Intelligent logistics warehouse cargo weighing management system and method

Abstract

The invention discloses an intelligent logistics warehouse cargo weighing management system and method, and relates to the technical field of cargo weighing management, and the system comprises an initial image obtaining module, a contour midpoint obtaining module, a predicted weight obtaining module, a final image obtaining module, an observation weight obtaining module, and a final weight obtaining module. The contour midpoint acquisition module is used for acquiring an initial contour map of an initial cargo image based on a cargo boundary contour acquisition method and acquiring an initial contour midpoint based on the initial contour map, and the final weight acquisition module is used for calculating a mean value of a predicted weight and an observed weight and marking the mean value as a final weight. And taking the final weight as the weight of the goods. The goods weighing method and device are used for solving the problem that in an existing goods weighing technology, weighing is not accurate when the goods are weighed through a weighing conveying belt.

Description

Technical Field

[0001] The present invention relates to the technical field of cargo weighing management, and in particular to an intelligent logistics warehouse cargo weighing management system and method. Background Art

[0002] With the explosive development of the logistics industry, the traditional cargo weighing mode such as manual input of weighing data can no longer meet the needs of the modern logistics industry. Therefore, the semi-automatic weighing method is introduced to reduce manual operation steps, realize automatic weighing, automatic data upload, automatic record comparison and query, and improve the efficiency of logistics warehouse inbound and outbound weighing;

[0003] Semi-automatic weighing methods include weighing goods through weighing conveyor belts. Weighing conveyor belts can realize continuous and dynamic weighing of materials without stopping the conveyor belt, realizing continuous and uninterrupted weighing operations, improving the efficiency, accuracy, compliance and reducing costs of logistics and industrial production. However, the weighing conveyor belt causes unstable weighing data due to dynamic weighing. For example, if large goods have not all entered the weighing area, the weight weighed at this time is not accurate because they have not all entered the weighing area. For example, in a patent application with application publication number CN110704701A, a method and system for weighing goods in an intelligent logistics warehouse are disclosed. This method does not take into account the fact that when weighing goods using a weighing conveyor belt, the weighing weight obtained when the goods have not all entered the weighing area is not accurate. Therefore, in the existing cargo weighing technology, there is inaccurate weighing when weighing goods using a weighing conveyor belt. Summary of the invention

[0004] The present invention aims to solve one of the technical problems in the prior art to at least a certain extent, calculate the time when the midpoint of the starting contour reaches the midpoint of the weighing area through the data of the conveyor belt, obtain the predicted weight weighed at this time point, obtain the final contour map of the final cargo image based on the cargo boundary contour acquisition method, obtain the observed weight weighed when the entire final contour map is within the weighing area, calculate the average of the predicted weight and the observed weight, mark it as the final weight, and use the final weight as the weight of the cargo, so as to solve the problem of inaccurate weighing of cargo using a weighing conveyor belt in the existing cargo weighing technology.

[0005] To achieve the above-mentioned purpose, in a first aspect, the present invention provides an intelligent logistics warehouse cargo weighing management system, a starting image acquisition module, a contour midpoint acquisition module, a predicted weight acquisition module, a final image acquisition module, an observed weight acquisition module and a final weight acquisition module;

[0006] The starting image acquisition module is used to acquire a cargo image, which is marked as a starting cargo image;

[0007] The contour midpoint acquisition module is used to acquire a starting contour map of the starting cargo image based on a cargo boundary contour acquisition method, and acquire a starting contour midpoint based on the starting contour map;

[0008] The predicted weight acquisition module is used to acquire the data of the conveyor belt, calculate the time when the midpoint of the starting contour reaches the midpoint of the weighing area based on the data of the conveyor belt, and acquire the weight of the goods weighed at this time point, which is marked as the predicted weight;

[0009] The final image acquisition module is used to acquire a cargo image based on a weighing camera and mark it as a final cargo image;

[0010] The observed weight acquisition module is used to acquire a final contour map of the final cargo image based on the cargo boundary contour acquisition method, and acquire the cargo weight weighed when the entire final contour map is within the weighing area, which is marked as the observed weight;

[0011] The final weight acquisition module is used to obtain the average of the predicted weight and the observed weight, mark it as the final weight, and use the final weight as the weight of the goods.

[0012] Furthermore, the starting image acquisition module is configured with a camera installation strategy, and the camera installation strategy includes:

[0013] The weighing conveyor belt includes a weighing area and a buffer area, wherein the weighing area can transport goods and weigh the goods at the same time, and the buffer area is used to transport the goods to the weighing area, obtain the midpoint of the weighing area, and mark it as the weighing midpoint;

[0014] A starting line segment is set at the entrance of the buffer area. The starting line segment is parallel to the width direction of the weighing conveyor belt and its length is equal to the width of the weighing conveyor belt. The midpoint of the starting line segment is obtained and marked as the buffer starting point. Cameras are installed directly above the buffer starting point and the weighing midpoint, marked as the starting camera and the weighing camera respectively.

[0015] Furthermore, the contour midpoint acquisition module is configured with a strategy for acquiring a starting contour map, and the strategy for acquiring a starting contour map includes:

[0016] Acquire a starting cargo image based on a starting camera;

[0017] The cargo boundary contour acquisition method is used to obtain a cargo boundary contour map of the initial cargo map, which is marked as the initial contour map.

