Digital intelligent file management method and system based on machine vision

Abstract

The present invention relates to a digital intelligent file management method and system based on machine vision. By detecting the cabinet doors of file cabinets, different storage cycles are divided. When the cabinet door is opened, the camera automatically collects the tilted video inside the cabinet, and extracts the target frame indicating the completion of the operation before the cabinet door is closed from the tilted video. The tiles corresponding to all storage compartments in the target frame are analyzed in combination with the pressure data inside the cabinet. For the tiles without pressure change, a rough inspection based on gray feature analysis is adopted, and for the tiles with pressure change, a precise inspection based on gray feature, geometric feature and character recognition is adopted. Thus, the detection efficiency and detection accuracy are ensured. After the detection is completed, the position distribution information of all file bags is updated. Combining with the position distribution information of the previous storage cycle, the status update of the file bags can be efficiently completed, thereby realizing automated information management. This application has the advantages of high management efficiency, accuracy and high degree of automation.

Description

Technical Field

[0001] The present invention relates to the technical field of file management, and specifically to a digital intelligent file management method and system based on machine vision. Background Art

[0002] Files are important carriers for recording human activities and social changes. Properly managing files helps protect historical memories and ensures that future generations can understand and learn from past experiences and lessons. For enterprises, files provide valuable historical data and information resources, which can be used as a basis for formulating current and future strategies and decisions, improving the quality of decision-making.

[0003] In the prior art, although digital technologies have been gradually adopted to manage files, for the original source of file information, that is, the files themselves, manual management methods are still used for recording. Therefore, for the files themselves, if there are status changes, only personnel can be relied on to record the changed information, which is prone to information omission, resulting in information errors or even loss of files. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a digital intelligent file management method and system based on machine vision to solve the above technical problems.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions:

[0006] A digital intelligent file management method based on machine vision of the present invention includes the steps of:

[0007] Obtain the position distribution information of all file bags in the file cabinet in the previous storage cycle, and obtain the door state of the file cabinet, wherein the storage cycle is determined based on the door state;

[0008] When the door state is the open state, obtain the status change timestamp and the tilt video of the file cabinet in the open state of the door; extract the shape features and gray features of each storage area of multiple frames of images in the tilt video based on a pre-constructed mask;

[0009] Screen the tilt video based on the shape features and gray features to obtain the target frame and the timestamp of the target frame;

[0010] Extract the pressure data sequence of each pressure sensing unit in the file cabinet within the time window from the status change timestamp to the timestamp of the target frame; and determine the target position where the pressure changes based on the pressure data sequence, wherein the pressure data sequence includes the pressure values of multiple time points at one position;

[0011] Segment the target frame based on a pre-constructed mask extraction to obtain a target tile containing the target position and a non-target tile not containing the target position; perform a rough inspection on the non-target tile based on gray-scale features, and perform a refined inspection on the target tile based on gray-scale features, geometric features, and character recognition to obtain the detection result of each tile;

[0012] Construct the position distribution information of all the file bags in the current storage period based on the detection results of each tile, and manage all the file bags in the filing cabinet based on the position distribution information of the current storage period and the position distribution information of the previous storage period.

[0013] In an embodiment of the present application, extracting the shape features and gray-scale features of each storage area of multiple frames of images in the tilted video based on a pre-constructed mask includes:

[0014] Perform dynamic frame extraction on the tilted video to obtain multiple frames of images;

[0015] Perform high-pass filtering and grayscale conversion processing on the multiple frames of images to obtain multiple preprocessed images;

[0016] Based on affine transformation, convert the multiple preprocessed images from a tilted perspective to a front-facing perspective to obtain multiple intermediate images;

[0017] Perform an AND operation on the pre-constructed mask and the multiple intermediate images respectively to obtain multiple AND operation images; and mark the positions of the storage areas in the multiple AND operation images based on the pre-constructed mask;

[0018] Extract the target areas that meet the pre-constructed first gray-scale range from the multiple AND operation images;

[0019] Determine the storage area corresponding to each target area based on the markings of the multiple target areas; extract the contour features of each storage area, and extract the perimeter, area, and rectangularity of the contour features to obtain shape features;

[0020] Extract the average gray-scale and gray-scale variance of each storage area to obtain gray-scale features.

[0021] In an embodiment of the present application, screening the tilted video based on the shape features and gray-scale features to obtain the target frame and the time stamp of the target frame includes:

[0022] Compare the shape features and gray-scale features of the multiple intermediate images with the pre-constructed shape feature screening parameters and gray-scale feature screening parameters respectively, where the morphological feature screening parameters include a perimeter tolerance range, an area tolerance range, and a rectangularity tolerance range, and the gray-scale feature screening parameters include a gray-scale tolerance range and a gray-scale variance tolerance range;

[0023] The intermediate image obtained by matching the shape feature and the grayscale feature with the pre-constructed shape feature screening parameter and grayscale feature screening parameter respectively is used as the complete image of the unoccluded storage area;

[0024] Obtain the closing timestamp when the cabinet door is closed, and use multiple consecutive complete images closest to the closing timestamp as target frames, and determine the timestamps of the target frames.

[0025] In an embodiment of the present application, determining the target position where the pressure changes based on the pressure data sequence includes:

[0026] Perform temporal difference on the pressure values at any adjacent time points in the pressure data sequence to obtain a difference sequence;

[0027] Slide a pre-constructed sliding window along the difference sequence, and calculate the sum of the pressure differences within the sliding window each time the window slides;

[0028] When the sum of the pressure differences is greater than a preset difference threshold, determine that the position corresponding to the pressure data sequence is the target position.

