A data processing method and device for warehouse goods

Abstract

The application discloses a data processing method and device for warehouse goods, and the method comprises the following steps: acquiring point cloud data information of the warehouse goods; the point cloud data information comprises a plurality of point cloud information; pre-processing the point cloud data information to obtain pre-processed point cloud data information; and processing the pre-processed point cloud data information to obtain a warehouse goods volume value. It can be seen that, by analyzing the point cloud data information of the goods in the warehouse, the space used by the goods in the warehouse can be accurately calculated, which is beneficial to optimizing the placement position of the warehouse goods, improving the space utilization rate and operation efficiency, and reducing the cost.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of warehouse management and logistics, and in particular to a warehouse goods data processing method and device. BACKGROUND

[0002] In modern warehouse management, accurate inventory management and space utilization are the key to improving operational efficiency, reducing costs, and optimizing resource allocation. With the rapid development of e-commerce and the diversification of consumer demand, the functions of warehouses are becoming increasingly complex, and they are no longer just storage places for goods, but have become efficient logistics centers. Therefore, how to effectively manage inventory, improve space utilization, and achieve rapid response has become an important challenge in warehouse management.

[0003] Traditional inventory measurement methods mainly rely on manual estimation, rule-based size measurement, or simple volume calculation. These methods usually require manual measurement, recording, and calculation of goods, which is not only time-consuming and labor-intensive, but also prone to measurement errors due to human factors. Such errors can lead to inaccurate inventory data, affecting inventory management decisions, reducing warehouse space utilization and operational efficiency, and increasing costs. SUMMARY

[0004] The technical problem to be solved by the present application is to provide a warehouse goods data processing method and device, which can accurately calculate the space used by goods in the warehouse by analyzing the point cloud data information of the goods in the warehouse, and is beneficial to optimizing the placement of warehouse goods, improving space utilization and operational efficiency, and reducing costs.

[0005] To solve the above technical problems, the first aspect of the embodiment of the present application discloses a warehouse goods data processing method, which comprises:

[0006] S1, obtaining point cloud data information of warehouse goods; the point cloud data information comprises a plurality of point cloud information;

[0007] S2, preprocessing the point cloud data information to obtain preprocessed point cloud data information;

[0008] S3, processing the preprocessed point cloud data information to obtain a warehouse goods volume value.

[0009] As an optional implementation manner, in the first aspect of the embodiment of the present application, the preprocessing of the point cloud data information to obtain the preprocessed point cloud data information comprises:

[0010] S21, performing coordinate conversion processing on the point cloud data information to obtain converted point cloud data information; the converted point cloud data information comprises a plurality of point cloud coordinate information;

[0011] S22, the converted point cloud data information is denoised to obtain denoised point cloud data information;

[0012] S23, the denoised point cloud data information is downsampled to obtain preprocessed point cloud data information; the preprocessed point cloud data information includes several preprocessed point cloud coordinate information.

[0013] As an optional implementation, in the first aspect of the present invention, the step of performing coordinate transformation processing on the point cloud data information to obtain transformed point cloud data information includes:

[0014] S211, obtain the horizontal angle value and the vertical angle value of the point cloud deviation;

[0015] S212, using the point cloud coordinate transformation calculation model, the point cloud data information, the point cloud deviation horizontal angle value and the point cloud deviation vertical angle value are calculated and processed to obtain the transformed point cloud data information;

[0016] The point cloud coordinate transformation calculation model is as follows:

[0017]

[0018] In the formula, (X i ,Y i Z i R represents the i-th point cloud coordinate information in the transformed point cloud data information. i θ1 i and θ2 i These are the distance measurement value, horizontal angle value, and vertical angle value corresponding to the i-th point cloud information in the point cloud data information, respectively. and These are the horizontal angle value and the vertical angle value of the point cloud deviation, respectively.

[0019] As an optional implementation, in the first aspect of the present invention, processing the preprocessed point cloud data information to obtain the warehouse cargo volume value includes:

[0020] S31, the preprocessed point cloud data information is analyzed and processed to obtain the point cloud data information to be processed, the normal vector information (a,b,c) and the offset d;

[0021] S32, according to the normal vector information (a,b,c) and the offset d, the point cloud data information to be processed is projected to obtain point cloud data projection information; the point cloud data projection information includes several point cloud projection coordinate information;

[0022] S33, calculate and process the projection information of the point cloud data to obtain the warehouse cargo volume value.

[0023] As an optional implementation, in the first aspect of the present invention, the step of analyzing and processing the preprocessed point cloud data information to obtain point cloud data information to be processed includes:

[0024] S311, The preprocessed point cloud data information is fitted to obtain normal vector information (a,b,c) and offset d;

[0025] S312, using a point cloud preprocessing calculation model, the preprocessed point cloud data information, the normal vector information, and the offset are calculated to obtain point cloud planar distance information; the point cloud planar distance information includes several point cloud planar distance values.

[0026] The point cloud preprocessing calculation model is as follows:

[0027]

[0028] In the formula, JL i2 For the i2th point cloud planar distance value in the point cloud planar distance information, (x i2 ,y i2 ,z i2 ) represents the i2th preprocessed point cloud coordinate information in the preprocessed point cloud data information, ∈1 represents the first deviation coefficient, and N2 represents the number of preprocessed point cloud coordinate information in the preprocessed point cloud data information;

[0029] S313, determine whether any of the point cloud plane distance values ​​in the point cloud plane distance information is greater than a preset point cloud plane distance threshold, and obtain a fourth determination result;

[0030] When the fourth determination result is yes, the preprocessed point cloud data information is determined to be the point cloud data information to be processed;

[0031] When the fourth judgment result is negative, the preprocessed point cloud coordinate information corresponding to the point cloud plane distance value is removed from the preprocessed point cloud data information to obtain updated preprocessed point cloud data information, and the updated preprocessed point cloud data information is determined to be the point cloud data information to be processed.

