponding conditions, it is identified as a target test paper bag. A deeper consideration of the overall correlation and changes in the test paper bag stacks distinguishes between reasonable changes during normal handling and stacking, and batch confusion caused by genuine improper handling, thus improving the accuracy of determining whether test paper batches are abnormal.

[0009] In conjunction with some embodiments of the first aspect, in some embodiments, after the step of collecting the interaction data between the personnel activity trajectory and the test paper bag area, and matching and analyzing the interaction data with the preset operating procedures, the method further includes: obtaining the type identifier of the test paper bag, the type identifier being used to group the test paper bags together, the type identifier including one or more of school, class, and printed product subject information; grouping the personnel activity trajectories by the type identifier; randomly selecting two personnel activity trajectories in the same group and judging their similarity; if the similarity is lower than the similarity threshold, extracting avoidance behavior features from the later-time personnel activity trajectory; identifying the obstacle test paper bag corresponding to the avoidance behavior features; obtaining the first test paper bag corresponding to the earlier-time personnel activity trajectory and the second test paper bag corresponding to the later-time personnel activity trajectory; judging whether the obstacle test paper bag simultaneously meets the preset operating procedures, and handling it after the first test paper bag and before the second test paper bag; if not all meet the requirements, judging the corresponding behaviors of the obstacle test paper bag, the first test paper bag, and the second test paper bag as abnormal events.

[0010] By employing the above technical solution, the type identification of the test paper bags is first obtained, and the activity trajectories of the data collection personnel are grouped accordingly. This allows for the categorization of personnel operations related to the same type of test paper, facilitating targeted analysis. Within the same group of data collection personnel activity trajectories, two trajectories are randomly selected to assess their similarity. If the similarity is below a threshold, avoidance behavior features are extracted. These features are used to identify obstacle test paper bags. Furthermore, by combining test paper bags corresponding to different time sequences, the handling order is determined according to preset operating procedures to ensure compliance. From the perspective of personnel activity trajectories, this approach allows for in-depth analysis of potential errors in the distribution of test papers due to sequence discrepancies, identifying erroneous behaviors related to non-standard timing.

[0011] In conjunction with some embodiments of the first aspect, in some embodiments, the step of extracting avoidance behavior features from the activity trajectories of data collectors in later time sequences specifically includes: acquiring the position sequence and velocity sequence of two data collector activity trajectories respectively; calculating the curvature value corresponding to the position sequence of the two data collector activity trajectories; in the activity trajectories of data collectors in later time sequences, when the curvature value is greater than a first preset threshold and the corresponding velocity value is less than a second preset threshold, determining a candidate avoidance position; determining whether the activity trajectories of data collectors in earlier time sequences satisfy the condition that the curvature value is greater than the first preset threshold and the velocity value is less than the second preset threshold at the corresponding spatial position; if the condition is satisfied, determining the candidate avoidance position as an avoidance behavior feature.

[0012] By employing the above technical solution, position and velocity sequences of two personnel activity trajectories are obtained. The curvature value corresponding to the position sequence reflects the degree of curvature of the trajectory, while the velocity value reflects the speed of movement. By setting a threshold, candidate avoidance positions with large curvature and low velocity in the later trajectory are selected. These positions are then compared with the spatial position of the earlier trajectory, and the two are mutually verified to determine the avoidance behavior characteristics.

[0013] In conjunction with some embodiments of the first aspect, in some embodiments, the step of identifying the obstacle test paper bag corresponding to the avoidance behavior feature specifically includes: constructing a search area based on the avoidance behavior feature; determining the target area closest to the search area in a preset operating procedure; and identifying the test paper bag corresponding to the target area as the obstacle test paper bag.

[0014] By employing the above technical solution, a search area is constructed based on the identified avoidance behavior characteristics. Then, according to preset operating procedures, the nearest target area is determined, thereby identifying the corresponding test paper bag as the obstacle test paper bag. Starting from personnel avoidance behavior, the system accurately associates with obstacle test paper bags that may affect the operating process.

[0015] In conjunction with some embodiments of the first aspect, in some embodiments, the step of performing differential sharpness processing on the monitoring image to obtain a feature map sequence specifically includes: extracting the boundary of the test paper bag in the monitoring image to obtain a preliminary test paper bag outline; determining whether the preliminary test paper bag outline meets the requirements of a simple region; if it does, constructing a multi-scale feature pyramid, extracting features at different scales from the test paper bag outline to obtain local fine features; and fusing the local fine features with the preliminary test paper bag outline to obtain the test paper bag outline structure.

[0016] By employing the above technical solution, the boundaries of the exam paper bags in the monitoring image are first extracted to obtain a preliminary outline. After determining whether it meets the requirements for a simple region, a multi-scale feature pyramid is constructed for those that do, extracting features at different scales. These features are then fused to obtain a more complete outline structure for the exam paper bags. Through this multi-step feature extraction and fusion, the presentation effect of the exam paper bag outline can be enhanced, key features can be highlighted, and the recognition difficulties caused by similar appearances of exam paper bags in the image can be overcome, thus better assisting in the accurate analysis and judgment of the exam paper bags in subsequent steps.

[0017] In conjunction with some embodiments of the first aspect, in some embodiments, after the step of marking the abnormal event, the method further includes: associating the corresponding batch identification information and recording the operator's identity information, operation timestamp, and spatial location coordinates.

[0018] By adopting the above technical solution, after marking abnormal events, corresponding batch identification information is associated, and the operator's identity, operation timestamp, and spatial location coordinates are recorded. This comprehensively preserves detailed background information of abnormal events, facilitating subsequent tracing of the root cause of the abnormality and accurate review of the event process.