[0029] In an embodiment of the present application, performing a rough inspection based on the grayscale feature on non-target tiles includes:

[0030] Perform high-pass filtering and grayscale conversion on the non-target tiles to obtain a grayscale image ;

[0031] For the grayscale image Perform brightness adjustment to obtain a brightness-adjusted image , where the mathematical expression of the brightness-adjusted image is:

[0032]

[0033] In the formula, is the grayscale value of the pixel point in the brightness-adjusted image, is the grayscale value of the pixel point in the grayscale image, is the minimum grayscale value in the grayscale image, is the maximum grayscale value in the grayscale image;

[0034] Extract the pixel points whose grayscale values fall within a preset second grayscale range from the brightness-adjusted image to construct a file bag area; perform morphological processing on the file bag area image to obtain a file bag area image ;

[0035] Based on the file bag area image Area and the grayscale image Area Calculate the effective occupancy ratio of the file bags in the current storage period , The mathematical expression is:

[0036]

[0037] Calculate the effective occupancy ratio of the file bags in the current storage period and the effective occupancy ratio of the file bags in the previous storage period Deviation rate , , when the deviation rate is less than the preset deviation rate threshold, it is determined that there is no change in the file bags in the storage unit corresponding to the current non-target tile; when the deviation rate is greater than or equal to the preset deviation rate threshold, the current non-target tile is marked as containing the target tile, and the target tile is subjected to precise inspection based on grayscale features, geometric features, and character recognition.

[0038] In an embodiment of the present application, the precise inspection of the target tile based on grayscale features, geometric features, and character recognition includes:

[0039] Perform high-pass filtering and grayscale conversion on the target tile to obtain a target grayscale image ;

[0040] Adjust the brightness of the target grayscale image to obtain a target brightness-adjusted image ;

[0041] Extract the pixel points whose grayscale values fall within a preset second grayscale range from the target brightness-adjusted image to construct a target file bag area; and extract contour features from the target brightness-adjusted image ;

[0042] Filter the contours in the target brightness-adjusted image to obtain target contours that meet the file bag size; perform morphological processing on the target file bag area and the target contour features to obtain a file bag area image containing the target contour features ;

[0043] Based on the target contour features, the target brightness-adjusted image Perform segmentation to obtain single - body images of multiple file bags; extract the grayscale features and geometric features of the single - body image of each file bag, and perform character recognition on the single - body image of each file bag to obtain the character recognition result; and construct matching features based on the grayscale features, geometric features, and character recognition results of the single - body image of each file bag.

[0044] Match the matching features of multiple file bags in the current storage cycle of the storage unit corresponding to the target tile with the matching features of multiple file bags in the previous storage cycle to obtain a matching result; and determine the file - bag change information of the storage unit based on the matching result, where the file - bag change information includes addition, reduction, and position change.

[0045] In an embodiment of the present application, matching the matching features of multiple file bags in the current storage cycle of the storage unit corresponding to the target tile with the matching features of multiple file bags in the previous storage cycle to obtain a matching result includes:

[0046] Calculate the grayscale similarity between one file bag in the current storage cycle and the file bag in the previous storage cycle , geometric similarity and cosine similarity of the character recognition result , where the mathematical expressions of the grayscale similarity and geometric similarity are respectively:

[0047]

[0048]

[0049] In the formula, is the average grayscale value of the th file bag in the th storage cycle, is the average grayscale value of the th file bag in the th storage cycle, is the variance of the grayscale values of the th file bag in the th storage cycle, is the variance of the grayscale values of the th file bag in the th storage cycle, is the perimeter of the contour of the th file bag in the th storage cycle, is the perimeter of the contour of the th file bag in the th storage cycle. For the th area of the outline of the th file bag in the th storage cycle, For the th aspect ratio of the outline of the th file bag in the th storage cycle, is the first weight, is the second weight, is the third weight, is the fourth weight, is the fifth weight;

[0050] Based on the gray - scale similarity , geometric similarity and cosine similarity calculate the matching degree , where the mathematical expression of the matching degree is:

[0051]

[0052] Match the file bags with a matching degree greater than a preset matching - degree threshold to obtain a matching result.

[0053] In an embodiment of the present application, manage all file bags in the filing cabinet based on the position - distribution information of the current storage cycle and the position - distribution information of the previous storage cycle, including:

[0054] Determine the difference information between the position - distribution information of the current storage cycle and the position - distribution information of the previous storage cycle; and change the storage status and retrieval information of the file bags based on the difference information.

[0055] In an embodiment of the present application, the method for determining the storage cycle includes:

[0056] Obtain the time difference between the cabinet - door opening timestamp and the cabinet - door closing timestamp;

[0057] When the time difference is greater than the target duration, use the cycle after the cabinet - door is closed as the next storage cycle.

[0058] The present application also provides a digital intelligent file - management system based on machine vision, including:

[0059] An acquisition module, configured to acquire the position distribution information of all file bags in the filing cabinet in the previous storage cycle, and acquire the cabinet door state of the filing cabinet, wherein the storage cycle is determined based on the cabinet door state;

[0060] A feature extraction module, configured to, when the cabinet door state is the open state, acquire the state change timestamp and the tilted video of the filing cabinet in the open state of the cabinet door; extract the shape features and gray-scale features of each storage area of multiple frames of images in the tilted video based on a pre-constructed mask;

[0061] A screening module, configured to screen the tilted video based on the shape features and gray-scale features to obtain the target frame and the timestamp of the target frame;

[0062] A pressure analysis module, configured to extract the pressure data sequence of each pressure sensing unit in the filing cabinet within a time window from the state change timestamp to the timestamp of the target frame; and determine the target positions where the pressure changes based on the pressure data sequence, wherein the pressure data sequence includes the pressure values at multiple time points of one position;

[0063] A detection module, configured to segment the target frame based on a pre-constructed mask to obtain a target tile containing the target position and a non-target tile not containing the target position; perform a rough inspection based on gray-scale features on the non-target tiles, and perform a refined inspection based on gray-scale features, geometric features, and character recognition on the target tiles to obtain the detection results of each tile;

[0064] A management module, configured to construct the position distribution information of all file bags in the current storage cycle based on the detection results of each tile, and manage all file bags in the filing cabinet based on the position distribution information in the current storage cycle and the position distribution information in the previous storage cycle.

