A fully automatic transmission crawler speed control discharging method and system

Abstract

The present invention relates to the technical field of conveyor speed control, and specifically to a method and system for controlling the speed of a fully automatic transmission crawler discharging, which obtains multiple frames of video images of the transmission crawler in the process of transporting materials, determines the centroid coordinates of each material in each frame of the video image; determines the maximum value of the motion difference of each material before and after each frame of the video image according to the centroid coordinates; classifies the materials whose maximum motion difference is greater than a preset difference threshold as first-classified materials, and classifies the materials whose maximum motion difference is below the preset difference threshold as second-classified materials; performs cluster analysis on the first-classified materials to obtain cluster analysis results; obtains speed adjustment parameters according to the centroid coordinates of the second-classified materials in the last frame of the video image and the cluster analysis results; and regulates the discharging speed of the transmission crawler according to the speed adjustment parameters. The scheme provided by the present invention improves the coordination between the material transmission speed of the transmission crawler and the material sorting speed.

Description

Technical Field

[0001] The invention relates to the technical field of conveyor speed control, and in particular to a full-automatic transmission crawler speed control discharging method and system. Background Art

[0002] A transmission track, also known as a chain conveyor or chain drive system, is a connector made of metal sheets or rubber and other materials. It is usually in the form of a ring or belt and is used to transmit force and motion. Transmission tracks are usually used in engineering machinery, agricultural machinery, material handling and transportation equipment. In the logistics and warehousing industries, transmission tracks can be used for automatic sorting and supply of materials. By controlling the discharge speed, the materials can be accurately delivered to the target location, improving the work efficiency and automation level of the logistics and warehousing links. However, for logistics sorting, it is necessary to reasonably control the material supply transmission rate according to the logistics sorting rate, so that the logistics sorting rate and the material supply transmission rate are more coordinated to improve the overall operating efficiency of the production line.

[0003] In the related technology, the discharging speed of the conveyor belt is usually regulated by manual adjustment or control according to the preset value of the conveyor system. The above control method is only applicable to the scene of uniform sorting of the conveyed materials. However, in the actual logistics sorting scene, the sorting speed of materials is not stable. In the scene where the material sorting speed is constantly changing, the above traditional control method is prone to the problem of poor coordination between the speed of conveyor belt material transmission and the sorting speed.

[0004] It can be seen that the traditional transmission crawler discharge control solution has technical problems such as poor flexibility, insufficient control reliability and stability. Summary of the invention

[0005] In order to solve the technical problems of poor flexibility, insufficient control reliability and stability of the traditional transmission crawler discharging control scheme, the purpose of the present invention is to provide a fully automatic transmission crawler speed control discharging method and system, and the technical scheme adopted is as follows:

[0006] In one aspect, the present invention provides a fully automatic transmission crawler speed controlled discharging method, the method comprising:

[0007] Acquire multiple frames of video images of the conveyor belt during the material transport process, and determine the centroid coordinates of each material in each frame of the video image;

[0008] Determine the maximum value of the motion difference of each of the materials before and after each frame of the video image according to the center of mass coordinates;

[0009] Classify the materials whose maximum motion difference is greater than a preset difference threshold as first-classified materials, and classify the materials whose maximum motion difference is less than the preset difference threshold as second-classified materials;

[0010] Performing cluster analysis on the first classified materials, determining the quantity corresponding to each type of materials in the first classified materials, and obtaining cluster analysis results;

[0011] Calculate the speed adjustment parameter of the transmission crawler according to the centroid coordinates of the second classified material in the last frame of the video image and the cluster analysis result;

[0012] The discharging speed of the transmission crawler is regulated according to the speed adjustment parameter.

[0013] According to a fully automatic transmission crawler speed-controlled material discharging method provided by the present invention, the determining of the centroid coordinates of each material in each frame of the video image includes:

[0014] Determining an image edge of each frame of the video image;

[0015] Using the left edge of the image edge as the ordinate axis and the lower edge of the image edge as the abscissa axis to establish a two-dimensional coordinate system;

[0016] The coordinate values ​​of the center of mass of each material in the two-dimensional coordinate system are determined respectively to obtain the center of mass coordinates.

[0017] According to a fully automatic transmission crawler speed control discharging method provided by the present invention, the maximum value of the movement difference of each material before and after each frame of video image is determined according to the centroid coordinates, including:

[0018] For each material, taking any frame as a segmentation point, determining the first motion state data before the segmentation point according to the centroid coordinates of the material in each frame of video image before the segmentation point;

[0019] Determine the second motion state data after the segmentation point according to the centroid coordinates of the material in each frame of video image after the segmentation point;

[0020] Determine a motion difference value of the material corresponding to the segmentation point according to the first motion state data and the second motion state data;

[0021] The maximum value of the motion difference values ​​corresponding to each frame as the segmentation point is taken as the maximum value of the motion difference of each material before and after each frame of the video image.