[0019] Secondly, this application provides a material detection system for a material storage area, the material detection system for the material storage area comprising: one or more processors and a memory; the memory is coupled to one or more processors, the memory is used to store computer program code, the computer program code including computer instructions, and the one or more processors invoke the computer instructions to cause the material detection system for the material storage area to perform the method described in the first aspect and any possible implementation thereof.

[0020] Thirdly, this application provides a computer program product containing instructions that, when the computer program product is run on a material detection system in a material storage area, cause the material detection system in the material storage area to perform the method described in the first aspect and any possible implementation thereof.

[0021] Fourthly, this application provides a computer-readable storage medium including instructions that, when executed on a material detection system in a material storage area, cause the material detection system in the material storage area to perform the method described in the first aspect and any possible implementation thereof.

[0022] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0023] 1. First, monitoring images of the exam paper storage area are acquired and processed for differential clarity. This operation makes the exam paper bag area stand out in the image because its clarity is higher than that of non-exam paper bag areas. The clarity of different parts within the exam paper bag is also differentiated, with the exam paper bag outline having the highest clarity. This is because it's necessary to increase the distinguishability of the exam paper bags and their boundaries. Simultaneously, different resolutions are used to sample the exam paper bag outlines according to their structural complexity. In simple areas, higher resolution allows for more precise outline capture, while in complex areas, where the differences are already obvious, lower resolution reduces resource consumption and interference. These two methods work together to optimize outline information acquisition. Then, a dynamic benchmark model is used for spatial registration to calculate displacement. Based on the 3D spatial mapping of the initial state of the exam papers upon entering the storage, the current positional changes of the exam paper bags are accurately compared. A series of rigorous judgment steps are then used to determine the target exam paper bag, overcoming problems such as similar appearance and blurred boundaries. Ultimately, this effectively improves the ability to accurately identify exam paper batches and reduces the risk of missed and false detections.

[0024] 2. Determine the relative positions of the test paper bag areas to clarify the spatial layout of each test paper bag stack. Next, establish the correlation strength between different test paper bag stacks, noting that the correlation strength decreases with increasing spacing. This allows us to measure the closeness of the correlation between each test paper bag stack based on distance. Then, analyze the changes in distance between the test paper bags added or removed from the stack and their respective stacks, combining this with group behavior consistency indicators for a comprehensive judgment. When a test paper bag stack shows increases or decreases and meets certain conditions, it is identified as a target test paper bag. By deeply considering the overall correlation and changes in the test paper bag stacks, we can distinguish between reasonable changes during normal handling and stacking and batch confusion caused by improper handling, thus improving the accuracy of determining whether test paper batches are abnormal.

[0025] 3. First, obtain the type identifier of the test paper bag. This allows for grouping the activity trajectories of the data collection personnel. Grouping personnel actions related to the same type of test paper facilitates targeted analysis. Within the same group of personnel activity trajectories, randomly select two trajectories to assess similarity. If the similarity is below a threshold, extract avoidance behavior features. Use these features to identify obstacle test paper bags. Then, combine this with test paper bags from different time sequences to determine if the handling order is compliant with pre-defined operating procedures. By focusing on personnel activity trajectories, we can delve deeper into potential errors in the test paper distribution process due to sequence discrepancies, identifying any non-compliant behaviors related to timing. Attached Figure Description

[0026] Figure 1 This is a flowchart illustrating a material detection method for a material storage area in an embodiment of this application.

[0027] Figure 2 This is another schematic flowchart of the material detection method in the material stacking area in the embodiments of this application;

[0028] Figure 3 This is another schematic flowchart of the material detection method in the material stacking area in the embodiments of this application;

[0029] Figure 4 This is an exemplary hardware structure diagram of a material detection system for a material stacking area in an embodiment of this application. Detailed Implementation

[0030] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to and includes any or all possible combinations of one or more of the listed items.

[0031] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0032] Please see Figure 1 , Figure 1 This is a flowchart illustrating a material detection method for a material storage area in an embodiment of this application.

[0033] S101. Collect monitoring images of the test paper storage area and perform differential clarity processing on the monitoring images to obtain a feature map sequence. The image clarity of the test paper bag area is higher than that of the non-test paper bag area. Within the test paper bag area, the clarity of the test paper bag outline, other areas, and the test paper bag body area decreases in that order. Increase the resolution sampling for areas with simple test paper bag outline structure and decrease the resolution sampling for areas with complex test paper bag outline structure.

[0034] The "exam paper bag area" refers to the portion of the image containing the exam papers, and is the primary focus of analysis. The "non-exam paper bag area" refers to all areas excluding the exam paper bag area. The exam paper bag outline, i.e., the outer edge shape and lines of the exam paper bag in the image, is crucial for subsequent recognition due to its sharpness. "Other areas" refers to the surrounding image areas excluding the exam paper bag and its internal components. The exam paper bag body area is the image area corresponding to the main internal portion of the exam paper bag, excluding the outline.

[0035] Specifically, the process begins by using cameras to capture surveillance images of the area where the test papers are stored, and then image algorithms are used to process the captured surveillance images for differentiating clarity.

[0036] During processing, the image sharpness of the exam paper bag area is prioritized to be higher than that of non-exam paper bag areas. Within the exam paper bag area, the sharpness is further refined to maximize the clarity of the exam paper bag outline, as a clear outline helps in accurately distinguishing different exam paper bags. Next, other areas are processed, as they are used to determine whether interactive behavior exists. Finally, the exam paper bag body area is processed. Then, based on the exam paper bag outline, its structure is assessed for simplicity or complexity. For simple areas, the resolution sampling is increased to capture outline details more precisely; while for complex areas, where the outline features are relatively obvious, the resolution sampling is reduced to minimize resource consumption and avoid excessive interference. The final result is a feature map sequence, providing a valuable image data foundation for subsequent steps.