[0018] Furthermore, the cargo boundary contour acquisition method includes:

[0019] Get the R, G and B values ​​of each pixel in the RGB value of the starting cargo image;

[0020] Use the grayscale conversion formula to convert the RGB value into a grayscale value. The grayscale conversion formula is:

[0021] Qwh=β1*R+β2*G+β3*B; where Qwh is the grayscale value of the pixel in the starting cargo image, and β1, β2 and β3 are the R, G and B weights respectively;

[0022] Divide the grayscale value of 0-255 into E intervals, marked as grayscale intervals;

[0023] Count the frequency of the grayscale values ​​in each grayscale interval respectively, and mark it as grayscale interval frequency;

[0024] Draw a histogram with grayscale value as X-axis and grayscale interval frequency as Y-axis, marked as grayscale histogram;

[0025] Add up the frequencies of all grayscale intervals to get the total frequency, marked as F;

[0026] Mark the intervals with grayscale interval frequency less than F / E as small frequency areas, and mark the intervals other than small frequency areas as large frequency areas. Determine whether there are large frequency areas on both sides of the small frequency area. If so, mark the small frequency area as the final area.

[0027] The midpoint value of the abscissa of the final area is set as the background threshold; the grayscale value of the pixel points greater than or equal to the background threshold is set to 255, and the grayscale value of the pixel points less than the background threshold is set to 0, to obtain a binary image of the goods;

[0028] If a pixel with a grayscale value of 255 is adjacent to a pixel with a grayscale value of 0, the pixel with a grayscale value of 0 is marked as a pixel at the edge of the cargo;

[0029] The grayscale values ​​of all pixels in the cargo binary image that are not cargo boundary pixels are set to 255 and marked as the cargo boundary contour image.

[0030] Furthermore, the contour midpoint acquisition module is configured with a strategy for acquiring the midpoint of the starting contour, and the strategy for acquiring the midpoint of the starting contour includes:

[0031] Establish a first plane rectangular coordinate system, with the lower left corner of the starting contour as the origin, the long side of the starting contour parallel to the X-axis, the wide side of the starting contour parallel to the Y-axis, and place the starting contour in the first quadrant;

[0032] Set the coordinate point of the edge pixel of the cargo in the first plane rectangular coordinate system to (xi, yi), and obtain an x i The maximum coordinates of max ,y 0 ), get an x i The minimum value of (x min ,y1 ), get a y i The maximum coordinates of are: (x 0 ,y max ), get y i The coordinates of the minimum value are: (x 1 ,y min ); then obtain (x max ,y 0 ) and parallel to the Y axis, marked as the front segment, obtain the line segment through (x min ,y 1 ) and parallel to the Y axis, marked as the rear segment, obtain the line segment through (x 0 ,y max ) and parallel to the X-axis, marked as the left segment, obtain the line segment through (x 1 ,y min ) and parallel to the X-axis, marked as the right segment, where the front segment, the back segment, the left segment and the right segment form a rectangle; get the lower left corner point of the rectangle (x zx ,y zx ) and the upper right corner (x ys ,y ys ), get point Mark the midpoint of the starting contour.

[0033] Furthermore, the predicted weight acquisition module is configured with a predicted weight acquisition strategy, and the predicted weight acquisition strategy includes:

[0034] Get the distance between the buffer starting point and the weighing midpoint, marked as L;

[0035] Get the speed of the conveyor belt, marked as V;

[0036] The time from the starting point of the material buffer to the midpoint of weighing is calculated as: T = L / V;

[0037] Establish a second plane rectangular coordinate system, with the lower left corner of the starting cargo image as the origin, the long side of the starting cargo image parallel to the X-axis, the wide side of the starting cargo image parallel to the Y-axis, and the starting cargo image is placed in the first quadrant;

[0038] Get the coordinates of the buffer starting point;

[0039] When the horizontal coordinates of the midpoint of the starting contour and the starting point of the buffer are equal, the timing starts. When the time reaches T, the weighed weight of the goods is obtained and marked as the predicted weight.

[0040] Furthermore, the observed weight acquisition module is configured with an observed weight acquisition strategy, and the observed weight acquisition strategy includes:

[0041] A cargo boundary contour map of a final cargo image is obtained based on a cargo boundary contour acquisition method, and is marked as a final contour map;

[0042] Establish a third plane rectangular coordinate system, with the lower left corner of the final cargo image as the origin, the long side of the final cargo image parallel to the X-axis, the wide side of the final cargo image parallel to the Y-axis, and place the final cargo image in the first quadrant;

[0043] Set the coordinate point of the final contour map in the third plane rectangular coordinate system to (m i , n i ), get an m i The maximum coordinates of max , n 1 ), get an m i The minimum coordinate of min , n 2 );

[0044] Set the coordinate point of the weighing area in the third plane rectangular coordinate system as (q i , w i ), get a q i The maximum coordinate of max , w 1 ), get an m i The minimum coordinate of min , w 2 );

[0045] When m is satisfied at the same time max max With m min >q min , obtain the cargo weight displayed in the weighing area when the final cargo image is taken, and mark it as the observed weight.

[0046] Furthermore, the final weight acquisition module is configured with a final weight acquisition strategy, and the final weight acquisition strategy includes:

[0047] Label the predicted weight as G1 and the observed weight as Gc j ;

[0048] Delete Gc j The maximum and minimum values ​​in are marked as Gz i ;

[0049] Ask for Gz i The mean of

[0050] Find Gz i The mean square error is:

[0051] ​ Where MSE is Gz i The mean square error of , the value range of j is: j is a positive integer and 1≤j≤u;

[0052] Determine whether the MSE is less than the error threshold. If it is less than the error threshold, calculate the final weight as:

[0053] Where Gzz is the final weight;

[0054] The final weight shall be the weight of the cargo;

[0055] If it is greater than the error threshold, a cargo weighing abnormality signal is issued.