[0022] According to a fully automatic transmission crawler speed control discharging method provided by the present invention, the first motion state data before the segmentation point is determined according to the centroid coordinates of the material in each frame of video image before the segmentation point, including:

[0023] Determine the connecting line between the centroid coordinates and the coordinate origin in each frame of the video image of the material before the segmentation point, and obtain at least one first coordinate connecting line;

[0024] Determine a first cosine value of an angle between each of the first coordinate lines and the abscissa axis, and calculate a first cosine mean value based on the first cosine values ​​corresponding to all of the coordinate lines;

[0025] Determine a first change distance of the centroid coordinates of the material in adjacent frames of video images before the segmentation point, and calculate a first distance mean value based on the first change distances corresponding to all groups of adjacent frames of video images;

[0026] The first cosine mean and the first distance mean are used as the first motion state data.

[0027] According to a fully automatic transmission crawler speed control discharging method provided by the present invention, the second motion state data after the segmentation point is determined according to the centroid coordinates of the material in each frame of video image after the segmentation point, including:

[0028] Determine the connecting line between the centroid coordinates and the coordinate origin in each frame of the video image of the material after the segmentation point, and obtain at least one second coordinate connecting line;

[0029] Determine the second cosine value of the angle between each of the second coordinate lines and the abscissa axis, and calculate the second cosine mean value based on the second cosine values ​​corresponding to all the coordinate lines;

[0030] Determine the second change distance of the centroid coordinates of each group of adjacent frame video images of the material before the segmentation point, and calculate the second distance mean according to the second change distances corresponding to all groups of adjacent frame video images;

[0031] The second cosine mean and the second distance mean are used as the second motion state data.

[0032] According to a fully automatic transmission crawler speed control discharging method provided by the present invention, the motion difference value of the material corresponding to the split point is determined according to the first motion state data and the second motion state data, including:

[0033] Calculate the absolute value of the difference between the first cosine mean and the second cosine mean to obtain a first difference absolute value;

[0034] Calculate the absolute value of the difference between the first distance mean and the second distance mean to obtain a second difference absolute value;

[0035] multiplying the absolute value of the first difference by the absolute value of the second difference to obtain an absolute value product;

[0036] The absolute value product is linearly normalized to obtain the motion difference value of the material corresponding to the segmentation point.

[0037] According to a fully automatic transmission crawler speed control discharging method provided by the present invention, the speed adjustment parameter of the transmission crawler is calculated based on the centroid coordinates of the second classified material in the last frame of the video image and the cluster analysis result, including:

[0038] According to the quantities corresponding to each type of material in the cluster analysis results, determine the maximum quantity, the minimum quantity and the mean quantity;

[0039] Calculate a first intermediate parameter based on the maximum quantity, the minimum quantity, the mean quantity, the quantity corresponding to each type of material, and the total number of material types in the cluster analysis result;

[0040] Determine the straight-line distance between each of the second-classified materials and the abscissa axis according to the centroid coordinates of the second-classified materials in the last frame of the video image;

[0041] Calculate a second intermediate parameter based on the straight-line distance, the quantity of the second-classified materials, and the total quantity of the materials on the transmission track;

[0042] Based on the first intermediate parameter, the second intermediate parameter and the preset hyperparameter, the speed adjustment parameter of the transmission track is calculated.

[0043] According to a fully automatic transmission crawler speed control discharging method provided by the present invention, the speed adjustment parameter of the transmission crawler is calculated based on the first intermediate parameter, the second intermediate parameter and the preset hyperparameter, including:

[0044] Subtract the first intermediate parameter from the second intermediate parameter to obtain a parameter difference;

[0045] The parameter difference is summed with the preset hyperparameter to obtain the speed adjustment parameter of the transmission crawler.

[0046] According to a fully automatic transmission crawler speed control discharging method provided by the present invention, the discharging speed of the transmission crawler is regulated according to the speed adjustment parameter, comprising:

[0047] Determine an initial value of the discharging speed of the transmission crawler corresponding to the last frame sampling moment of the multiple frames of video images;

[0048] Based on the initial value of the discharging speed and the speed adjustment parameter, a target value of the discharging speed is calculated;

[0049] The initial value of the discharging speed is adjusted to the target value of the discharging speed.

[0050] On the other hand, the present invention also provides a fully automatic transmission crawler speed control discharging system, comprising:

[0051] An image acquisition device is installed at one end of the discharge port of the conveyor belt, and is used to capture video images of the conveyor belt during the material transportation process;

[0052] A control device is respectively connected to the image acquisition device and the transmission crawler, and the control device includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the program, any one of the above-mentioned fully automatic transmission crawler speed control and discharging methods is implemented.