[0037] In some specific embodiments, image recognition algorithms are used to analyze the acquired monitoring images and locate the test paper bags within the images. Then, based on a preset specific range, the identified test paper bags are completely framed within this range. This framed area is thus defined as the test paper bag region, while the remaining portion of the monitoring image excluding the test paper bag region naturally belongs to the non-test paper bag region. Next, for the identified test paper bag region, image recognition algorithms are used again to further identify the outline of the test paper bag. The portion enclosed by the test paper bag outline is clearly defined as the test paper bag body region. Correspondingly, other parts within the test paper bag region besides the test paper bag body region are identified as other regions. After accurately dividing the above regions, according to preset requirements—that is, ensuring the image clarity of the test paper bag region is higher than that of the non-test paper bag regions, and within the test paper bag region, ensuring the clarity of the test paper bag outline is higher than that of the test paper bag body region, and the clarity of the test paper bag body region is higher than that of other regions—differential clarity processing is applied to different regions using appropriate image processing techniques. No restrictions are imposed here.

[0038] In some specific embodiments, the curvature changes of the contour curve are calculated, and the number of points with frequent curvature changes (i.e., large fluctuations in curvature values ​​multiple times over a short distance) and the number of times curvature abruptly changes (e.g., from a smooth curve to a sharp bend) are counted. If these statistical values ​​are below a set threshold (which can be determined by testing and analyzing a large number of samples), the shape is considered regular and the structure is judged to be simple; if they exceed the threshold, the structure is judged to be complex. In other embodiments, parameters are selected according to the curvature changes, with the curvature changes being inversely proportional to the parameters. The parameters are used to limit sharpness and are directly proportional to sharpness.

[0039] In some specific embodiments, since the exam paper bags are stacked together, a segmentation operation is performed on the outline of the exam paper bags to rationally divide the outline. Viewed from a lateral perspective, the outline of the exam paper bags presents several relatively uniform shapes, mostly rectangular. When attempting to approximate the outline of the exam paper bags using basic geometric shapes, if only a few rectangles are needed to fit it relatively accurately, it means that the structure of the exam paper bag outline is relatively simple. However, if a large number of rectangles are required, or even a combination of other geometric shapes, to approximate the outline, it indicates that the structure of the exam paper bag outline is relatively complex. This suggests that the outline has many concave and convex features, bends, and irregular variations, and that the stacking is uneven. Simultaneously, corresponding parameters are obtained based on the number of rectangles or other geometric shapes used, and the curvature of the outline and the parameters show an inverse relationship. The parameters are used to limit sharpness and are directly proportional to sharpness.

[0040] In some specific embodiments, for areas with simple outline structures in the test paper bag, the specific features include:

[0041] S1011. Extract the boundary of the test paper bag in the monitoring image to obtain a preliminary outline of the test paper bag;

[0042] S1012. Determine whether the outline of the preliminary test paper bag meets the requirements of a simple area;

[0043] S1013. If the conditions are met, construct a multi-scale feature pyramid, extract features from the outline of the test paper bag at different scales, and obtain local fine features.

[0044] S1014. The local fine features are fused with the preliminary test paper bag outline to obtain the test paper bag outline structure.

[0045] As can be seen, the initial outline of the exam paper bags in the monitoring image is obtained by first extracting their boundaries. After determining whether it meets the requirements of a simple region, a multi-scale feature pyramid is constructed for those that do meet the requirements to extract features at different scales. These features are then fused to obtain a more complete outline structure of the exam paper bags. Through this multi-step feature extraction and fusion, the presentation effect of the exam paper bag outline can be enhanced, key features can be highlighted, and the recognition difficulties caused by similar appearances of exam paper bags in the image can be overcome, thus better assisting in the accurate analysis and judgment of the exam paper bags in subsequent steps.

[0046] S102. When a change in the position of the test paper bag is detected, the feature map sequence from before the last position change to the current time is spatially registered with the dynamic benchmark model to obtain the displacement of different test paper bags; the dynamic benchmark model is a three-dimensional spatial mapping established for the initial stacking state of the test papers when they are put into storage.

[0047] Specifically, in scenarios where the test paper storage area is continuously monitored and image analysis detects changes in the position of the test paper bags, the feature map sequence from before the last position change to the current moment is used as the data to be analyzed. This sequence is then spatially registered with a pre-built dynamic benchmark model. This dynamic benchmark model is based on the initial stacking state of the test papers upon entry into the warehouse, and uses 3D modeling and other technologies to record in detail the initial spatial position of each test paper bag and their layout relationships. During the spatial registration calculation, image spatial transformation algorithms are used to accurately match and align the images of each test paper bag in the feature map sequence with the corresponding initial state in the dynamic benchmark model. After a series of complex coordinate transformations and similarity calculations, the displacement of different test paper bags relative to their initial state is finally obtained, providing a basis for subsequent judgments regarding the addition or removal of test paper bags.

[0048] In some embodiments, key feature points of each test paper bag image in the feature map sequence are first extracted, such as contour corners and specific marker positions, and the corresponding initial feature points are also marked in the dynamic benchmark model. In the second step, a feature point matching algorithm, such as SIFT (Scale Invariant Feature Transform) algorithm, is used to find the corresponding feature point pairs in the feature map sequence and the dynamic benchmark model. In the third step, based on the successfully matched feature point pairs, the spatial coordinate changes of each test paper bag image relative to the initial state are determined by calculation methods such as least squares, and then the displacement is obtained, which is not limited here.

[0049] S103. Determine the target number of test paper bags to be reduced or increased based on the displacement of the test paper bags.

[0050] In some embodiments, different displacement thresholds are set, the displacement of each test paper bag is compared with the threshold, and test papers with displacement exceeding the threshold are selected and identified as target test paper bags.