[0065] The beneficial effects of the present invention are as follows: The digital intelligent file management method and system based on machine vision of the present invention divide different storage cycles by detecting the cabinet door of the filing cabinet. When the cabinet door is opened, the camera automatically collects the tilted video inside the cabinet, and extracts the target frame indicating the completion of the operation before the cabinet door is closed from the tilted video. The tiles corresponding to all storage compartments in the target frame are analyzed in combination with the pressure data inside the cabinet. For the tiles without pressure change, a rough inspection based on gray-scale feature analysis is adopted, and for the tiles with pressure change, a refined inspection based on gray-scale features, geometric features, and character recognition is adopted. Thereby, the detection efficiency and detection accuracy are ensured. After the detection is completed, the position distribution information of all file bags is updated. Combining with the position distribution information in the previous storage cycle, the status update of the file bags can be efficiently completed, thereby realizing automated information management. This application has the advantages of high management efficiency, accuracy, and high automation degree. Description of the Drawings

[0066] The present invention will be further described below in conjunction with the accompanying drawings and embodiments:

[0067] Figure 1 It is an application scenario diagram of a digital intelligent file management method based on machine vision shown in an embodiment of the present application;

[0068] Figure 2 It is a flowchart of a digital intelligent file management method based on machine vision shown in an embodiment of the present application;

[0069] Figure 3 It is a schematic diagram of the rough inspection process in an embodiment of the present application;

[0070] Figure 4 It is a schematic diagram of the fine inspection process in an embodiment of the present application;

[0071] Figure 5 It is a structural diagram of a digital intelligent file management system based on machine vision shown in an embodiment of the present application;

[0072] Figure 6 It shows a schematic structural diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application. Specific Embodiments

[0073] The following uses specific specific examples to illustrate the implementation manners of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0074] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner. Therefore, only the layers related to the present invention are shown in the diagrams, rather than being drawn according to the number, shape, and size ratio of the layers in actual implementation. The type, quantity, and can be arbitrarily changed in actual implementation, and the layer layout type may also be more complex.

[0075] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details.

[0076] Figure 1 It is an application scenario diagram of a digital intelligent file management method based on machine vision shown in an embodiment of the present application, asFigure 1 As shown, in the present application, a camera facing the front of the filing cabinet is provided at the top of the filing cabinet, and a door magnetic switch is provided on the cabinet door, and the door magnetic switch is used to sense the opening and closing state of the cabinet door. After each cabinet door is opened, the camera takes pictures of the filing cabinet at an inclined angle to avoid the occlusion of the cabinet door. Although the operator may also occlude the image during the operation, the inclined video contains a time window after the hands leave after the operation is completed. The present application extracts the complete image by collecting the time window when the hands leave before the cabinet door is closed, and detects the image to obtain the change information of each file bag, so as to complete the automatic update of the status of the file bag.

[0077] Figure 2 It is a flowchart of a digital intelligent file management method based on machine vision shown in an embodiment of the present application. As Figure 2 shown: A digital intelligent file management method based on machine vision in this embodiment may include steps S210 to S260:

[0078] S210, obtain the position distribution information of all file bags in the filing cabinet in the previous storage cycle, and obtain the cabinet door state of the filing cabinet, wherein the storage cycle is determined based on the cabinet door state;

[0079] In the present application, the storage cycle is determined by using the opening and closing state of the cabinet door, including:

[0080] (1) Obtain the cabinet door opening timestamp and the cabinet door closing timestamp of the time difference ;

[0081] (2) When the time difference is greater than the target duration (such as 5 seconds), the cycle after the cabinet door is closed is used as the next storage cycle.

[0082] When the time difference is greater than the target duration (such as 5 seconds), it is considered that this is a valid access operation, which may involve the movement or rearrangement of file bags, and the cycle after the cabinet door is closed is marked as the next storage cycle. This helps the system to judge the correct storage cycle.

[0083] S220, when the cabinet door state is the open state, obtain the status change timestamp and the inclined video of the filing cabinet in the open state of the cabinet door; extract the shape features and gray features of each storage area of multiple frames of images in the inclined video based on a pre-constructed mask;

[0084] To avoid the cabinet door blocking the view when it is opened, the camera in this application is tilted towards the inside of the cabinet. However, this setting also causes the operator's arm to block the view during operation. Therefore, this application extracts frames from the tilted video based on the morphological and grayscale features within the storage cell images. The principle is that the morphology (determined by the contour) and grayscale features of the storage cell images are different when they are unobstructed and obstructed.

[0085] The specific process of extracting the shape features and grayscale features of each storage area of multiple frames of images in the tilted video based on a pre-constructed mask includes:

[0086] S221, perform dynamic frame extraction on the tilted video to obtain multiple frames of images;

[0087] Dynamically extract several frames from the tilted video as the basis for analysis. This can be done by setting a fixed frame interval (such as extracting one frame every few seconds) or determining when to extract new frames based on changes in the video content.

[0088] In this embodiment, based on dynamic frame extraction, when the degree of change in the picture is large, multiple frames of images can be extracted to retain more picture information.

[0089] S222, perform high-pass filtering and grayscale conversion processing on the multiple frames of images to obtain multiple preprocessed images;

[0090] High-pass filtering is used to enhance the edge information in the image and reduce the influence of background noise.

[0091] Grayscale conversion converts a color image into a grayscale image, simplifying the subsequent processing flow. Grayscale conversion is usually achieved by calculating the weighted average of the RGB values of each pixel point.

[0092] S223, based on affine transformation, convert the multiple frames of preprocessed images from a tilted perspective to a frontal perspective to obtain multiple intermediate images;

[0093] Use affine transformation to adjust the angle of the image and flip the image to the frontal perspective. The affine transformation requires a pre-determined transformation matrix, which can be calculated through known key points (such as the corner points of the filing cabinet).

[0094] S224, perform AND operation on the pre-constructed mask and the multiple frames of intermediate images respectively to obtain multiple AND operation images; and mark the positions of the storage areas in the multiple AND operation images based on the pre-constructed mask;

[0095] Through the AND operation, the image of the storage area can be retained. Thus, the border area of the storage compartment is removed. Each storage area is pre-marked in the mask, so that when the mask is aligned with multiple intermediate images, each storage area can be directly marked in the image.