[0053] The present invention has the following beneficial effects:

[0054] By acquiring multiple frames of video images of the transmission track in the process of transporting materials, and determining the centroid coordinates of each material in each frame of video images, and then determining the maximum value of the motion difference of each material before and after each frame of video images, after comparing the maximum value of the motion difference with the preset difference threshold, the materials on the transmission track can be divided into sorted first-classified materials and unsorted second-classified materials. Cluster analysis of the first-classified materials can obtain the corresponding quantity of each type of material, and then according to the cluster analysis results and the centroid coordinates of the second-classified materials in the last frame of video images, the speed adjustment parameters of the transmission track can be calculated, and finally the speed adjustment parameters can be used to accurately control the discharging speed of the transmission track. Since the discharging speed control process refers to the sorting situation of the sorted first-classified materials, the coordination between the material transmission speed and the material sorting speed of the transmission track is improved, and the overall operating efficiency of the transmission track is significantly improved, and the discharging control process is more flexible, stable and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1 A schematic flow chart of a fully automatic transmission crawler speed-controlled material discharging method provided by an embodiment of the present invention;

[0057] Figure 2 A schematic diagram of the structure of a fully automatic transmission crawler speed control discharging system provided by an embodiment of the present invention;

[0058] Figure 3 It is a structural schematic diagram of a control device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a fully automatic transmission crawler speed control discharging method and system proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0060] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0061] Combine the following Figures 1 to 3 The specific scheme of a fully automatic transmission crawler speed-controlled discharging method and system provided by the present invention is specifically described.

[0062] See also Figure 1 , which shows a schematic flow chart of a fully automatic transmission crawler speed-controlled discharging method provided by an embodiment of the present invention.

[0063] like Figure 1 As shown, the fully automatic transmission crawler speed control discharging method provided by the embodiment of the present invention can be executed by a control device with data receiving and sending and data processing functions. The method specifically includes the following steps:

[0064] Step 110: Acquire multiple frames of video images of the conveyor track during the material transport process, and determine the centroid coordinates of each material in each frame of the video image.

[0065] In the process of logistics sorting, the conveyor belt transports the materials placed on it from one end to the other. During the conveyor belt transmission process, multiple sorting ports will be set on both sides of the conveyor belt. Usually, the sorting ports use manual or mechanical methods to sort the materials that match the identification type of the sorting port (such as size, cargo type, transportation area, etc.). The discharging speed or running speed of the conveyor belt is related to the sorting speed. Therefore, the discharging speed of the conveyor belt needs to be adjusted according to the sorting speed.

[0066] In this embodiment, an image acquisition device can be installed at the transmission port of the transmission crawler, and specifically, the image acquisition device can be installed at one end of the discharge port of the transmission crawler. The image acquisition device can be a camera, a high-definition camera, etc., and the image acquisition device can be used to capture video images of the material during the transmission process on the transmission crawler. In practical applications, continuous multi-frame video images captured within a preset time can be obtained, for example, continuous multi-frame video images captured within 20 seconds can be obtained as a data basis within a control cycle. In some embodiments, the frame rate of the video image captured by the image acquisition device can be set to 60 frames.

[0067] Step 120: Determine the maximum value of the motion difference of each material before and after each frame of video image based on the centroid coordinates.

[0068] It is understandable that, since the running speed and direction of each material remain unchanged when the material is transported on the conveyor belt, when the material is sorted, its motion trajectory will change, and the displacement speed of the material in the video image will also change. Therefore, it is possible to analyze whether each material is sorted based on the motion difference of the material before and after each frame of the video image. To this end, this embodiment determines the maximum value of the motion difference of each material before and after each frame of the video image based on the centroid coordinates, providing an effective data basis for the subsequent analysis of whether it is sorted and the classification of materials.

[0069] Step 130: Classify materials whose maximum motion difference is greater than a preset difference threshold as first-classified materials, and classify materials whose maximum motion difference is less than the preset difference threshold as second-classified materials.

[0070] It should be noted that materials with a maximum motion difference greater than the preset difference threshold indicate that the motion trajectory and displacement speed of such materials have undergone significant changes during the transmission process, and can be determined as sorted materials, so the first-classified materials are sorted materials. Materials with a maximum motion difference below the preset difference threshold indicate that such materials have not undergone significant changes in motion trajectory and displacement speed during the transmission process, and can be determined as unsorted materials, so the second-classified materials are unsorted materials.

[0071] Step 140: Perform cluster analysis on the first classification materials, determine the corresponding quantity of each type of material in the first classification materials, and obtain cluster analysis results.

[0072] For the sorted first-class materials, the coordinates of the first-class materials can be mapped in a new coordinate plane, and then the mapped points are clustered into multiple clusters using an iterative self-organizing clustering analysis method (ISODATA), thereby realizing cluster analysis of the first-class materials.