[0056] In a second aspect, the present invention provides a method for managing cargo weighing in an intelligent logistics warehouse, comprising the following steps: acquiring a cargo image and marking it as a starting cargo image;

[0057] Acquire a cargo boundary contour of a starting cargo image based on a cargo boundary contour acquisition method, and acquire a starting contour midpoint based on the cargo boundary contour;

[0058] Acquire the data of the conveyor belt, calculate the time when the midpoint of the starting contour reaches the midpoint of the weighing area based on the data of the conveyor belt, obtain the weight of the goods weighed at this time point, and mark it as the predicted weight;

[0059] Obtain a cargo image and mark it as a final cargo image;

[0060] The final contour of the final cargo image is obtained based on the cargo boundary contour acquisition method, and the cargo weight weighed when the final contour is in the entire weighing area is obtained and marked as the observed weight;

[0061] Find the mean of the predicted weight and the observed weight, mark it as the final weight, and use the final weight as the weight of the goods.

[0062] Beneficial effects of the present invention: The present invention calculates the time when the midpoint of the starting contour reaches the midpoint of the weighing area through the data of the conveyor belt, obtains the predicted weight weighed at the time point, obtains the final contour map of the final cargo image based on the cargo boundary contour acquisition method, obtains the observed weight weighed when the entire final contour map is in the weighing area, calculates the average of the predicted weight and the observed weight, marks it as the final weight, and uses the final weight as the weight of the cargo. The advantage is that, by combining the image and the weighing conveyor belt analysis, the cargo weight is obtained when the cargo is completely in the weighing area, and then the appropriate cargo weight is selected to calculate the average, so that the final obtained cargo weight is more accurate;

[0063] The present invention obtains the starting contour midpoint and the weighing midpoint, and has the advantage that when the starting contour midpoint is close to the weighing midpoint, that is, the goods are in the middle of the weighing area, the weighing weight obtained at this moment is closest to the actual weight of the goods, thereby increasing the accuracy of weighing. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 is a functional block diagram of the system of the present invention;

[0065] Figure 2 is a schematic diagram of a top view of a conveyor belt of the present invention;

[0066] Figure 3 is a schematic diagram of a grayscale histogram of the present invention;

[0067] Figure 4 A schematic diagram of obtaining the midpoint of the starting contour of the present invention;

[0068] Figure 5 A flow chart of the steps of the present invention. DETAILED DESCRIPTION

[0069] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0070] Example 1, please refer to Figure 1 As shown, an intelligent logistics warehouse cargo weighing management system includes: a starting image acquisition module, a contour midpoint acquisition module, a predicted weight acquisition module, a final image acquisition module, an observed weight acquisition module and a final weight acquisition module;

[0071] The starting image acquisition module is used to acquire a cargo image, which is marked as a starting cargo image; the starting cargo image is a frame of image acquired by the starting camera;

[0072] The initial image acquisition module is configured with a camera installation strategy, which includes:

[0073] See also Figure 2 As shown, the weighing conveyor belt includes a weighing area and a buffer area, wherein the weighing area can transport goods and weigh the goods at the same time, and the buffer area is used to transport the goods to the weighing area, obtain the midpoint of the weighing area, and mark it as the weighing midpoint; set the weighing midpoint, and the goods are weighed most accurately and stably at the weighing midpoint;

[0074] A starting line segment is set at the entrance of the buffer area. The starting line segment is parallel to the width direction of the weighing conveyor belt and its length is equal to the width of the weighing conveyor belt. The midpoint of the starting line segment is obtained and marked as the buffer starting point. Cameras are installed directly above the buffer starting point and the weighing midpoint, marked as the starting camera and the weighing camera respectively. The buffer area can transport goods while allowing the goods to pass the weighing smoothly. Setting the buffer starting point facilitates the subsequent calculation of the time when the goods arrive at the weighing midpoint.

[0075] The contour midpoint acquisition module is used to acquire a starting contour map of a starting cargo image based on a cargo boundary contour acquisition method, and acquire a starting contour midpoint based on the starting contour map;

[0076] The contour midpoint acquisition module is configured with a strategy for obtaining a starting contour map, which includes:

[0077] Acquire a starting cargo image based on a starting camera;

[0078] The cargo boundary contour acquisition method is used to obtain a cargo boundary contour map of the initial cargo map, which is marked as the initial contour map.

[0079] The method for obtaining the cargo boundary contour includes:

[0080] Get the R, G and B values ​​of each pixel in the RGB value of the starting cargo image;

[0081] Use the grayscale conversion formula to convert the RGB value into a grayscale value. The grayscale conversion formula is:

[0082] Qwh=β1*R+β2*G+β3*B; Qwh is the gray value of the pixel in the starting cargo image, β1, β2 and β3 are the weights of R, G and B respectively; weighted average gray value conversion, the weighted average method will give different weights to the three RGB color channels according to the different sensitivities of the human eye to red, green and blue, specifically: Qwh=0.299*R+0.587*G+0.114*B;

[0083] Divide the grayscale value of 0-255 into E intervals on average, marked as grayscale intervals; the setting of E can find the background threshold between the grayscale values ​​of the goods and the weighing conveyor belt according to the subsequent histogram. If the background threshold cannot be found, E can be appropriately increased;