[0096] S225, extract a target area that meets a pre - constructed first gray - scale range from the multiple AND - operation images;

[0097] Under normal circumstances, the file bags in the storage compartments and the background will fall within a specific gray - scale range. However, if there is an interference from an arm, it will cause a change in the gray - scale. Therefore, in this application, the target area that falls within the first gray - scale range is first extracted as the unobstructed storage - compartment area.

[0098] S226, determine the storage area corresponding to each target area based on the markings of the multiple target areas; extract the contour features of each storage area, and extract the perimeter, area, and rectangularity of the contour features to obtain shape features;

[0099] Then extract the contour features of the unobstructed storage - compartment area to verify whether the shape of the unobstructed storage - compartment area is complete, so as to determine whether it is obstructed.

[0100] S227, extract the average gray - scale and gray - scale variance of each storage area to obtain gray - scale features.

[0101] In addition, directly extract the average gray - scale and gray - scale variance of the storage area to be used to verify whether there is a change in the gray - scale value due to being obstructed.

[0102] S230, screen the tilted video based on the shape features and gray - scale features to obtain the target frame and the time - stamp of the target frame;

[0103] After obtaining the shape features and gray - scale features, the shape features and gray - scale features can be used to verify whether there is a situation of hand obstruction in the storage - cell image, so as to extract the frame where the unobstructed storage - compartment area is located. Specifically, it includes:

[0104] S231, compare the shape features and gray - scale features of multiple intermediate images with pre - constructed shape - feature screening parameters and gray - scale - feature screening parameters respectively. Among them, the morphological - feature screening parameters include a perimeter tolerance range, an area tolerance range, and a rectangularity tolerance range, and the gray - scale - feature screening parameters include a gray - scale tolerance range and a gray - scale - variance tolerance range;

[0105] In this application, the corresponding tolerance ranges are constructed by extracting the shape features and gray - scale features of multiple storage - cell areas in an unobstructed standard image in advance. The construction of the tolerance range is based on statistical principles. That is, for each storage box, after extracting images multiple times, extract the perimeter, area, and rectangularity of multiple images. Then calculate the mean and variance based on the perimeter, area, and rectangularity of multiple images respectively, and construct the perimeter tolerance range, area tolerance range, and rectangularity tolerance range based on 3 - times the standard deviation.

[0106] Similarly, for each storage box, after extracting images multiple times, the grayscale means and grayscale variances of multiple images are extracted, and the means and variances of multiple grayscale means and grayscale variances are calculated respectively, and the grayscale tolerance range and grayscale variance tolerance range are constructed based on 3 times the standard deviation.

[0107] S232, taking the intermediate image whose shape features and grayscale features are matched with the pre-constructed shape feature screening parameters and grayscale feature screening parameters respectively as the complete image of the storage area that is not blocked;

[0108] During the comparison, if both the grayscale features and the shape features fall within the corresponding tolerance range, it means that the grayscale and shape of the storage cell in the current image are consistent with the unobstructed image, which can indicate that the current image is not obstructed by the operator's hand, thereby causing changes in the contour and grayscale features.

[0109] S233, obtaining a closing timestamp when the cabinet door is closed, and taking a plurality of continuous complete images closest to the closing timestamp as target frames, and determining the timestamp of the target frames.

[0110] Considering that the operator may be in a daze in front of the filing cabinet, or perform other actions, in order to accurately filter out the image that best reflects the operation result, the present application also extracts multiple continuous complete images before the cabinet door is closed as the target frame.

[0111] S240, extracting a pressure data sequence of each pressure sensing unit in the filing cabinet in a time window between the state change timestamp and the target frame timestamp; and determining a target position where the pressure changes based on the pressure data sequence, wherein the pressure data sequence includes pressure values ​​at multiple time points of a position;

[0112] In order to efficiently detect the image of each storage compartment unit, the present application uses a pressure sensor at the bottom of the storage compartment to detect the pressure change of each storage compartment, so as to find the storage compartment with possible state change. For the storage compartment image without pressure change, a rough inspection method is adopted to improve the detection efficiency and speed.

[0113] Wherein, determining the target position where the pressure changes based on the pressure data sequence includes:

[0114] S241, performing time series difference on the pressure values ​​at any adjacent time points in the pressure data sequence to obtain a difference sequence;

[0115] For any pressure data sequence at a position , perform time difference , we can get the difference series reflecting the pressure value changes at multiple time points .

[0116] S242, Slide along the difference sequence based on a pre-constructed sliding window, and calculate the total pressure difference within the sliding window each time it slides;

[0117] For the difference sequence, extract time windows using a sliding window and accumulate the total pressure differences within the time windows , and the pressure change conditions within multiple time windows can be obtained.

[0118] S243, When the total pressure difference is greater than a preset difference threshold, determine that the position corresponding to the pressure data sequence is the target position.

[0119] If within a time window, the pressure changes significantly such that the total pressure difference is greater than the preset difference threshold, it indicates that there is a change in the file bag at the corresponding position, resulting in a pressure change.

[0120] In addition, in this embodiment, there are multiple pressure sensors in one storage cell, that is, there are multiple positions.

[0121] S250, Segment the target frame based on a pre-constructed mask extraction to obtain a target tile containing the target position and a non-target tile not containing the target position; perform a rough inspection on the non-target tile based on gray-scale features, and perform a fine inspection on the target tile based on gray-scale features, geometric features, and character recognition to obtain the detection results of each tile;

[0122] Before segmenting the target frame using the mask, it is necessary to calculate the average image of multiple target frames. Then perform the segmentation to obtain the tiles of multiple storage cell units. If these tiles have a target position, they are marked as target tiles; if they do not have a target position, they are marked as non-target tiles. Then perform a rough inspection on the non-target images. If there is no problem through quick detection, they are marked as "no change", and the position distribution information within the storage cell continues the position distribution information of the previous storage cycle. For the target tiles, precise detection is required to ensure whether the file bag corresponding to the target tile has changed.