[0073] Through the above cluster analysis, each cluster corresponds to a type of material, and different types of materials can be divided into different types of sorting ports. For each data point in a cluster, it corresponds to the number of materials sorted at the sorting port in multiple frames of video images. When the number of data points in different clusters is similar, it means that the number of materials sorted at different sorting ports in the current time period is similar. If the difference in the number of sorted materials at each sorting port is greater, it means that the sorting pressure of the current material for some sorting ports may be relatively large. In this case, it is necessary to slow down the transmission speed or discharge speed of the transmission crawler to prevent excessive sorting pressure at some sorting ports from causing accumulation of goods.

[0074] Step 150: Calculate the speed adjustment parameters of the transmission crawler according to the centroid coordinates of the second classification material in the last frame of the video image and the cluster analysis result.

[0075] In this embodiment, the speed adjustment parameter is a coefficient that can be directly used in the speed control process of the transmission track. Since the speed adjustment parameter is obtained through comprehensive calculation based on the cluster analysis results of the sorted first-category materials and the position conditions of the unsorted second-category materials, the speed control of the transmission track can be achieved more accurately.

[0076] Step 160: regulating the discharging speed of the transmission crawler according to the speed adjustment parameter.

[0077] This embodiment analyzes the movement trajectory of the material in the video image to classify the sorted and unsorted materials, and then analyzes the cluster analysis results of the sorted first-class materials and the centroid coordinates of the unsorted second-class materials to obtain the speed adjustment parameters of the transmission belt in the next control cycle. The discharge speed of the transmission belt is adjusted by the speed adjustment parameters, which improves the coordination between the material transmission speed of the transmission belt and the material sorting speed, thereby improving the overall operating efficiency of the transmission belt.

[0078] In one embodiment, determining the centroid coordinates of each material in each frame of video image specifically includes:

[0079] The first step is to determine the image edge of each frame of video image.

[0080] It can be understood that, since each frame of video image is a rectangular image with a fixed size, the image edges specifically include an upper edge, a lower edge, a left edge, and a right edge.

[0081] In the second step, the left edge of the image edge is used as the vertical axis, and the lower edge of the image edge is used as the horizontal axis to establish a two-dimensional coordinate system.

[0082] In this step, the scheme of determining the vertical axis and the horizontal axis is the more preferred scheme. In practical applications, other feasible coordinate axis determination schemes can also be adopted. For example, the right edge can be used as the vertical axis and the lower edge as the horizontal axis, or the right edge can be used as the vertical axis and the upper edge as the horizontal axis.

[0083] The third step is to determine the coordinate value of the center of mass of each material in the two-dimensional coordinate system and obtain the center of mass coordinates.

[0084] It is understandable that when using the transmission crawler to transport materials, there are certain differences in the quantity of different types of materials, and there is a certain randomness in the transmission of the quantity of different types of materials. This may result in a large number of some types of materials, which may be slower in the sorting process, while the number of some types of materials may be smaller, and the sorting speed is faster. If the transmission crawler speed is too fast at this time, the slower sorting port may not be able to sort the materials on the transmission crawler in time, resulting in subsequent sorting errors or accumulation of materials on the crawler, thereby affecting the overall material sorting efficiency.

[0085] In order to make the material transmission rate and the material sorting rate more coordinated, this embodiment first detects and tracks the materials in the captured video frames through the Mask R-CNN algorithm for subsequent analysis. The Mask R-CNN algorithm is an algorithm for target detection, which is used for tasks such as target detection, semantic recognition, and segmentation in video images.

[0086] In order to better analyze the transmission and sorting of materials on the transmission track, after determining the image edges of each frame of video image, this embodiment uses two of the edges to establish a two-dimensional coordinate system. Specifically, the left edge of each frame of video image is used as the vertical axis and the lower edge is used as the horizontal axis to establish a two-dimensional coordinate system, and the center of mass coordinates of each material in each frame of video image are marked for subsequent analysis.

[0087] In one embodiment, determining the maximum value of the motion difference of each material before and after each frame of video image based on the centroid coordinates specifically includes:

[0088] In the first step, for each material, any frame is taken as a segmentation point, and the first motion state data before the segmentation point is determined according to the centroid coordinates of the material in each frame of video image before the segmentation point.

[0089] It can be understood that the first motion state data can represent the motion change of the material before the segmentation point.

[0090] The second step is to determine the second motion state data after the segmentation point according to the centroid coordinates of the material in each frame of video image after the segmentation point.

[0091] Similarly, the second motion state data can represent the motion change of the material after the segmentation point.

[0092] The third step is to determine the motion difference value of the material corresponding to the split point according to the first motion state data and the second motion state data.

[0093] It can be understood that by comparing and analyzing the first motion state data and the second motion state data determined before and after the split point, the operation difference value of the material before and after the split point can be determined, and the motion difference value can characterize the motion difference of the material before and after the split point.