[0084] Count the frequency of the grayscale values ​​in each grayscale interval respectively, and mark it as grayscale interval frequency;

[0085] Draw a histogram with grayscale value as X-axis and grayscale interval frequency as Y-axis, marked as grayscale histogram;

[0086] Add up the frequencies of all grayscale intervals to get the total frequency, marked as F;

[0087] The intervals with grayscale interval frequency less than F / E are marked as small frequency areas, and the intervals other than the small frequency areas are marked as large frequency areas. It is determined whether there are large frequency areas on both sides of the small frequency area. If so, the small frequency area is marked as the final area; that is, the grayscale value between the goods and the weighing conveyor belt in the final area; the principle is that the grayscale values ​​of the background and the goods occupy the main part of the grayscale image, and the grayscale value distribution ranges of the background and the goods are different, that is, a double peak trend will appear. Finding the value between the double peaks can distinguish the grayscale values ​​of the background and the goods;

[0088] The midpoint value of the abscissa of the final area is set as the background threshold; the grayscale value of the pixel points greater than or equal to the background threshold is set to 255, and the grayscale value of the pixel points less than the background threshold is set to 0, to obtain a binary image of the goods;

[0089] In practical applications, set E to 8 and draw a grayscale histogram. Figure 3 As shown;

[0090] If a pixel with a grayscale value of 255 is adjacent to a pixel with a grayscale value of 0, the pixel with a grayscale value of 0 is marked as a pixel at the edge of the cargo;

[0091] The grayscale values ​​of all pixels in the cargo binary image that are not cargo boundary pixels are set to 255, marking it as a cargo boundary outline image; only the cargo boundary outline is retained;

[0092] The contour midpoint acquisition module is configured with a strategy for acquiring the starting contour midpoint. The strategy for acquiring the starting contour midpoint includes:

[0093] Establish the first plane rectangular coordinate system, take the lower left corner of the starting outline as the origin, the long side of the starting outline is parallel to the X-axis, the wide side of the starting outline is parallel to the Y-axis, and the starting outline is placed in the first quadrant; establish the first plane rectangular coordinate system for coordinate data; the lower left corner of the starting outline is the lower left corner of the entire image, not just the minimum angle of the outline, that is, the starting outline is the same size as the starting cargo image;

[0094] Obtain all cargo edge pixel points, and mark all cargo edge pixel points as cargo edge contours;

[0095] See also Figure 4 As shown in the figure, the coordinate point of the edge pixel of the goods in the first plane rectangular coordinate system is set to (xi, yi), and an x i The maximum coordinates of max ,y 0 ), get an x i The minimum value of (x min ,y 1 ), get a y i The maximum coordinates of0 ,y max ), get y i The coordinates of the minimum value are: (x 1 ,y min ); then obtain (x max ,y 0 ) and parallel to the Y axis, marked as the front segment, obtain the line segment through (x min ,y 1 ) and parallel to the Y axis, marked as the rear segment, obtain the line segment through (x 0 ,y max ) and parallel to the X-axis, marked as the left segment, obtain the line segment through (x 1 ,y min ) and parallel to the X-axis, marked as the right segment, where the front segment, the back segment, the left segment and the right segment form a rectangle; get the lower left corner point of the rectangle (x zx ,y zx ) and the upper right corner (x ys ,y ys ), get point Mark as the midpoint of the starting contour;

[0096] The specific method for obtaining the coordinate points of the edge pixel points of the goods is as follows: obtaining the center point of all the edge pixel points of the goods, and taking the center point of the pixel point as the coordinate point; obtaining the midpoint of the starting contour because the contour of the goods may have an irregular shape, and the center point of the goods is difficult to obtain, obtaining an outer rectangle, obtaining the midpoint of the outer rectangle, and taking the midpoint of the outer rectangle as the midpoint of the boundary contour of the goods, that is, the center point of the goods;

[0097] In practical applications, get an x i The maximum coordinates of are: (12, 6), get an x i The minimum value is: (6, 6), get a y i The maximum coordinates of are: (8, 13), get y i The coordinates of the minimum value are: (8, 2); then obtain the line segment passing through (12, 6) and parallel to the Y axis, marked as the front line segment, obtain the line segment passing through (6, 6) and parallel to the Y axis, marked as the back line segment, obtain the line segment passing through (8, 13) and parallel to the X axis, marked as the left line segment, obtain the line segment passing through (8, 2) and parallel to the X axis, marked as the right line segment, where the front line segment, the back line segment, the left line segment and the right line segment form a rectangle; obtain the lower left corner point (2, 6) and the upper right corner point (12, 13) of the rectangle, (2+12) / 2=7, (6+13) / 2=9.5, that is, (7, 9.5) is the midpoint of the starting contour.

[0098] The predicted weight acquisition module is used to obtain the data of the conveyor belt, calculate the time when the midpoint of the starting contour reaches the midpoint of the weighing area based on the data of the conveyor belt, obtain the weight of the goods weighed at this time point, and mark it as the predicted weight;

[0099] The predicted weight acquisition module is configured with a predicted weight acquisition strategy, which includes:

[0100] Get the distance between the buffer starting point and the weighing midpoint, marked as L;

[0101] Get the speed of the conveyor belt, marked as V;

[0102] The time from the starting point of the material buffer to the midpoint of weighing is calculated as: T = L / V;

[0103] A second plane rectangular coordinate system is established, with the lower left corner of the starting cargo image as the origin, the long side of the starting cargo image parallel to the X-axis, the wide side of the starting cargo image parallel to the Y-axis, and the starting cargo image is placed in the first quadrant; the starting contour image and the starting cargo image have the same size under the same camera, that is, the starting contour image and the starting cargo image are in the same coordinate system, and the coordinates of the buffer starting point and the coordinates of the midpoint of the starting contour are comparable;

[0104] Get the coordinates of the buffer starting point;

[0105] When the horizontal coordinates of the midpoint of the starting contour and the starting point of the buffer are equal, the timing starts. When the time reaches T, the weighed weight of the goods is obtained and marked as the predicted weight.