[0123] Figure 3 is a schematic diagram of the rough inspection process in an embodiment of the present application. As Figure 3 shown, performing a rough inspection on the non-target tile based on gray-scale features includes:

[0124] S2501, Perform high-pass filtering and gray-scale conversion on the non-target tile to obtain a gray-scale image ;

[0125] S2502, Adjust the brightness of the gray-scale image to obtain a brightness-adjusted image , wherein, the brightness adjustment image has the following mathematical expression:

[0126]

[0127] In step S2502, first normalize the grayscale image , that is , and then expand the normalized image into a grayscale space with a maximum grayscale value of 255, so as to avoid the grayscale differences caused by different ambient brightnesses and provide a unified brightness parameter for subsequent processing.

[0128] In the formula, is the grayscale value of the pixel point in the brightness adjustment image, is the grayscale value of the pixel point in the grayscale image, is the minimum grayscale value in the grayscale image, is the maximum grayscale value in the grayscale image;

[0129] S2503, extract the pixel points whose grayscale values fall within a preset second grayscale range from the brightness adjustment image to construct a file bag area; perform morphological processing on the file bag area image to obtain the file bag area image ;

[0130] The second grayscale range is the approximate grayscale range presented by the file bag under standard brightness conditions, and the second grayscale range can also be constructed in a statistical manner. Thus, the area where the file bag is located can be extracted. For some discrete abnormal points extracted, morphological processing (including erosion and dilation) is used to remove them, and a file bag area image that only retains the grayscale information of the file bag is obtained .

[0131] S2504, calculate the effective occupancy ratio of the file bag in the current storage cycle based on the area of the file bag area image and the area of the grayscale image , has the following mathematical expression:

[0132]

[0133] By calculating the effective occupancy ratio of the file bag , the proportion of the file bag area in the storage grid area can be roughly judged, and then the number of file bags can be inferred.

[0134] S2505, calculate the effective occupancy ratio of the file bag in the current storage cycle The effective occupancy ratio of the file bag in the previous storage cycle Deviation rate , , when the deviation rate is less than the preset deviation rate threshold, it is determined that there is no change in the file bag in the storage unit corresponding to the current non-target tile; when the deviation rate is greater than or equal to the preset deviation rate threshold, the current non-target tile is marked as containing the target tile, and the target tile is subjected to refined inspection based on gray-scale features, geometric features, and character recognition.

[0135] If the occupancy ratio in the current storage cycle and the occupancy ratio in the previous storage cycle have a small difference in deviation rate, it indicates that the file bag has not changed, and there is no significant pressure change and file bag shape change in this storage unit, so it can be determined that there is no change in the state of the file bag in this storage unit.

[0136] If the occupancy ratio in the current storage cycle and the occupancy ratio in the previous storage cycle have a large difference in deviation rate, further refined inspection and determination are required.

[0137] Figure 4 is a schematic diagram of the refined inspection process in an embodiment of the present application. As Figure 4 shown in this embodiment, the implementation process of the refined inspection is as follows:

[0138] S2511, perform high-pass filtering and gray-scale conversion on the target tile to obtain a target gray-scale image ;

[0139] S2512, perform brightness adjustment on the target gray-scale image to obtain a target brightness-adjusted image ;

[0140] The process and principle of brightness adjustment in step S2512 are the same as those of the brightness adjustment process in the rough inspection process, and will not be elaborated here.

[0141] S2513, extract the pixel points whose gray-scale values fall within a preset second gray-scale range from the target brightness-adjusted image to construct a target file bag area; and extract contour features from the target brightness-adjusted image ;

[0142] The refined inspection process requires not only the gray-scale information of the target file bag area, but also the contour features of the file bag to verify the geometric shape of the file bag. Therefore, contour features also need to be extracted.

[0143] S2514, perform on the target brightness-adjusted image Filter the contours in it to obtain the target contours that meet the size of the file bag; perform morphological processing on the target file bag area and the target contour features to obtain the file bag area image containing the target contour features ;

[0144] In order to accurately screen out the contours belonging to the file bag, the present application performs morphological screening on the contours in the target brightness adjustment image The contours that meet the preset area range, perimeter range, and aspect ratio range are used as the contours of the file bag, and other contours are deleted. In addition, in order to make the target contour completely closed, erosion and dilation are also performed on the target contour to obtain a contour image containing the complete contour.

[0145] S2515, based on the target contour features, segment the target brightness adjustment image to obtain the monomer images of multiple file bags; extract the gray-scale features and geometric features of the monomer image of each file bag, and perform text recognition on the monomer image of each file bag to obtain the text recognition result; and construct matching features based on the gray-scale features, geometric features, and text recognition results of the monomer image of each file bag;

[0146] After obtaining the closed contour, use the closed contour to segment the target brightness adjustment image Thereby, the monomer image of a single file bag is extracted. The gray-scale features and geometric features of each monomer image are extracted. In addition, the text on the side label of the file bag is also recognized through an externally retrieved text recognition model. Thereby, gray-scale features (including average gray value and gray value variance), geometric features (including the area, perimeter, and aspect ratio of the contour), and text recognition results are obtained. As the reference features for subsequent matching.

[0147] S2516, match the matching features of multiple file bags in the current storage cycle of the target tile corresponding storage unit with the matching features of multiple file bags in the previous storage cycle to obtain a matching result; and determine the file bag change information of the storage unit based on the matching result, where the file bag change information includes new addition, reduction, and position change.

[0148] After obtaining the matching features of the current storage cycle, comparing them with the matching features of the previous storage cycle can obtain the change situation of the file bags in the storage unit, such as new file bags added, file bags reduced, and file bag position changes. The matching features of the previous storage cycle are extracted in the same way and will not be elaborated here.