[0094] The fourth step is to use each frame as the maximum value of the motion difference value corresponding to the segmentation point as the maximum motion difference value of each material before and after each frame of the video image.

[0095] Since each frame of the video image can be used as a segmentation point for the motion difference analysis of the material, by using different video images as segmentation points, the motion difference values ​​corresponding to different segmentation points can be obtained, thereby obtaining multiple motion difference values, and then the maximum value thereof, i.e., the maximum motion difference value, can be determined.

[0096] In one embodiment, determining the first motion state data before the segmentation point according to the centroid coordinates of the material in each frame of video image before the segmentation point specifically includes:

[0097] The first step is to determine the connecting line between the centroid coordinates and the coordinate origin in each frame of the video image of the material before the segmentation point, and obtain at least one first coordinate connecting line.

[0098] It should be noted that, in this embodiment, the centroid coordinates and the coordinate origin can be obtained based on a two-dimensional coordinate system established with the lower edge as the horizontal axis and the left edge as the vertical axis.

[0099] The second step is to determine the first cosine value of the angle between each first coordinate line and the horizontal axis, and calculate the first cosine mean value based on the first cosine values ​​corresponding to all the coordinate lines.

[0100] In this step, each first coordinate connecting line and the horizontal coordinate axis can determine a first cosine value, thereby obtaining a plurality of first cosine values, and then calculating the average value to obtain the first cosine mean.

[0101] The third step is to determine the first change distance of the centroid coordinates of the material in the adjacent frame video images before the segmentation point, and calculate the first distance mean based on the first change distances corresponding to all groups of adjacent frame video images.

[0102] In this step, every two adjacent video images may be grouped together, and the first change distances may be determined respectively, thereby obtaining a plurality of first change distances, and then the first distance mean may be obtained by averaging the distances.

[0103] The fourth step is to use the first cosine mean and the first distance mean as the first motion state data.

[0104] In one embodiment, determining the second motion state data after the segmentation point according to the centroid coordinates of the material in each frame of video image after the segmentation point specifically includes:

[0105] The first step is to determine the connecting line between the centroid coordinates and the coordinate origin in each frame of the video image of the material after the segmentation point, and obtain at least one second coordinate connecting line.

[0106] The second step is to determine the second cosine value of the angle between each second coordinate line and the abscissa axis, and calculate the second cosine mean value based on the second cosine values ​​corresponding to all the coordinate lines.

[0107] The third step is to determine the second change distance of the centroid coordinates of each group of adjacent frame video images before the segmentation point, and calculate the second distance mean based on the second change distances corresponding to all groups of adjacent frame video images.

[0108] The fourth step is to use the second cosine mean and the second distance mean as the second motion state data.

[0109] It can be understood that the process of determining the second motion state data is substantially the same as the process of determining the first motion state data, except that the data objects they target are different.

[0110] In one embodiment, determining the motion difference value of the material corresponding to the split point according to the first motion state data and the second motion state data specifically includes:

[0111] In the first step, the absolute value of the difference between the first cosine mean and the second cosine mean is calculated to obtain the first absolute value of the difference.

[0112] The second step is to calculate the absolute value of the difference between the first distance mean and the second distance mean to obtain the second difference absolute value.

[0113] In the third step, the absolute value of the first difference is multiplied by the absolute value of the second difference to obtain the absolute value product.

[0114] The fourth step is to perform linear normalization on the absolute value product to obtain the motion difference value corresponding to the split point of the material.

[0115] In this embodiment, the calculation formula of the motion difference value is as follows:

[0116] (1)

[0117] In the formula, It indicates that the i-th material takes the L-th frame video image as the segmentation point, and the motion difference value of the motion before and after the corresponding segmentation point; It represents the mean of the sum of the cosine values ​​of the angles between the centroid coordinates of the material in each frame of the video image and the line connecting the origin of the coordinates and the horizontal axis in each frame before the Lth frame of the image, that is, the first cosine mean; It represents the mean of the sum of the cosine values ​​of the angles between the centroid coordinates of the material in each frame of the video image and the line connecting the origin of the coordinates and the horizontal axis in each frame after the Lth frame of the image, that is, the second cosine mean; It represents the mean of the sum of the distances of the centroid position changes of the i-th material between adjacent frames in each frame before the L-th frame image, that is, the first distance mean; It represents the mean of the sum of the distances of the center of mass position changes of the i-th material between adjacent frames in each frame after the L-th frame of the video image, that is, the second distance mean; represents the linear normalization function.

[0118] It represents the absolute value of the difference between the mean of the sum of the cosine values ​​of the angle between the centroid coordinates of the i-th material in each frame before the L-th frame of the video image and the line connecting the origin of the coordinates and the horizontal axis, and the mean of the sum of the cosine values ​​of the angle between the centroid coordinates of the i-th material in each frame after the L-th frame of the video image, that is, the first absolute value of the difference. Because when the material is sorted in the L-th frame of the image, when it is transported from the conveyor crawler to the sorting bin, the linear motion trajectory of the material on the conveyor crawler is changed, therefore, when the material is sorted in the L-th frame, the difference in the change of the front and rear motion trajectory of the material is relatively large.