[0106] In actual application, the distance between the buffer starting point and the weighing midpoint is obtained as L = 5m, the speed of the conveyor belt is obtained as V = 2m / s, and the time from the goods buffer starting point to the weighing midpoint is calculated as: T = 5 / 2 = 2.5s. When the horizontal coordinates of the starting contour midpoint and the buffer starting point are equal, the timing starts. When the time reaches 2.5s, the weighed weight of the goods is obtained as 612g, that is, the predicted weight is 612g;

[0107] The final image acquisition module is used to acquire the cargo image based on the weighing camera and mark it as the final cargo image;

[0108] The observed weight acquisition module is used to acquire a final contour map of the final cargo image based on the cargo boundary contour acquisition method, and acquire the cargo weight weighed when the entire final contour map is within the weighing area, which is marked as the observed weight;

[0109] The observation weight acquisition module is configured with an observation weight acquisition strategy, which includes:

[0110] A cargo boundary contour map of a final cargo image is obtained based on a cargo boundary contour acquisition method, and is marked as a final contour map;

[0111] Establish a third plane rectangular coordinate system, with the lower left corner of the final cargo image as the origin, the long side of the final cargo image parallel to the X-axis, the wide side of the final cargo image parallel to the Y-axis, and place the final cargo image in the first quadrant;

[0112] Set the coordinate point of the final contour in the third plane rectangular coordinate system to (m i , n i ), get an m i The maximum coordinates of max , n 1 ), get an m i The minimum coordinate of min , n 2 );

[0113] Set the coordinate point of the weighing area in the third plane rectangular coordinate system as (q i , w i ), get a q i The maximum coordinate of max , w 1 ), get an m i The minimum coordinate of min , w 2 );

[0114] When m is satisfied at the same time max max With m min >q min When the final cargo image is taken, the cargo weight displayed in the weighing area is obtained and marked as the observed weight; in order to realize the cargo weight displayed in the weighing area when the entire cargo is in the weighing area, that is, when the minimum coordinate of the cargo on the X-axis is greater than the minimum coordinate of the weighing area and the maximum coordinate of the cargo on the X-axis is less than the maximum coordinate of the weighing area, the entire cargo is in the weighing area;

[0115] In practical applications, get an m i The maximum coordinates of m are marked as (12, 5). i The minimum coordinate of q is marked as (2, 5); get a i The maximum coordinate of m is marked as (50, 0). i The minimum coordinate of is marked as (0, 0); 12<50 and 2>0 are satisfied at the same time, and the weight of the goods displayed in the weighing area when the final cargo image is taken is 613g, that is, 613g is one of the observed weights;

[0116] The final weight acquisition module is used to obtain the mean of the predicted weight and the observed weight, marked as the final weight, and the final weight is used as the weight of the goods; ​

[0117] The final weight acquisition module is configured with a final weight acquisition strategy, which includes:

[0118] Label the predicted weight as G1 and the observed weight as Gc j ;

[0119] Delete Gc j The maximum and minimum values ​​in are marked as Gz i ;

[0120] Ask for Gz i The mean of

[0121] Find Gz i The mean square error is:

[0122] Where MSE is Gz i The mean square error of , the value range of j is: j is a positive integer and 1≤j≤u;

[0123] Determine whether the MSE is less than the error threshold. If it is less than the error threshold, calculate the final weight as:

[0124] Where Gzz is the final weight;

[0125] The error threshold is set. If the observed weight fluctuates greatly, that is, the observed weight tested is unstable, the weighing data is inaccurate and cannot be used as the weighing value of the goods this time. Therefore, the smaller the error threshold is set, the better. That is, the difference between each group of data cannot be too large. In the error threshold setting process, for example, the difference between each group of observed weight and the mean of the observed weight cannot exceed 2g. There are three groups of data, that is, the error threshold = 4g;

[0126] If it is greater than the error threshold, a signal of abnormal cargo weighing will be issued;

[0127] In practical applications, if there is a group of Gc j One of 613g, 612g, 614g, 611g, 610g; delete Gc j The maximum value is 614g and the minimum value is 610g, Gz i is one of 613g, 612g, 611g; find Gz i The mean value of Find Gz i The mean square error is: MSE = 2 / 3g, MSE = 2 / 3g is less than the error threshold = 4g, and the final weight is calculated to be: Gzz = 612g, and 612g is taken as the weight of the goods.

[0128] Example 2, please refer to Figure 5As shown, a method for managing cargo weighing in an intelligent logistics warehouse includes the following steps:

[0129] Step S1, obtaining a cargo image and marking it as a starting cargo image; Step S1 includes the following sub-steps:

[0130] Step S101, the weighing conveyor includes a weighing area and a buffer area, wherein the weighing area can transport goods and weigh the goods at the same time, and the buffer area is used to transport the goods to the weighing area, obtain the midpoint of the weighing area, and mark it as the weighing midpoint;

[0131] Step S102, set a starting line segment at the entrance of the buffer area, the starting line segment is parallel to the width direction of the weighing conveyor belt, and the length is equal to the width of the weighing conveyor belt, obtain the midpoint of the starting line segment, and mark it as the buffer starting point. Cameras are installed directly above the buffer starting point and the weighing midpoint, which are marked as the starting camera and the weighing camera respectively.