[0051] S104. Collect the interaction data between personnel activity trajectory and test paper bag area, and match and analyze the interaction data with the preset operating procedures;

[0052] The personnel activity trajectory refers to the movement route records left by relevant staff when performing various operations within the test paper storage area. This data is typically obtained through positioning devices, surveillance video analysis, etc., reflecting the personnel's activities. The interaction data in the test paper bag area refers to various data information generated during personnel's approach, contact, and handling of the test paper bag area, such as contact time and operation sequence. This data is crucial for analyzing whether operations are compliant. Pre-set operating procedures specify which personnel have the appropriate permissions and can interact with specific test paper bags, such as handling, viewing, and storing them. Other unauthorized personnel are prohibited from interacting with these bags, thereby ensuring the standardization, security, and confidentiality of test paper bag-related operations.

[0053] In some embodiments, a video surveillance system is used to analyze video footage using image recognition algorithms to extract interactive data such as the actions and dwell time of personnel in the test paper bag area; the preset operating procedures are compiled into a detailed table, clarifying the requirements for each operating step and its sequence; the extracted interactive data is compared one by one with the requirements in the table, either manually or with the help of data analysis software, to determine whether they match, and thus complete the analysis.

[0054] S105. When the interactive data conforms to the preset operating procedure, the corresponding behavior is judged as a normal event; when the interactive data does not conform to the preset operating procedure, the corresponding behavior is judged as an abnormal event.

[0055] Specifically, after comparison, if the personnel operational behaviors reflected in the interactive data, such as the order of operations, action specifications, and the test paper bags involved, all correspond one-to-one with the content specified in the preset operating procedures, and no violations of the rules are found, then the corresponding behaviors are judged as normal events. Conversely, if any operations are found to be inconsistent with the preset operating procedures during the comparison process, then the corresponding behaviors are judged as abnormal events, so that targeted measures can be taken subsequently, such as further investigation and correction of abnormal events.

[0056] S106. Determine the target test paper bag corresponding to the normal event against the preset work procedure;

[0057] The pre-set work procedures include the target test paper bags, quantities, and target areas that relevant personnel should store in a certain batch, which serve as an important reference for measuring whether the actual operation is fully compliant.

[0058] In some specific embodiments, key elements regarding the storage and retrieval of exam paper bags in the preset work procedures are identified, such as storage location requirements, target exam paper bags, quantity, and operator, forming a detailed comparison list. For each target exam paper bag corresponding to a normal event, its corresponding relevant information is extracted and organized into a data list in the same format. The two lists are compared item by item to check whether they are completely consistent. If they are completely consistent, it is determined that the requirements are met. If there are any discrepancies, it is determined that there may be a problem. This is not limited here.

[0059] S107. When the test paper bag specified in the preset work procedure does not correspond to the target test paper bag, change the corresponding normal event to an abnormal event.

[0060] Specifically, after comparing the target exam paper bags corresponding to normal events with the preset work procedures, if it is found that the exam paper bags specified in the preset work procedures do not correspond to the actual target exam paper bags—for example, the procedures require the storage of batch A exam paper bags, but the actual movement involves batch B exam paper bags—it indicates that the previously identified normal event may actually have a problem. The operation may superficially comply with some procedures, but there is a deviation in the key exam paper bag object. In this case, the corresponding normal event needs to be changed to an abnormal event so that this seemingly compliant but actually potentially risky operation can be thoroughly investigated and corrected to avoid adverse effects on exam paper management.

[0061] S108. Mark abnormal events.

[0062] In some embodiments, the method further includes: S109, associating the corresponding batch identification information and recording the operator's identity information, operation timestamp, and spatial location coordinates.

[0063] As can be seen, the process begins with acquiring monitoring images of the exam paper storage area and performing differential clarity processing. This operation makes the exam paper bag area stand out in the image because its clarity is higher than that of non-exam paper bag areas. Furthermore, the clarity of different parts within the exam paper bag is also differentiated, with the exam paper bag outline having the highest clarity. This is because it's necessary to increase the distinguishability of the exam paper bags and their boundaries. Simultaneously, different resolutions are used to sample the exam paper bag outlines according to their structural complexity. Increasing the resolution in simple areas allows for more precise outline capture, while in complex areas where the differences are already obvious, the resolution is reduced to minimize resource consumption and interference. These two methods work together to optimize outline information acquisition. Then, a dynamic benchmark model is used for spatial registration to calculate displacement. Based on the three-dimensional spatial mapping of the initial state of the exam papers upon entering the storage area, the current positional changes of the exam paper bags are accurately compared. A series of rigorous judgment steps are then used to determine the target exam paper bag, overcoming problems such as similar appearance and blurred boundaries. Ultimately, this effectively improves the ability to accurately identify exam paper batches and reduces the risk of missed and false detections.

[0064] The above embodiments address the thorny issue of missed and false detection risks caused by the extremely low distinguishability and similar outlines between exam paper bags. However, in actual use, different batches of exam paper bags may be similar in appearance and specifications. Relying solely on the batch of the target exam paper bag for judgment may lead to misjudgment. It's possible that two batches of exam paper bags simply look very similar, causing visual confusion during normal handling and stacking, without any actual batch mixing. For example, two batches of exam paper bags from different schools but printed by the same examination institution may have very similar colors, sizes, and basic markings. If, during monitoring, a certain exam paper bag is found in "another batch," and "another batch" happens to have fewer exam paper bags, it's possible that the exam papers in that batch were just being moved out while new exam papers were being added, rather than actual improper handling causing it to be separated from the original batch. For example, it's also possible that a handling error caused it to be separated from the original batch. In summary, given two similar piles of exam papers, and the "reasonable changes" made (one pile increased, the other decreased), how can we distinguish between errors and normal handling?