[0119] It represents the absolute value of the difference between the mean of the sum of the distances of the centroid position changes of the i-th material between the adjacent frames in each frame before the L-th frame of the video image and the mean of the sum of the distances of the centroid position changes of the i-th material between the adjacent frames in each frame after the L-th frame of the video image, that is, the second absolute value of the difference. Because when the conveyor belt is transporting materials, the speed of the conveyor belt is kept stable in a short period of time, and when the materials are sorted, the speed of the movement away from the conveyor belt is different from the speed on the conveyor belt, so the displacement of the materials in the video image at the moment of transportation is also different. Therefore, the larger the value, the greater the difference in the movement speed of the i-th material before and after the L-th frame of the video image.

[0120] By traversing the motion difference value of each material in each frame of the multi-frame video image, when the motion difference value When the value is the largest, the maximum value of the motion difference satisfies When the coordinate position of the material in the video image of the corresponding frame is recorded, the same operation is performed on the other detected objects, and the corresponding centroid coordinates are obtained, thereby obtaining the first classified material.

[0121] When the maximum value of the motion difference of the material does not meet the above conditions, that is, the maximum value of the motion difference meets When the coordinate position of the material in the last frame of the video image is recorded, the second classification material is obtained.

[0122] It should be noted that the preset difference threshold You can choose a reasonable value based on the actual scenario requirements, for example, you can choose a value of 0.7.

[0123] In one embodiment, the speed adjustment parameters of the transmission track are calculated based on the centroid coordinates of the second classification material in the last frame of the video image and the cluster analysis results, specifically including:

[0124] The first step is to determine the maximum quantity, minimum quantity and mean quantity based on the quantity corresponding to each type of material in the cluster analysis results.

[0125] In the second step, the first intermediate parameter is calculated based on the maximum quantity, the minimum quantity, the mean quantity, the quantity corresponding to each type of material, and the total number of material types in the cluster analysis results.

[0126] The third step is to determine the straight-line distance between each second-classified material and the horizontal axis according to the centroid coordinates of the second-classified material in the last frame of the video image.

[0127] The fourth step is to calculate the second intermediate parameter based on the straight-line distance, the quantity of the second-classified materials and the total quantity of the materials on the transmission track.

[0128] The fifth step is to calculate the speed adjustment parameters of the transmission track based on the first intermediate parameter, the second intermediate parameter and the preset hyperparameter.

[0129] In one embodiment, based on the first intermediate parameter, the second intermediate parameter and the preset hyperparameter, the speed adjustment parameter of the transmission crawler is calculated, specifically including:

[0130] In the first step, the first intermediate parameter is subtracted from the second intermediate parameter to obtain a parameter difference.

[0131] In the second step, the parameter difference is summed with the preset hyperparameters to obtain the speed adjustment parameters of the transmission track.

[0132] In this embodiment, the calculation formulas of the first intermediate parameter, the second intermediate parameter and the speed adjustment parameter are as follows:

[0133] (2)

[0134] In the formula, , represent the first intermediate parameter and the second intermediate parameter of the transmission crawler respectively; W Indicates the speed adjustment parameter of the transmission track; 、 They represent the maximum and minimum number of data points in the cluster, that is, the maximum and minimum number of each type of material; Represents the number of data points in the rth cluster in the cluster, that is, the number of materials in the rth category; Represents the mean number of data points in the cluster, that is, the mean number of different types of materials; n Indicates the number of clusters, that is, the number of material types; Indicates the number of data points in the second classification material; m Indicates the total number of materials detected in the video image; 、 All represent linear normalized functions; Indicates the distance between the u-th material in the second classification and the horizontal axis; represents an exponential function with a natural constant as base; T It represents a hyperparameter used to calibrate the transmission rate of the transmission track, and in this embodiment, the value can be 0.8.

[0135] It represents the ratio of the maximum number of data points to the minimum number of data points in the cluster. The larger the value, the greater the difference in the uniformity of the number of data points in the cluster. This also means that the sorting pressure at the sorting port may be different. In order to reduce the pressure at the sorting port with a large sorting volume, the speed of the conveyor belt should be reduced. Therefore, the larger the value, the greater the reduction in the conveyor belt speed may be.

[0136] It represents the mean of the sum of the squares of the mean differences between the number of data points in each cluster and the number of data points in all clusters. The larger the value, the more uneven the sorting pressure at the sorting port may be, so as to avoid problems such as excessive sorting pressure at some sorting ports leading to untimely sorting. Therefore, the larger the value, the greater the drop in the speed of the transmission crawler.