[0132] Step S2, obtaining the cargo boundary contour of the initial cargo image based on the cargo boundary contour obtaining method, and obtaining the midpoint of the initial contour based on the cargo boundary contour; Step S2 includes the following sub-steps:

[0133] Step S201, acquiring a starting cargo image based on a starting camera;

[0134] Step S202, using a cargo boundary contour acquisition method to acquire a cargo boundary contour map of a starting cargo map, and marking it as a starting contour map; Step S202 includes the following sub-steps:

[0135] Step S20201, obtaining the R, G and B values ​​of the RGB value of each pixel of the starting cargo image;

[0136] Step S20202, convert the RGB value into a grayscale value using a grayscale conversion formula, the grayscale conversion formula is:

[0137] Qwh=β1*R+β2*G+β3*B; where Qwh is the grayscale value of the pixel in the starting cargo image, and β1, β2 and β3 are the R, G and B weights respectively;

[0138] Step S20203, divide the grayscale values ​​of 0-255 into E intervals on average, marked as grayscale intervals;

[0139] Step S20204, respectively counting the frequency of the grayscale value of each grayscale interval, and marking it as grayscale interval frequency;

[0140] Step S20205, draw a histogram with the gray value as the X-axis and the gray interval frequency as the Y-axis, marked as gray histogram;

[0141] Step S20206, add up the frequencies of all grayscale intervals to obtain a total frequency, marked as F;

[0142] Step S20207, marking the intervals where the grayscale interval frequency is less than F / E as small frequency areas, marking the intervals other than the small frequency areas as large frequency areas, and determining whether there are large frequency areas on both sides of the small frequency area. If so, marking the small frequency area as the final area;

[0143] Step S20208, setting the midpoint value of the horizontal coordinate of the final area as the background threshold; setting the grayscale value of the pixel points greater than or equal to the background threshold to 255, and setting the grayscale value of the pixel points less than the background threshold to 0, to obtain a binary image of the goods;

[0144] Step S20209: If a pixel with a grayscale value of 255 is adjacent to a pixel with a grayscale value of 0, the pixel with a grayscale value of 0 is marked as a cargo edge pixel; the grayscale values ​​of all pixels in the cargo binary image that are not cargo boundary pixels are set to 255, and the image is marked as a cargo boundary contour image.

[0145] Step S203, establishing a first plane rectangular coordinate system, taking the lower left corner of the starting outline as the origin, the long side of the starting outline is parallel to the X-axis, the wide side of the starting outline is parallel to the Y-axis, and placing the starting outline in the first quadrant;

[0146] Step S204, set the coordinate point of the edge pixel of the goods in the first plane rectangular coordinate system as (xi, yi), and obtain an x i The maximum coordinates of max ,y 0 ), get an x i The minimum value of (x min ,y 1 ), get a y i The maximum coordinates of 0 ,y max ), get y i The coordinates of the minimum value are: (x 1 ,y min ); then obtain (x max ,y 0 ) and parallel to the Y axis, marked as the front segment, obtain the line segment through (x min ,y 1 ) and parallel to the Y axis, marked as the rear segment, obtain the line segment through (x 0 ,y max ) and parallel to the X-axis, marked as the left segment, obtain the line segment through (x 1 ,y min) and parallel to the X-axis, marked as the right segment, where the front segment, the back segment, the left segment and the right segment form a rectangle; get the lower left corner point of the rectangle (x zx ,y zx ) and the upper right corner (x ys ,y ys ), get point Mark the midpoint of the starting contour.

[0147] Step S3, obtaining the data of the conveyor belt, calculating the time when the midpoint of the starting contour reaches the midpoint of the weighing area based on the data of the conveyor belt, obtaining the weight of the goods weighed at this time point, and marking it as the predicted weight; Step S3 includes the following sub-steps:

[0148] Step S301, obtaining the distance between the buffer starting point and the weighing midpoint, marked as L;

[0149] Step S302, obtaining the speed of the conveyor belt, marked as V;

[0150] Step S303, calculating the time from the starting point of the goods buffer to the midpoint of the weighing: T = L / V;

[0151] Step S304, establishing a second plane rectangular coordinate system, taking the lower left corner of the initial cargo image as the origin, with the long side of the initial cargo image parallel to the X-axis, and the wide side of the initial cargo image parallel to the Y-axis, and placing the initial cargo image in the first quadrant;

[0152] Step S305, obtaining the coordinates of the buffer starting point;

[0153] Step S306, when the horizontal coordinates of the midpoint of the starting contour and the buffer starting point are equal, start timing, and when the time reaches T, obtain the weighed weight of the goods and mark it as the predicted weight.

[0154] Step S4, obtaining a cargo image and marking it as a final cargo image.