[0065] Please see Figure 2 , Figure 2 This is another schematic flowchart of the material detection method in the material stacking area in the embodiments of this application;

[0066] In some specific embodiments, step S103 specifically includes:

[0067] S201. Determine the relative positional relationships between the test paper bag areas;

[0068] Relative positional relationship refers to the interrelationship between different test paper bag areas in terms of spatial orientation and distance. It is a reference comparison information used to describe the location of each test paper bag area. For example, test paper bag area A is 2 meters away from area B, which is a relative positional relationship.

[0069] In some embodiments, simply inputting the coordinate information corresponding to all test paper bag areas into the system one by one will allow the system to perform calculations based on these coordinate data using the corresponding spatial location analysis algorithm, thereby obtaining the specific relative positional relationship between each test paper bag area.

[0070] S202. Establish the correlation strength of different test paper bag stacks, wherein the correlation strength decreases as the spacing between test paper bag stacks increases; a test paper bag stack is all test paper bags within the test paper bag area.

[0071] Specifically, for each pair of test paper bag stacks, the correlation strength is established based on the distance between them. Stacks of test paper bags that are closer together are more likely to interfere with each other during handling and stacking, so the correlation strength is set relatively high. As the distance between them increases, the probability of mutual interference decreases, and the correlation strength weakens accordingly. This provides a basis for subsequently judging whether changes to the test paper bags are reasonable.

[0072] S203. Determine the change in distance between the reduced or increased test paper bags in the test paper bag stack and the stack to which they belong;

[0073] Specifically, the process begins by accurately identifying which stack of exam paper bags experienced a decrease or increase in quantity. The spatial location of these bags with changed quantities is then tracked. Combined with their initial positions within their respective stacks, a spatial distance calculation algorithm is used to calculate the change in distance between these bags and their stack. This process provides detailed data to support subsequent comprehensive assessments of the exam paper bag positions.

[0074] S204. Determine the group behavior consistency index based on all transformation quantities;

[0075] Among them, the group behavior consistency index is a quantitative indicator that comprehensively reflects whether the overall behavior of multiple test paper bags during the process of change conforms to normal rules and whether it has consistency. It takes into account many factors such as the positional changes of different test paper bags and the correlation of the test paper bag stacks. It is used to measure whether the changes of the entire test paper bag group are in a reasonable and normal state. For example, under normal handling operations, the changes of test paper bags in the same batch are often relatively synchronous and regular, and the group behavior consistency index will be higher, and vice versa.

[0076] In some embodiments, for each stack of exam paper bags, the similarity of their pairwise distance transformations is calculated. Methods such as Euclidean distance and cosine similarity can be used to measure this. A combined index of association strength and similarity is calculated. Based on the previously established association strength between stacks of exam paper bags, the similarity calculation result for each stack is assigned a corresponding weight. The higher the association strength, the greater the weight. Then, the weighted similarity results of all stacks of exam paper bags are summarized to obtain a group behavior consistency index.

[0077] S205. If the change in distance between a reduced or added test paper bag in the test paper bag pile and its corresponding test paper bag pile is greater than a preset threshold, and it deviates from the corresponding group behavior consistency index, it is determined as the target test paper bag.

[0078] Specifically, after determining the group behavior consistency index based on all changes, it is necessary to determine which changes in the test paper bags are truly abnormal according to the set standards. This step is then executed. The changes in the distance between the test paper bags that have decreased or increased in the stack and their respective stacks are compared with a preset threshold, while checking whether they deviate from the corresponding group behavior consistency index requirements. If the change in the distance of a particular test paper bag is greater than the preset threshold, it proves that it is not a temporary placement, and its change does not conform to the normal change pattern reflected by the group behavior consistency index. This indicates that the change in this test paper bag is likely not caused by normal handling or stacking operations, but by abnormal situations such as handling errors or misplacement. In this case, this test paper bag is identified as the target test paper bag.

[0079] It is evident that determining the relative positional relationships between the test paper bag areas clarifies the spatial layout of each test paper bag stack. Next, the correlation strength between different test paper bag stacks is established, with the correlation strength decreasing as the distance increases. This allows for the measurement of the closeness of the correlation between each test paper bag stack based on distance. Subsequently, the changes in distance between the test paper bags that are added or removed from the stack and their respective stacks are analyzed, and this is combined with group behavior consistency indicators for a comprehensive judgment. When a test paper bag stack shows an increase or decrease and meets certain conditions, it is identified as a target test paper bag. By deeply considering the overall correlation and changes in the test paper bag stacks, it is possible to distinguish between reasonable changes during normal handling and stacking, and batch confusion caused by genuine improper handling, thus improving the accuracy of judging whether there are abnormalities in test paper batches.

[0080] It should be noted that the above embodiments apply to scenarios where a pile of exam papers increases or decreases multiple times. For example, in a large educational examination paper reserve, there exists a pile specifically for storing college entrance examination papers for a particular subject. Because the examination arrangements for this subject differ in different examination areas, exam papers need to be frequently retrieved from this pile and sent to some examination areas. At the same time, newly printed spare exam papers are added, resulting in the number of exam paper bags in this pile decreasing or increasing multiple times.

[0081] The above embodiment addresses the thorny issue of missed and false detection risks arising from the extremely low distinguishability and similar outlines between exam paper bags. However, in actual use, even if the personnel collecting exam paper batch information are correct and the exam paper retrieval is perfectly accurate, shortcomings still exist in the specific scenario of monitoring exam paper batches in education examinations. This is because the subsequent exam paper distribution process follows a specific order. If everything else is accurate except for the distribution order, an error in the order itself can still pose a potential risk to the backend.

[0082] Please see Figure 3 , Figure 3 This is another schematic flowchart of the material detection method in the material stacking area in the embodiments of this application;

[0083] After step S104, the method further includes: S301, obtaining the type identifier of the test paper bag, the type identifier being used to group the test paper bags together, the type identifier including one or more of the following: school, class, and printed product subject information;

[0084] Among them, the type identification of the test paper bag refers to a mark information used to distinguish the belonging characteristics of different test paper bags. It refers to the relevant content that can reflect the unique attributes of the test paper bag and facilitate its classification and management. It is used to indicate the classification of test paper bags in certain key dimensions.