[0137] It indicates the ratio of the number of data points in the second classification material to the total number of materials detected in the video image. The larger the value, the slower the material transportation speed on the conveyor belt is during the video image acquisition process, resulting in a longer waiting time at the sorting port. In this case, the conveyor belt speed may need to be adjusted upward. It represents the sum of the distances between the center of mass of the second-classified material in the last frame of the video image and the horizontal axis. The smaller the value, the The larger the value, the slower the speed of the transmission track may be, resulting in slower material transportation.

[0138] Therefore, when If the value is greater than 0, it means that the current transmission crawler speed may be too fast and the transmission rate may need to be adjusted down. If the value is less than 0, it means that the speed of the transmission track may be too slow and needs to be adjusted upward.

[0139] In one embodiment, the discharging speed of the transmission crawler is regulated according to the speed adjustment parameter, specifically including:

[0140] The first step is to determine the initial value of the discharging speed of the transmission track corresponding to the sampling moment of the last frame of the multi-frame video image.

[0141] The second step is to calculate the target value of the discharge speed based on the initial value of the discharge speed and the speed adjustment parameters.

[0142] The third step is to adjust the initial value of the discharging speed to the target value of the discharging speed.

[0143] In this embodiment, the calculation formula of the target value of the discharge speed of the transmission crawler is as follows:

[0144] (3)

[0145] In the formula, Indicates the discharging speed of the next transmission crawler at the last moment of the video frame, that is, the discharging speed target value of the transmission crawler; Indicates the speed of the transmission crawler at the last time node of the video frame, that is, the initial value of the discharge speed; W Indicates the speed adjustment parameter.

[0146] This embodiment analyzes the multiple frames of video frame images obtained by shooting to obtain the centroid coordinates and classification results of the materials in the video images, performs cluster analysis on the first classified materials, and then performs a comprehensive analysis based on the cluster analysis results and the centroid coordinates of the second classified materials to obtain the speed adjustment parameters of the transmission track, and finally uses the speed adjustment parameters to adjust the discharging speed of the transmission track, thereby achieving accurate and reliable speed control and discharging.

[0147] Based on the same general inventive concept, the present invention also protects a fully automatic transmission crawler speed controlled discharging system. The fully automatic transmission crawler speed controlled discharging system provided by the present invention is described below. The fully automatic transmission crawler speed controlled discharging system described below and the fully automatic transmission crawler speed controlled discharging method described above can be referenced to each other.

[0148] See also Figure 2 , which shows a schematic structural diagram of a fully automatic transmission crawler speed controlled discharging system provided by an embodiment of the present invention.

[0149] like Figure 2 As shown, the fully automatic transmission crawler speed control discharging system provided by the embodiment of the present invention specifically includes:

[0150] The image acquisition device 210 is installed at one end of the discharge port of the transmission crawler. The image acquisition device 210 is used to capture video images of the transmission crawler during the material transportation process and upload the video images to the control device 220.

[0151] The control device 220 is connected to the image acquisition device 210 and the transmission crawler respectively. The control device 220 includes a memory, a processor and a computer program stored in the memory and running on the processor. When the processor executes the program, the fully automatic transmission crawler speed control discharging method provided in the above embodiments is implemented.

[0152] It is understandable that the image acquisition device 210 can be a device capable of acquiring multiple frames of continuous video images, such as a camera or a high-definition camera. The control device 220 can be connected to the image acquisition device 210 in a wired or wireless manner.

[0153] Figure 3 Schematic diagram of the structure of the control device in the embodiment of the present invention.

[0154] like Figure 3As shown, the control device may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the fully automatic transmission crawler speed control discharging method provided in the above embodiments.

[0155] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0156] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the fully automatic transmission crawler speed controlled discharging method provided in the above-mentioned embodiments.

[0157] On the other hand, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the fully automatic transmission crawler speed-controlled discharging method provided in the above-mentioned embodiments.