[0155] Step S5, obtaining the final contour of the final cargo image based on the cargo boundary contour obtaining method, obtaining the cargo weight weighed when the final contour is within the entire weighing area, and marking it as the observed weight; Step S5 includes the following sub-steps:

[0156] Step S501, obtaining a cargo boundary contour map of a final cargo image based on a cargo boundary contour obtaining method, and marking it as a final contour map;

[0157] Step S502, establishing a third plane rectangular coordinate system, taking the lower left corner of the final cargo image as the origin, with the long side of the final cargo image parallel to the X-axis, and the wide side of the final cargo image parallel to the Y-axis, and placing the final cargo image in the first quadrant;

[0158] Step S503, setting the coordinate point of the final contour image in the third plane rectangular coordinate system to (m i , n i ), get an m i The maximum coordinates of max , n 1 ), get an m i The minimum coordinate of min , n 2 );

[0159] Step S504, setting the coordinate point of the weighing area in the third plane rectangular coordinate system to (q i , w i ), get a q i The maximum coordinate of max , w 1 ), get an m i The minimum coordinate of min , w 2 );

[0160] Step S505: When m max max With m min >q min , obtain the cargo weight displayed in the weighing area when the final cargo image is taken, and mark it as the observed weight.

[0161] Step S6, calculating the average of the predicted weight and the observed weight, marking it as the final weight, and taking the final weight as the weight of the goods; Step S6 includes the following sub-steps:

[0162] Step S601, mark the predicted weight as G1 and the observed weight as Gc j ;

[0163] Step S602, delete Gc j The maximum and minimum values ​​in are marked as Gz i ;

[0164] Step S603, find Gz i The mean of

[0165] Step S604, obtain Gz i The mean square error is:

[0166] Where MSE is Gz i The mean square error of , the value range of j is: j is a positive integer and 1≤j≤u;

[0167] ​Step S605, determine whether the MSE is less than the error threshold. If so, calculate the final weight as:

[0168] Where Gzz is the final weight; the final weight is taken as the weight of the goods;

[0169] Step S606: If the value is greater than the error threshold, a cargo weighing abnormality signal is issued.

[0170] It should be understood by those skilled in the art that the embodiments of the present invention can be provided as methods, systems or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0171] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

Claims

1. An intelligent logistics warehouse cargo weighing management system, characterized in that: include: A starting image acquisition module, a contour midpoint acquisition module, a predicted weight acquisition module, a final image acquisition module, an observed weight acquisition module, and a final weight acquisition module; The starting image acquisition module is used to acquire a cargo image, which is marked as a starting cargo image; The contour midpoint acquisition module is used to acquire a starting contour map of the starting cargo image based on a cargo boundary contour acquisition method, and acquire a starting contour midpoint based on the starting contour map; The predicted weight acquisition module is used to acquire the data of the conveyor belt, calculate the time when the midpoint of the starting contour reaches the midpoint of the weighing area based on the data of the conveyor belt, and acquire the weight of the goods weighed at this time point, which is marked as the predicted weight; The final image acquisition module is used to acquire a cargo image based on a weighing camera and mark it as a final cargo image; The observed weight acquisition module is used to acquire a final contour map of the final cargo image based on the cargo boundary contour acquisition method, and acquire the cargo weight weighed when the entire final contour map is within the weighing area, which is marked as the observed weight; The final weight acquisition module is used to obtain the average of the predicted weight and the observed weight, mark it as the final weight, and use the final weight as the weight of the goods.

2. The intelligent logistics warehouse cargo weighing management system according to claim 1 is characterized in that: The starting image acquisition module is configured with a camera installation strategy, and the camera installation strategy includes: The weighing conveyor belt includes a weighing area and a buffer area, wherein the weighing area can transport goods and weigh the goods at the same time, and the buffer area is used to transport the goods to the weighing area, obtain the midpoint of the weighing area, and mark it as the weighing midpoint; A starting line segment is set at the entrance of the buffer area. The starting line segment is parallel to the width direction of the weighing conveyor belt and its length is equal to the width of the weighing conveyor belt. The midpoint of the starting line segment is obtained and marked as the buffer starting point. Cameras are installed directly above the buffer starting point and the weighing midpoint, marked as the starting camera and the weighing camera respectively.

3. The intelligent logistics warehouse cargo weighing management system according to claim 2 is characterized in that: The contour midpoint acquisition module is configured with a strategy for acquiring a starting contour map, and the strategy for acquiring a starting contour map includes: Acquire a starting cargo image based on a starting camera; The cargo boundary contour acquisition method is used to obtain a cargo boundary contour map of the initial cargo map, which is marked as the initial contour map.

4. The intelligent logistics warehouse cargo weighing management system according to claim 3 is characterized in that: The method for obtaining the cargo boundary contour includes: Get the R, G and B values ​​of each pixel in the RGB value of the starting cargo image; Use the grayscale conversion formula to convert the RGB value into a grayscale value. The grayscale conversion formula is: Qwh=β1*R+β2*G+β3*B; where Qwh is the grayscale value of the pixel in the starting cargo image, and β1, β2 and β3 are the R, G and B weights respectively; Divide the grayscale value of 0-255 into E intervals, marked as grayscale intervals; Count the frequency of the grayscale values ​​in each grayscale interval respectively, and mark it as grayscale interval frequency; Draw a histogram with grayscale value as X-axis and grayscale interval frequency as Y-axis, marked as grayscale histogram; Add up the frequencies of all grayscale intervals to get the total frequency, marked as F; Mark the intervals with grayscale interval frequency less than F / E as small frequency areas, and mark the intervals other than small frequency areas as large frequency areas. Determine whether there are large frequency areas on both sides of the small frequency area. If so, mark the small frequency area as the final area. The midpoint value of the abscissa of the final area is set as the background threshold; the grayscale value of the pixel points greater than or equal to the background threshold is set to 255, and the grayscale value of the pixel points less than the background threshold is set to 0, to obtain a binary image of the goods; If a pixel with a grayscale value of 255 is adjacent to a pixel with a grayscale value of 0, the pixel with a grayscale value of 0 is marked as a pixel at the edge of the cargo; The grayscale values ​​of all pixels in the cargo binary image that are not cargo boundary pixels are set to 255 and marked as the cargo boundary contour image.