[0085] S302. Group the activity trajectories of the personnel being collected using type identifiers;

[0086] Specifically, based on the acquisition of the test paper bag type identification and the collection of personnel activity trajectories, in order to conduct in-depth analysis of the personnel operation related to different types of test paper bags and determine whether the operation complies with the specifications, all the collected personnel activity trajectories were first sorted out. Then, for each trajectory, the type identification of the test paper bag involved in the operation was checked. All personnel activity trajectories were classified according to the type identification of the test paper bag, so that subsequent analysis could focus on the personnel operation behavior related to the same type of test paper bag and more accurately identify possible anomalies.

[0087] It should be noted that there are many types of data for type identification; however, in actual operation, to facilitate analysis and make the grouping more organized, only one relevant data point is selected as the classification basis. The purpose is to make the activity trajectories comparable.

[0088] S303. From the activity trajectories of the same group of data collectors, randomly select two activity trajectories of data collectors and determine their similarity.

[0089] In some embodiments, numerical differentiation is used to calculate the curvature value at each position point for the position sequences of two trajectories. After obtaining the curvature values ​​at each position point of the two trajectories, the curvature values ​​at their corresponding positions are compared point by point. Once the difference between the curvature values ​​at a corresponding point is found to be greater than a preset threshold, it means that the curvature of the two trajectories at that position point is significantly different. The similarity between the two trajectories is then adjusted, i.e., the similarity is reduced. The more corresponding points where the curvature difference is greater than the threshold, the more inconsistent the curvature characteristics of the two trajectories are at more positions, which means that the behavior patterns of the data acquisition personnel are more different at more operating positions. Accordingly, the similarity between the two trajectories will be lower.

[0090] S304. If the similarity is lower than the similarity threshold, then extract the avoidance behavior features from the activity trajectory of the collectors in the later time sequence.

[0091] Specifically, after calculating the similarity between two activity trajectories of the same group of data collectors and comparing them with a preset similarity threshold, if the similarity is found to be lower than the threshold, it means that there is a significant difference in the operational behavior reflected by these two trajectories. In this case, further analysis is needed to determine if it is due to situations such as avoiding test paper bags. The principle is that within a given timeframe, new stacks of test papers may be created, or some existing stacks may be reduced. When such changes occur in the number and layout of test paper stacks, the activity trajectory of the data collectors will naturally change accordingly during the execution of test paper-related tasks. The focus is initially on the later activity trajectory of the data collector, because if avoidance behavior exists, it is often more evident in subsequent operations. Then, carefully analyze each part of the trajectory to check for situations such as sudden changes in trajectory direction (a trajectory that was originally moving in a straight line suddenly turns at a large angle), significant decrease in speed (sudden deceleration in a section of the trajectory that was traveling at a normal speed), and short pauses (pausing at a certain position for a period of time that exceeds the normal operating pause time range). If these characteristics are present, extract them as avoidance behavior characteristics so that the corresponding obstacle test bag can be found in the future and further investigation of abnormal operation can be carried out.

[0092] In some specific embodiments, step S304 specifically includes:

[0093] S3041. Obtain the position sequence and velocity sequence of the two activity trajectories of the data collectors, respectively;

[0094] Specifically, image analysis is performed on the surveillance video. Position information at different times along the same trajectory is extracted in chronological order and organized into a position sequence. Similarly, the corresponding speed information is also extracted in chronological order to form a speed sequence.

[0095] S3042. Calculate the curvature values ​​corresponding to the position sequences of the two data collection personnel activity trajectories;

[0096] Specifically, for a sequence of positions on a plane, a curvature calculation formula based on the principles of calculus can be used. By analyzing and calculating the changes in the slope of the tangent between adjacent coordinate points in the position sequence, the curvature value of each position point can be obtained.

[0097] S3043. In the activity trajectory of the personnel in the later time sequence, when the curvature value is greater than the first preset threshold and the corresponding speed value is less than the second preset threshold, the candidate avoidance position is determined.

[0098] Specifically, the data collection personnel's activity trajectory is traversed chronologically, and the corresponding curvature and velocity values ​​are obtained for each location. The curvature value is then compared to a first preset threshold, and the velocity value is compared to a second preset threshold. If the curvature value is greater than the first preset threshold and the velocity value is less than the second preset threshold, it indicates that the data collection personnel's trajectory has significantly curved and their movement speed has noticeably slowed down at this location. This is likely due to encountering a situation requiring avoidance, such as an obstruction by a test paper bag. This location is then identified as a candidate avoidance location. All locations meeting these conditions are selected to form a set of candidate avoidance locations, preparing for further assessment of whether new avoidance behaviors exist.

[0099] S3044. Determine whether the activity trajectory of the data acquisition personnel who are earlier in the time sequence satisfies the condition that the curvature value is greater than the first preset threshold and the velocity value is less than the second preset threshold at the corresponding spatial location.

[0100] It should be noted that the principle and process of this step are similar to those of step S3043. The relevant principles and processes can be referred to in step S3043, and are not limited here.

[0101] S3045. Under certain conditions, the candidate avoidance position is determined as the avoidance behavior feature.

[0102] Specifically, after the preceding steps determine that the activity trajectories of the data collectors at earlier timelines also meet the conditions of having a curvature value greater than the first preset threshold and a velocity value less than the second preset threshold at their corresponding spatial locations, it indicates that these locations exhibit similar characteristics of high curvature and slow velocity on both trajectories, which is highly likely due to new avoidance behavior. The previously identified candidate avoidance locations are then formally confirmed as avoidance behavior characteristics.