[0149] In an embodiment of the present application, the matching features of multiple file bags of the storage unit corresponding to the target tile in the current storage cycle are matched with the matching features of multiple file bags in the previous storage cycle to obtain a matching result, including:

[0150] S25161, calculate one of the file bags in the current storage cycle and the file bag in the previous storage cycle for gray-scale similarity and geometric similarity as well as the cosine similarity of the character recognition result , where the mathematical expressions of the gray-scale similarity and geometric similarity are respectively:

[0151]

[0152]

[0153] In the formula, is the average gray value of the th file bag in the th storage cycle, is the average gray value of the th file bag in the th storage cycle, is the variance of the gray values of the th file bag in the th storage cycle, is the variance of the gray values of the th file bag in the th storage cycle, is the perimeter of the contour of the th file bag in the th storage cycle, is the perimeter of the contour of the th file bag in the th storage cycle, is the area of the contour of the th file bag in the th storage cycle, is the area of the contour of the th file bag in the th storage cycle, is the aspect ratio of the contour of the th file bag in the th storage cycle, is the aspect ratio of the contour of the th file bag in the th storage cycle, is the first weight, is the second weight, is the third weight, is the fourth weight, is the fifth weight;

[0154] In this embodiment, the gray - scale deviation rate and the gray - scale variance deviation rate are respectively calculated as the benchmark of the gray - scale similarity and the perimeter deviation rate, the area deviation rate and the aspect - ratio deviation rate are respectively calculated as the benchmark of the geometric similarity Finally, exponential weighting is used to calculate the gray - scale similarity and the geometric similarity Generally, the weights are all set to 1.

[0155] S25162, based on the gray - scale similarity and the geometric similarity and the cosine similarity calculate the matching degree , where the mathematical expression of the matching degree is:

[0156]

[0157] where, is the sixth weight, is the seventh weight, is the eighth weight.

[0158] Then use the gray - scale similarity and the geometric similarity to calculate the comprehensive matching degree. In this application, the importance of text is relatively high, so takes 0.6, . Different weight values can also be configured according to actual needs.

[0159] S25163, match the file bags with the matching degree greater than the preset matching - degree threshold to obtain the matching result.

[0160] In the specific matching process, the matching features of a file bag in the current storage unit of the current storage cycle are extracted and respectively matched with the matching features of multiple file bags in the current storage unit of the previous storage cycle. It is determined whether the current file bag is a newly added file bag. If the current file bag cannot be matched with any of the multiple file bags in the current storage unit of the previous storage cycle, it indicates that the current file bag is a newly added file bag. If there is a matching file bag, its location information is compared to determine whether there is a location change. After the matching is completed, if there is a file bag in the multiple file bags in the current storage unit of the previous storage cycle that is not matched, it indicates that there is a situation of file bag reduction.

[0161] All of the above change situations can correspond to the identification codes of the file bags through the text recognition results.

[0162] S260, construct the location distribution information of all file bags in the current storage cycle based on the detection results of each tile, and manage all file bags in the file cabinet based on the location distribution information of the current storage cycle and the location distribution information of the previous storage cycle.

[0163] Specifically, it includes: determining the difference information between the location distribution information of the current storage cycle and the location distribution information of the previous storage cycle; and changing the storage status of the file bags and changing the retrieval information based on the difference information.

[0164] For example, if there is a reduction of file bag A1 in storage unit A, the reduction information of file bag A1 can be recorded in the location distribution information of the current storage cycle. Combining with the personnel registration information can quickly determine who took file bag A1.

[0165] The updated location distribution information can also help personnel to quickly and accurately retrieve files, avoiding unnecessary retrieval errors. This application can effectively help managers to manage the information of file bags.

[0166] A digital intelligent file management method based on machine vision according to the present invention divides different storage cycles by detecting the cabinet door of the file cabinet. When the cabinet door is opened, the camera automatically collects the tilted video inside the cabinet, and extracts the target frame indicating the completion of the operation from the tilted video before the cabinet door is closed. Analyze the tiles corresponding to all storage compartments in the target frame in combination with the pressure data inside the cabinet. For the tiles without pressure changes, a rough inspection based on gray-scale feature analysis is adopted, and for the tiles with pressure changes, a precise inspection based on gray-scale features, geometric features, and character recognition is adopted. Thus, the detection efficiency and detection accuracy are ensured. After the detection is completed, the position distribution information of all file bags is updated. Combining the position distribution information of the previous storage cycle, the status update of the file bags can be efficiently completed, thereby realizing automated information management. This application has the advantages of high management efficiency, accuracy, and high degree of automation.

[0167] As Figure 5 shown, this application also provides a digital intelligent file management system based on machine vision, including:

[0168] An acquisition module for acquiring the position distribution information of all file bags in the file cabinet in the previous storage cycle, and acquiring the cabinet door state of the file cabinet, wherein the storage cycle is determined based on the cabinet door state;

[0169] A feature extraction module for, when the cabinet door state is the open state, acquiring the status change timestamp and the tilted video of the file cabinet in the open state of the cabinet door; extracting the shape features and gray-scale features of each storage area of multiple frames of images in the tilted video based on a pre-constructed mask;

[0170] A screening module for screening the tilted video based on the shape features and gray-scale features to obtain the target frame and the timestamp of the target frame;

[0171] A pressure analysis module for extracting the pressure data sequence of each pressure sensing unit in the file cabinet in the time window from the status change timestamp to the timestamp of the target frame; and determining the target position where the pressure changes based on the pressure data sequence, wherein the pressure data sequence includes the pressure values of multiple time points at one position;

[0172] A detection module for segmenting the target frame based on a pre-constructed mask to obtain a target tile containing the target position and a non-target tile not containing the target position; performing a rough inspection based on gray-scale features on the non-target tiles, and performing a precise inspection based on gray-scale features, geometric features, and character recognition on the target tiles to obtain the detection results of each tile;

[0173] A management module is used to construct the position distribution information of all file bags in the current storage cycle based on the detection results of each tile, and manage all file bags in the file cabinet based on the position distribution information of the current storage cycle and the position distribution information of the previous storage cycle.

[0174] A digital intelligent file management system based on machine vision according to the present invention divides different storage cycles by detecting the cabinet door of the file cabinet. When the cabinet door is opened, the camera automatically collects the tilted video inside the cabinet, and extracts the target frame indicating the completion of the operation before the cabinet door is closed from the tilted video. Analyze the tiles corresponding to all storage compartments in the target frame in combination with the pressure data inside the cabinet. For the tiles without pressure change, a rough inspection based on gray-scale feature analysis is adopted, and for the tiles with pressure change, a precise inspection based on gray-scale feature, geometric feature and character recognition is adopted. Thus, the detection efficiency and detection accuracy are guaranteed. After the detection is completed, the position distribution information of all file bags is updated. Combining the position distribution information of the previous storage cycle, the status update of the file bags can be efficiently completed, so as to realize automated information management. This application has the advantages of high management efficiency, accuracy and high automation.