[0158] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0159] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0160] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0161] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A fully automatic transmission crawler speed control discharging method, characterized in that: The method comprises: Acquire multiple frames of video images of the conveyor belt in the process of transporting materials, and determine the centroid coordinates of each material in each frame of the video image; Determine the maximum value of the motion difference of each material before and after each frame of video image according to the center of mass coordinates; Classify the materials whose maximum motion difference is greater than a preset difference threshold as first-classified materials, and classify the materials whose maximum motion difference is less than the preset difference threshold as second-classified materials; Performing cluster analysis on the first classified materials, determining the quantity corresponding to each type of materials in the first classified materials, and obtaining cluster analysis results; Calculate the speed adjustment parameter of the transmission crawler according to the centroid coordinates of the second classified material in the last frame of the video image and the cluster analysis result; Regulating the discharging speed of the transmission crawler according to the speed adjustment parameter; Determining the maximum value of the motion difference of each material before and after each frame of video image according to the centroid coordinates includes: For each material, taking any frame as a segmentation point, determining the first motion state data before the segmentation point according to the centroid coordinates of the material in each frame of video image before the segmentation point; Determine the second motion state data after the segmentation point according to the centroid coordinates of the material in each frame of video image after the segmentation point; Determine a motion difference value of the material corresponding to the segmentation point according to the first motion state data and the second motion state data; Taking each frame as the maximum value of the motion difference values ​​corresponding to the segmentation points as the maximum value of the motion difference of each material before and after each frame of the video image; The determining of the first motion state data before the segmentation point according to the centroid coordinates of the material in each frame of video image before the segmentation point includes: Determine the connecting line between the centroid coordinates and the coordinate origin in each frame of the video image of the material before the segmentation point, and obtain at least one first coordinate connecting line; Determine a first cosine value of an angle between each of the first coordinate lines and the abscissa axis, and calculate a first cosine mean value based on the first cosine values ​​corresponding to all of the coordinate lines; Determine a first change distance of the centroid coordinates of the material in adjacent frames of video images before the segmentation point, and calculate a first distance mean value based on the first change distances corresponding to all groups of adjacent frames of video images; Using the first cosine mean and the first distance mean as the first motion state data; The determining of the second motion state data after the segmentation point according to the centroid coordinates of the material in each frame of video image after the segmentation point comprises: Determine the connecting line between the centroid coordinates and the coordinate origin in each frame of the video image of the material after the segmentation point, and obtain at least one second coordinate connecting line; Determine the second cosine value of the angle between each of the second coordinate lines and the abscissa axis, and calculate the second cosine mean value based on the second cosine values ​​corresponding to all the coordinate lines; Determine the second change distance of the centroid coordinates of each group of adjacent frame video images of the material before the segmentation point, and calculate the second distance mean according to the second change distances corresponding to all groups of adjacent frame video images; Using the second cosine mean and the second distance mean as the second motion state data; The determining, according to the first motion state data and the second motion state data, a motion difference value of the material corresponding to the segmentation point includes: Calculate the absolute value of the difference between the first cosine mean and the second cosine mean to obtain a first difference absolute value; Calculate the absolute value of the difference between the first distance mean and the second distance mean to obtain a second difference absolute value; multiplying the absolute value of the first difference by the absolute value of the second difference to obtain an absolute value product; The absolute value product is linearly normalized to obtain the motion difference value of the material corresponding to the segmentation point; The speed adjustment parameter of the transmission crawler is calculated based on the centroid coordinates of the second classified material in the last frame of the video image and the cluster analysis result, including: According to the quantities corresponding to each type of material in the cluster analysis results, determine the maximum quantity, the minimum quantity and the mean quantity; Calculate a first intermediate parameter based on the maximum quantity, the minimum quantity, the mean quantity, the quantity corresponding to each type of material, and the total number of material types in the cluster analysis result; Determine the straight-line distance between each of the second-classified materials and the abscissa axis according to the centroid coordinates of the second-classified materials in the last frame of the video image; Calculate a second intermediate parameter based on the straight-line distance, the quantity of the second-classified materials, and the total quantity of the materials on the transmission track; Based on the first intermediate parameter, the second intermediate parameter and a preset hyperparameter, a speed adjustment parameter of the transmission crawler is calculated; The calculating the speed adjustment parameter of the transmission crawler based on the first intermediate parameter, the second intermediate parameter and the preset hyperparameter includes: Subtract the first intermediate parameter from the second intermediate parameter to obtain a parameter difference; Summing the parameter difference and the preset hyperparameter to obtain the speed adjustment parameter of the transmission crawler; The step of regulating the discharging speed of the transmission crawler according to the speed adjustment parameter includes: Determine an initial value of the discharging speed of the transmission crawler corresponding to the last frame sampling moment of the multiple frames of video images; Based on the initial value of the discharging speed and the speed adjustment parameter, a target value of the discharging speed is calculated; The initial value of the discharging speed is adjusted to the target value of the discharging speed.

2. A fully automatic transmission crawler speed control discharging method according to claim 1, characterized in that: Determining the centroid coordinates of each material in each frame of the video image includes: Determining an image edge of each frame of the video image; Using the left edge of the image edge as the ordinate axis and the lower edge of the image edge as the abscissa axis to establish a two-dimensional coordinate system; The coordinate values ​​of the center of mass of each material in the two-dimensional coordinate system are determined respectively to obtain the center of mass coordinates.

3. A fully automatic transmission crawler speed control discharging system, characterized in that: include: An image acquisition device is installed at one end of the discharge port of the conveyor belt, and is used to capture video images of the conveyor belt during the material transportation process; A control device is respectively connected to the image acquisition device and the transmission crawler, and the control device includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the program, a fully automatic transmission crawler speed control discharging method as described in any one of claims 1 to 2 is implemented.

Images