[0103] As can be seen, by acquiring the position and velocity sequences of two data collection personnel activity trajectories, the curvature value corresponding to the position sequence reflects the degree of curvature of the trajectory, and the velocity value reflects the speed of movement. By setting a threshold, candidate avoidance positions with large curvature and low velocity in the later trajectory are selected, and then compared with the spatial position of the earlier trajectory. The two are mutually corroborated to determine the avoidance behavior characteristics.

[0104] S305. Identify the obstacle test paper bag corresponding to the avoidance behavior characteristics; obtain the first test paper bag corresponding to the activity trajectory of the data collector earlier in the time sequence and the second test paper bag corresponding to the activity trajectory of the data collector later in the time sequence.

[0105] Specifically, based on the spatial location information of the avoidance behavior characteristics, the area where obstacle test paper bags might exist is roughly determined. For example, if the avoidance behavior characteristics manifest as a change in trajectory at a certain location, then a circular area with a certain radius is defined as the search range, centered on this change point. Then, within this search area, combined with information such as the placement and type identification of the test paper bags, the corresponding test paper bags are located and identified as obstacle test paper bags. At the same time, the first test paper bag corresponding to the activity trajectory of the earlier data collector and the second test paper bag corresponding to the activity trajectory of the later data collector are obtained. By examining the relevant information of these three test paper bags and their sequential relationship in operation, preparation is made for subsequent judgment on whether they conform to the preset operating procedures.

[0106] In some embodiments, step S305 specifically includes: S3051, constructing a search region based on the avoidance behavior features;

[0107] The search area refers to a spatial region defined according to certain rules and scope based on the location of the avoidance behavior characteristics. It is used to subsequently find related objects that may lead to the avoidance behavior (mainly the obstacle test paper bag in this case). It is equivalent to a scope limit for key investigation.

[0108] S3052. Determine the target area closest to the search area in the preset operation procedure;

[0109] Specifically, the pre-defined operating procedures are consulted to determine the regional divisions and corresponding functional descriptions for each step, such as the storage and handling of exam paper bags. Information such as the spatial location, scope, and relationships with other areas are then identified. Next, by calculating spatial distances or analyzing regional relationships, the search area is compared with the areas mentioned in the pre-defined operating procedures to identify the area closest to the search area or with the strongest correlation, thus determining it as the target area.

[0110] S3053. The test paper bag corresponding to the target area is identified as the obstacle test paper bag.

[0111] As can be seen, a search area is constructed based on the identified avoidance behavior characteristics. Then, according to the preset operating procedures, the nearest target area is determined, and the corresponding test paper bag is identified as the obstacle test paper bag. Starting from the personnel's avoidance behavior, the system accurately associates the obstacle test paper bags that may affect the operating procedures.

[0112] S306. Determine whether the obstacle test paper bags meet the requirements simultaneously according to the preset operating procedures, and carry them out after the first test paper bag and before the second test paper bag.

[0113] Specifically, after identifying the obstructing exam paper bags and determining the first and second exam paper bags, to thoroughly verify whether the operation process follows the preset sequence requirements, the specific provisions regarding the handling order of the relevant exam paper bags in the preset operating procedures are first reviewed in detail. Then, the actual handling sequence of the obstructing exam paper bags is compared with that of the first and second exam paper bags in reality to check whether the obstructing exam paper bags were indeed handled after the first exam paper bags and before the second exam paper bags. For example, if the preset operating procedures clearly require that when handling a batch of Chinese exam papers, the exam paper bags on shelf A (i.e., the first exam paper bags) be handled first, and then if an obstructing exam paper bag is encountered at a specific location (i.e., the obstructing exam paper bag), the exam paper bags on shelf B (i.e., the second exam paper bags) should be handled. In this case, it is necessary to verify whether the actual personnel movement trajectory and the handling of the exam paper bags are consistent with this to determine whether the operating sequence is compliant and to avoid subsequent problems such as chaotic exam paper distribution caused by disordered sequence.

[0114] S307. If not all conditions are met, the corresponding behaviors of the obstacle test paper bag, the first test paper bag, and the second test paper bag shall be judged as abnormal events.

[0115] It is evident that determining the relative positional relationships between the test paper bag areas clarifies the spatial layout of each test paper bag stack. Next, the correlation strength between different test paper bag stacks is established, with the correlation strength decreasing as the distance increases. This allows for the measurement of the closeness of the correlation between each test paper bag stack based on distance. Subsequently, the changes in distance between the test paper bags that are added or removed from the stack and their respective stacks are analyzed, and this is combined with group behavior consistency indicators for a comprehensive judgment. When a test paper bag stack shows an increase or decrease and meets certain conditions, it is identified as a target test paper bag. By deeply considering the overall correlation and changes in the test paper bag stacks, it is possible to distinguish between reasonable changes during normal handling and stacking, and batch confusion caused by genuine improper handling, thus improving the accuracy of judging whether there are abnormalities in test paper batches.

[0116] The following describes an exemplary material detection system 400 for a material stacking area provided in an embodiment of this application. Figure 4 This is an exemplary hardware structure diagram of the material detection system 400 for the material stacking area provided in this application embodiment.

[0117] In some embodiments, the material detection system 400 of the material storage area is a computer device or includes a computer device in the material detection system 400 of the material storage area. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with other external terminals or servers via a network connection. In some embodiments, the network interface can be a wired network interface; in some embodiments, the network interface can also be a wireless network interface. When the computer program is executed by the processor, it implements the methods in the embodiments of this application.

[0118] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0119] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0120] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0121] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive), etc.