[0175] Figure 6 The structural schematic diagram of the computer system of the electronic device suitable for implementing the embodiments of the present application is shown. It should be noted that Figure 6 The computer system of the shown electronic device is only an example, and should not bring any limitation to the functions and usage scopes of the embodiments of the present application.

[0176] As Figure 6 shown, the computer system includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 602 or the program loaded from the storage section 608 into the random access memory (RAM) 603, such as executing the method in the above embodiments. In the RAM 603, various programs and data required for system operation are also stored. The CPU 601, ROM 602 and RAM 603 are connected to each other through a bus 604. The input / output (I / O) interface 605 is also connected to the bus 604.

[0177] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as required. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is mounted on the drive 610 as required so that a computer program read therefrom is installed into the storage section 608 as required.

[0178] Specifically, according to an embodiment of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present application includes a computer program product including a computer program carried on a computer-readable medium, the computer program including a computer program for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication section 609, and / or installed from the removable medium 611. When the computer program is executed by a central processing unit (CPU) 601, various functions defined in the system of the present application are executed.

[0179] It should be noted that the computer-readable medium shown in the embodiments of the present application may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium may be transmitted by any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0180] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Among them, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above module, program segment, or part of code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in an order different from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0181] The units involved in the embodiments described in this application can be implemented in software or in hardware, and the described units can also be provided in a processor. Among them, the names of these units do not constitute a limitation to the unit itself in some cases.

[0182] Another aspect of this application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer is caused to execute the method as described above. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist alone without being assembled into the electronic device.

[0183] Another aspect of this application also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above various embodiments.

[0184] The above embodiments are only preferred embodiments given to fully illustrate this application, and the protection scope of this application is not limited thereto. Equivalent substitutions or transformations made by those skilled in the art on the basis of this application are all within the protection scope of this application.

Claims

1. A digital intelligent archive management method based on machine vision, characterized in that: Includes steps: Obtaining the location distribution information of all the file bags in the filing cabinet in the previous storage period, and obtaining the door status of the filing cabinet, wherein the storage period is determined based on the door status; When the cabinet door is in an open state, a state change timestamp and a tilt video of the filing cabinet in an open state are obtained; shape features and grayscale features of each storage area of ​​multiple frames of images in the tilt video are extracted based on a pre-constructed mask; The tilted video is screened based on the shape feature and the grayscale feature to obtain a target frame and a timestamp of the target frame; Extracting a pressure data sequence of each pressure sensing unit in the filing cabinet in a time window starting from the state change timestamp and ending at the timestamp of the target frame; and determining a target position where the pressure changes based on the pressure data sequence, wherein the pressure data sequence includes pressure values ​​at multiple time points of a position; The target frame is segmented based on a pre-built mask extraction to obtain a target block containing the target position and a non-target block not containing the target position; a rough inspection based on grayscale features is performed on the non-target block, and a fine inspection based on grayscale features, geometric features and text recognition is performed on the target block to obtain a detection result for each block; The position distribution information of all the file bags in the current storage period is constructed based on the detection result of each block, and all the file bags in the filing cabinet are managed based on the position distribution information of the current storage period and the position distribution information of the previous storage period.

2. According to the method of claim 1, the digital intelligent archive management method based on machine vision is characterized in that: Extracting shape features and grayscale features of each storage area of ​​the multiple frame images in the oblique video based on a pre-built mask, including: Dynamically extracting frames from the tilted video to obtain multiple frames of images; Performing high-pass filtering and grayscale conversion processing on the multiple frames of images to obtain multiple frames of pre-processed images; Based on affine transformation, multiple frames of pre-processed images are converted from oblique viewing angles to normal viewing angles to obtain multiple frames of intermediate images; Performing AND operations on the pre-constructed mask and the multiple frames of intermediate images respectively to obtain multiple AND operation images; and marking the positions of the storage areas in the multiple AND operation images based on the pre-constructed mask; Extracting a target area that conforms to a pre-constructed first grayscale range from the plurality of AND operation images; Determine the storage area corresponding to each target area based on the marks of multiple target areas; extract the contour features of each storage area, extract the perimeter, area and rectangularity of the contour features, and obtain the shape features; The average grayscale and grayscale variance of each storage area are extracted to obtain the grayscale features.

3. The method for digital intelligent archive management based on machine vision according to claim 2 is characterized in that: The tilted video is screened based on the shape feature and the grayscale feature to obtain a target frame and a timestamp of the target frame, including: Comparing the shape features and grayscale features of the multiple frames of intermediate images with pre-constructed shape feature screening parameters and grayscale feature screening parameters, respectively, wherein the shape feature screening parameters include a perimeter tolerance range, an area tolerance range, and a rectangular tolerance range, and the grayscale feature screening parameters include a grayscale tolerance range and a grayscale variance tolerance range; The intermediate image whose shape features and grayscale features are matched with the pre-constructed shape feature screening parameters and grayscale feature screening parameters respectively is used as the complete image of the storage area that is not blocked; A closing timestamp when the cabinet door is closed is obtained, and a plurality of continuous complete images closest to the closing timestamp are used as target frames, and the timestamp of the target frame is determined.

4. The method for digital intelligent archive management based on machine vision according to claim 1, characterized in that: Determining a target position where pressure changes based on the pressure data sequence includes: Performing time series differentiation on the pressure values ​​at any adjacent time points in the pressure data sequence to obtain a differential sequence; Sliding along the differential sequence based on a pre-constructed sliding window, and calculating the sum of the pressure difference values ​​within the sliding window during each sliding; When the sum of the pressure differences is greater than a preset difference threshold, it is determined that the position corresponding to the pressure data sequence is the target position.