5. The intelligent logistics warehouse cargo weighing management system according to claim 4, characterized in that: The contour midpoint acquisition module is configured with a strategy for acquiring the starting contour midpoint, and the strategy for acquiring the starting contour midpoint includes: Establish a first plane rectangular coordinate system, with the lower left corner of the starting contour as the origin, the long side of the starting contour parallel to the X-axis, the wide side of the starting contour parallel to the Y-axis, and place the starting contour in the first quadrant; Set the coordinate point of the edge pixel of the cargo in the first plane rectangular coordinate system to (xi, yi), and obtain an x i The maximum coordinates of are: (x max , y0), get an x i The minimum value of (x min , y1), get a y i The maximum coordinates are: (x0, y max ), get y i The coordinates of the minimum value are: (x1, y min ); then obtain (x max , y0) and parallel to the Y axis, marked as the front segment, obtain the line segment through (x min , y1) and parallel to the Y axis, marked as the rear segment, obtain the line segment through (x0, y max ) and parallel to the X-axis, marked as the left segment, obtain the line segment through (x1, y min ) and parallel to the X-axis, marked as the right segment, where the front segment, the back segment, the left segment and the right segment form a rectangle; get the lower left corner point of the rectangle (x zx ,y zx ) and the upper right corner (x ys ,y ys ), get point Mark the midpoint of the starting contour.

6. The intelligent logistics warehouse cargo weighing management system according to claim 5, characterized in that: The predicted weight acquisition module is configured with a predicted weight acquisition strategy, and the predicted weight acquisition strategy includes: Get the distance between the buffer starting point and the weighing midpoint, marked as L; Get the speed of the conveyor belt, marked as V; The time from the starting point of the material buffer to the midpoint of weighing is calculated as: T = L / V; Establish a second plane rectangular coordinate system, with the lower left corner of the starting cargo image as the origin, the long side of the starting cargo image parallel to the X-axis, the wide side of the starting cargo image parallel to the Y-axis, and the starting cargo image is placed in the first quadrant; Get the coordinates of the buffer starting point; When the horizontal coordinates of the midpoint of the starting contour and the starting point of the buffer are equal, the timing starts. When the time reaches T, the weighed weight of the goods is obtained and marked as the predicted weight.

7. The intelligent logistics warehouse cargo weighing management system according to claim 6, characterized in that: The observed weight acquisition module is configured with an observed weight acquisition strategy, and the observed weight acquisition strategy includes: A cargo boundary contour map of a final cargo image is obtained based on a cargo boundary contour acquisition method, and is marked as a final contour map; Establish a third plane rectangular coordinate system, with the lower left corner of the final cargo image as the origin, the long side of the final cargo image parallel to the X-axis, the wide side of the final cargo image parallel to the Y-axis, and place the final cargo image in the first quadrant; Set the coordinate point of the final contour map in the third plane rectangular coordinate system to (m i , n i ), get an m i The maximum coordinates of max , n1), get an m i The minimum coordinate of min , n2); Set the coordinate point of the weighing area in the third plane rectangular coordinate system as (q i , w i ), get a q i The maximum coordinate of max , w1), get an m i The minimum coordinate of min , w2); When m is satisfied at the same time max max With m min >q min , obtain the cargo weight displayed in the weighing area when the final cargo image is taken, and mark it as the observed weight.​ 8. The intelligent logistics warehouse cargo weighing management system according to claim 7 is characterized in that: The final weight acquisition module is configured with a final weight acquisition strategy, and the final weight acquisition strategy includes: Label the predicted weight as G1 and the observed weight as Gc j ; Delete Gc j The maximum and minimum values ​​in are marked as Gz i ; Ask for Gz i The mean of Find Gz i The mean square error is: Where MSE is Gz i The mean square error of , the value range of j is: j is a positive integer and 1≤j≤u; Determine whether the MSE is less than the error threshold. If it is less than the error threshold, calculate the final weight as: Where Gzz is the final weight; The final weight shall be the weight of the cargo; If it is greater than the error threshold, a cargo weighing abnormality signal is issued.

9. An intelligent logistics warehouse cargo weighing management method, applicable to an intelligent logistics warehouse cargo weighing management system according to any one of claims 1 to 8, characterized in that: The method comprises the following steps: obtaining a cargo image and marking it as a starting cargo image; Acquire a cargo boundary contour of a starting cargo image based on a cargo boundary contour acquisition method, and acquire a starting contour midpoint based on the cargo boundary contour; Acquire the data of the conveyor belt, calculate the time when the midpoint of the starting contour reaches the midpoint of the weighing area based on the data of the conveyor belt, obtain the weight of the goods weighed at this time point, and mark it as the predicted weight; Obtain a cargo image and mark it as a final cargo image; The final contour of the final cargo image is obtained based on the cargo boundary contour acquisition method, and the cargo weight weighed when the final contour is in the entire weighing area is obtained and marked as the observed weight; Find the mean of the predicted weight and the observed weight, mark it as the final weight, and use the final weight as the weight of the goods.

Images