[0122] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for detecting materials in a material storage area, characterized in that, include: Monitoring images of the test paper storage area are acquired, and the images are processed with differential clarity to obtain a feature map sequence. The image clarity of the test paper bag area is higher than that of the non-test paper bag area. Within the test paper bag area, the clarity decreases sequentially from the test paper bag outline to other areas and then to the test paper bag body area. The resolution is increased for areas with simple test paper bag outline structures, and decreased for areas with complex outline structures. The simple areas are defined as those where the statistical value of the outline curve is below a set threshold, and the complex areas are those where the statistical value of the outline curve is above a set threshold. When a change in the position of the test paper bag is detected, the feature map sequence from before the last position change to the current time is spatially registered with the dynamic benchmark model to obtain the displacement of different test paper bags; the dynamic benchmark model is a three-dimensional spatial mapping established by the initial stacking state of the test papers when they are put into storage. The target number of test paper bags to be reduced or increased is determined based on the amount of displacement of the test paper bags; The interaction data between personnel activity trajectories and the test paper bag area is collected, and the interaction data is matched and analyzed with preset operating procedures; the interaction data includes data information generated by personnel during the process of touching and handling the test paper bag area; When the interactive data conforms to the preset operating procedure, the corresponding behavior is judged as a normal event; when the interactive data does not conform to the preset operating procedure, the corresponding behavior is judged as an abnormal event; the preset operating procedure includes information on personnel with corresponding permissions and specific test paper bags that are allowed to interact with them. The target test paper bag corresponding to the normal event is compared with the preset work procedure; If the test paper bag specified in the preset work procedure does not correspond to the target test paper bag, the corresponding normal event will be changed to an abnormal event. Mark abnormal events.

2. The method according to claim 1, characterized in that, The step of determining the target number of test paper bags to be reduced or increased based on the displacement of the test paper bags specifically includes: Determine the relative positions of the test paper bag areas; Establish the correlation strength between different test paper bag stacks, wherein the correlation strength decreases as the spacing between the test paper bag stacks increases; the test paper bag stack refers to all test paper bags within the test paper bag area. Determine the change in distance between the reduced or increased test paper bags in the test paper bag stack and the stack to which they belong; Determine the group behavior consistency index based on all transformation quantities; If the change in distance between a decrease or increase in the number of test paper bags in a pile of test paper bags and its corresponding pile of test paper bags exceeds a preset threshold, and the bag deviates from the corresponding group behavior consistency index, it is identified as the target test paper bag.

3. The method according to claim 1, characterized in that, After the steps of collecting the interaction data between the personnel's activity trajectory and the test paper bag area, and matching and analyzing the interaction data with preset operating procedures, the method further includes: Obtain the type identifier of the test paper bag, the type identifier being used to group the test paper bags together, the type identifier including one or more of the following: school, class, and printed product subject information; The activity trajectories of the data collectors are grouped using type identifiers; From the activity trajectories of the same group of data collectors, two activity trajectories of data collectors are randomly selected, and their similarity is determined. If the similarity is lower than the similarity threshold, then avoidance behavior features are extracted from the activity trajectories of the personnel who collected the data later in the time sequence. Identify the obstacle test bag corresponding to the avoidance behavior characteristics; obtain the first test bag corresponding to the activity trajectory of the data collector earlier in the time sequence and the second test bag corresponding to the activity trajectory of the data collector later in the time sequence; According to the preset operating procedure, determine whether the obstacle test paper bags meet the requirements simultaneously, and carry them out after the first test paper bag and before the second test paper bag; If not all conditions are met, the corresponding behaviors of the obstacle test paper bag, the first test paper bag, and the second test paper bag will be judged as abnormal events.

4. The method according to claim 3, characterized in that, The step of extracting avoidance behavior features from the activity trajectories of personnel with later extraction times specifically includes: The location and velocity sequences of the two data collection personnel's activity trajectories were obtained respectively; Calculate the curvature values ​​corresponding to the position sequences of the two data collection personnel activity trajectories; In the activity trajectory of the data collection personnel in the later time sequence, when the curvature value is greater than the first preset threshold and the corresponding speed value is less than the second preset threshold, the candidate avoidance position is determined. Determine whether the activity trajectory of the data collector who is earlier in the time sequence satisfies the condition that the curvature value is greater than the first preset threshold and the velocity value is less than the second preset threshold at the corresponding spatial location; Under certain conditions, the candidate avoidance position is determined as the avoidance behavior feature.

5. The method according to claim 3, characterized in that, The step of identifying the obstacle test paper bag corresponding to the avoidance behavior characteristics specifically includes: The search area is constructed based on the avoidance behavior characteristics; Determine the target region closest to the search area in the preset operating procedures; The test paper bag corresponding to the target area is identified as the obstacle test paper bag.

6. The method according to claim 1, characterized in that, The step of performing differential sharpness processing on the monitoring image to obtain a feature map sequence specifically includes: The boundaries of the test paper bag in the monitoring image are extracted to obtain a preliminary outline of the test paper bag; Determine whether the preliminary outline of the test paper bag meets the requirements of the simple area; If the conditions are met, a multi-scale feature pyramid is constructed, and features at different scales are extracted from the outline of the test paper bag to obtain local fine features. The local fine features are fused with the preliminary test paper bag outline to obtain the test paper bag outline structure.

7. The method according to claim 1, characterized in that, After the step of marking the abnormal event, the method further includes: associating the corresponding batch identification information and recording the operator's identity information, operation timestamp, and spatial location coordinates.

8. A material detection system for a material storage area, characterized in that, The material detection system of the material stacking area includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code including computer instructions, and the one or more processors call the computer instructions to cause the material detection system of the material stacking area to perform the method as described in any one of claims 1-7.

9. A computer program product containing instructions, characterized in that, When the computer program product is run on the material detection system in the material storage area, the material detection system in the material storage area performs the method as described in any one of claims 1-7.

10. A computer-readable storage medium comprising instructions, characterized in that, When the instruction is executed on the material detection system in the material storage area, the material detection system in the material storage area performs the method as described in any one of claims 1-7.

Images