5. The method for digital intelligent archive management based on machine vision according to claim 1 is characterized in that: Perform a rough inspection of non-target blocks based on grayscale features, including: Perform high-pass filtering and grayscale conversion on non-target blocks to obtain a grayscale image ; For the grayscale image Perform brightness adjustment to obtain a brightness adjusted image , wherein the brightness adjustment image The mathematical expression is: In the formula, Adjust the pixels in the image for brightness The gray value of is the pixel in the grayscale image The gray value of is the minimum grayscale value in the grayscale image, is the maximum grayscale value in the grayscale image; Extract the pixel points whose grayscale values ​​fall into the preset second grayscale range from the brightness-adjusted image to construct the archive bag area; perform morphological processing on the archive bag area image to obtain the archive bag area image. ; Based on the portfolio area image Area and the grayscale image Area Calculate the effective proportion of archive bags in the current storage period , The mathematical expression is: Calculate the effective proportion of archive bags in the current storage period The effective proportion of the archive bags in the previous storage cycle Deviation rate , , at the deviation rate When the deviation rate is less than a preset threshold, it is determined that there is no file bag change in the storage unit corresponding to the current non-target block; When the deviation rate is greater than or equal to a preset threshold, the current non-target block is marked as containing the target block, and the target block is finely inspected based on grayscale features, geometric features, and text recognition.

6. A digital intelligent archive management method based on machine vision according to claim 1 or 5, characterized in that: Perform precision inspection on the target image blocks based on grayscale features, geometric features, and text recognition, including: Perform high-pass filtering and grayscale conversion on the target image block to obtain a target grayscale image ; For the target grayscale image Perform brightness adjustment to obtain the target brightness adjusted image ; Adjust the image from the target brightness Extracting pixel points whose grayscale values ​​fall into a preset second grayscale range to construct a target file bag area; and adjusting the image from the target brightness Extract contour features from Adjust the image to the target brightness The contours in the image are screened to obtain a target contour that meets the size of the file bag; the target file bag area and the target contour features are morphologically processed to obtain a file bag area image containing the target contour features. ; Adjusting the brightness of the target image based on the target contour feature Segmentation is performed to obtain a plurality of single images of the archive bags; the grayscale features and geometric features of the single image of each archive bag are extracted, and text recognition is performed on the single image of each archive bag to obtain text recognition results; and matching features are constructed based on the grayscale features, geometric features and text recognition results of the single image of each archive bag; Match the matching features of multiple file bags in the current storage period of the storage unit corresponding to the target block with the matching features of multiple file bags in the previous storage period to obtain a matching result; and determine the file bag change information of the storage unit based on the matching result, wherein the file bag change information includes addition, reduction and position change.

7. A digital intelligent archive management method based on machine vision according to claim 6, characterized in that: Matching the matching features of multiple archive bags in the current storage period of the storage unit corresponding to the target block with the matching features of multiple archive bags in the previous storage period to obtain a matching result, including: Calculate the current storage period of one of the archive bags The same as the archive bag from the previous storage cycle Grayscale similarity , geometric similarity And the cosine similarity of the text recognition results , where grayscale similarity and geometric similarity The mathematical expressions are: In the formula, For the The first storage cycle The average gray value of the file bag, For the The first storage cycle The average gray value of the file bag, For the The first storage cycle The gray value variance of the file bag, For the The first storage cycle The gray value variance of the file bag, For the The first storage cycle The perimeter of the outline of the file bag, For the The first storage cycle The perimeter of the outline of the file bag, For the The first storage cycle The area of ​​the outline of the file bag, For the The first storage cycle The area of ​​the outline of the file bag, For the The first storage cycle The aspect ratio of the outline of the portfolio, For the The first storage cycle The aspect ratio of the outline of the portfolio, is the first weight, is the second weight, is the third weight, is the fourth weight, is the fifth weight; Based on the grayscale similarity , geometric similarity And cosine similarity Calculate the matching degree , wherein the matching degree The mathematical expression is: In the formula, is the sixth weight, is the seventh weight, is the eighth weight; the file bags whose matching degree is greater than the preset matching degree threshold are matched to obtain the matching result.

8. The method for digital intelligent archive management based on machine vision according to claim 1, characterized in that: Managing all the file bags in the filing cabinet based on the location distribution information of the current storage period and the location distribution information of the previous storage period includes: Determine the difference information between the location distribution information of the current storage period and the location distribution information of the previous storage period; and change the storage status of the file bag and the retrieval information based on the difference information.

9. The method for digital intelligent archive management based on machine vision according to claim 1, characterized in that: Methods for determining the storage period include: Get the time difference between the cabinet door opening timestamp and the cabinet door closing timestamp; When the time difference is greater than the target duration, the period after the cabinet door is closed is taken as the next storage period.

10. A digital intelligent archive management system based on machine vision, characterized in that: include: An acquisition module, used to acquire the position distribution information of all the file bags in the filing cabinet in the previous storage period, and acquire the door status of the filing cabinet, wherein the storage period is determined based on the door status; A feature extraction module, used for obtaining a state change timestamp and a tilt video of the filing cabinet in the state where the cabinet door is open when the cabinet door is in the open state; extracting shape features and grayscale features of each storage area of ​​multiple frames of images in the tilt video based on a pre-built mask; A screening module, used for screening the oblique video based on the shape feature and the grayscale feature to obtain a target frame and a timestamp of the target frame; A pressure analysis module, for extracting a pressure data sequence of each pressure sensing unit in the filing cabinet in a time window from the state change timestamp to the target frame timestamp; and determining a target position where the pressure changes based on the pressure data sequence, wherein the pressure data sequence includes pressure values ​​at multiple time points of a position; A detection module is used to segment the target frame based on a pre-built mask extraction to obtain a target block containing the target position and a non-target block not containing the target position; perform a rough inspection based on grayscale features on the non-target block, and perform a fine inspection based on grayscale features, geometric features and text recognition on the target block to obtain a detection result for each block; A management module is used to construct the position distribution information of all the file bags in the current storage period based on the detection result of each block, and manage all the file bags in the filing cabinet based on the position distribution information of the current storage period and the position distribution information of the previous storage period.

Images