[0032] As an optional implementation, in a first aspect of the present invention, the step of projecting the point cloud data information to be processed according to the normal vector information (a,b,c) and the offset d to obtain point cloud data projection information includes:

[0033] Using a point cloud projection calculation model, the point cloud data to be processed is projected based on the normal vector information (a,b,c) and the offset d to obtain point cloud data projection information.

[0034] The point cloud projection calculation model is as follows:

[0035] (xx i3 yy i3 ,zz i3 )=(x i3 -a·JLY·ω,y i3 -b·JLY·ω,z i3 -c·JLY·ω);

[0036]

[0037] In the formula, (xx i3 yy i3 ,zz i3 ) represents the i-th point cloud projection coordinate information in the point cloud data projection information, (x i3 ,y i3 ,z i3 ) represents the i3rd preprocessed point cloud coordinate information in the point cloud data information to be processed, JLY is the distance factor, ω is the weight factor, and θ1 and θ2 are the first regularization parameter and the second regularization parameter, respectively.

[0038] As an optional implementation, in the first aspect of the present invention, the step of calculating and processing the projection information of the point cloud data to obtain the warehouse cargo volume value includes:

[0039] S331, Obtain the initial grid scale value, the maximum grid scale value, and the grid step size value; the initial grid scale value is less than the maximum grid scale value;

[0040] S332, set t=1;

[0041] S333, using the initial grid scale value, perform grid division processing on the point cloud data projection information to obtain several point cloud grid information;

[0042] S334, Calculate and process the several point cloud grid information to obtain the t-th cargo volume value of the warehouse cargo, and add the cargo volume value to the cargo volume set;

[0043] S335, determine whether the sum of the initial grid scale value and the grid step size value is greater than the maximum grid scale value, and obtain the fifth determination result;

[0044] When the fifth judgment result is negative, t is increased by 1, the sum of the initial grid scale value and the grid step size value is determined to be the initial grid scale value, and S333 is executed;

[0045] S336, When the fifth judgment result is yes, execute S337;

[0046] S337, Perform calculations on the cargo volume set to obtain the volume mean and volume standard deviation;

[0047] S338, The cargo volume set is filtered using the volume mean and the volume standard deviation to obtain the filtered cargo volume set;

[0048] S339, the average value of all the cargo volume values ​​in the filtered cargo volume set is calculated to obtain the warehouse cargo volume value.

[0049] A second aspect of this invention discloses a data processing apparatus for warehouse goods, the apparatus comprising:

[0050] The acquisition module is used to acquire point cloud data information of warehouse goods; the point cloud data information includes several point cloud information.

[0051] The first calculation module is used to preprocess the point cloud data information to obtain preprocessed point cloud data information;

[0052] The second calculation module is used to process the preprocessed point cloud data information to obtain the warehouse cargo volume value.

[0053] A third aspect of the present invention discloses another data processing apparatus for warehouse goods, the apparatus comprising:

[0054] processor;

[0055] A memory coupled to the processor stores executable program code;

[0056] The processor calls the executable program code stored in the memory to execute some or all of the steps of the warehouse cargo data processing method disclosed in the first aspect of the present invention.

[0057] A fourth aspect of the present invention discloses a computer-readable storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps of the data processing method for warehouse goods disclosed in the first aspect of the present invention.

[0058] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0059] In this embodiment of the invention, point cloud data of warehouse goods is acquired; the point cloud data includes several point cloud information; the point cloud data is preprocessed to obtain preprocessed point cloud data; the preprocessed point cloud data is further processed to obtain the warehouse goods volume value. It is evident that by analyzing the point cloud data of goods in the warehouse, the usable space of the goods in the warehouse can be accurately calculated, which is beneficial for optimizing the placement of warehouse goods, improving space utilization and operational efficiency, and reducing costs. Attached Figure Description

[0060] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0061] Figure 1 This is a schematic flowchart of a data processing method for warehouse goods disclosed in an embodiment of the present invention;

[0062] Figure 2 This is a schematic diagram of the structure of a data processing device for warehouse goods disclosed in an embodiment of the present invention;

[0063] Figure 3 This is a schematic diagram of another warehouse cargo data processing device disclosed in an embodiment of the present invention. Detailed Implementation

[0064] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0065] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0066] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0067] This invention discloses a data processing method and apparatus for warehouse goods. By analyzing the point cloud data of goods in the warehouse, it is possible to accurately calculate the space used by the goods in the warehouse, which is beneficial for optimizing the placement of warehouse goods, improving space utilization and operational efficiency, and reducing costs. Detailed descriptions follow.

[0068] Example 1

[0069] Please see Figure 1 , Figure 1 This is a flowchart illustrating a data processing method for warehouse goods disclosed in an embodiment of the present invention. Figure 1 The described data processing method for warehouse goods is applied in a data processing device for warehouse goods, such as a local server or cloud server for optimized management of warehouse goods data processing, etc., and the embodiments of the present invention are not limited thereto. Figure 1 As shown, the data processing method for warehouse goods may include the following operations:

[0070] S1, acquire point cloud data information of warehouse goods; the point cloud data information includes several point cloud information;

[0071] It should be noted that the above point cloud data information was obtained by using a LiDAR (Light Detection and Ranging) 3D scanning. All point cloud information in the obtained point cloud data information is in polar coordinates, where each polar coordinate includes a distance value, a horizontal angle value, and a vertical angle value.

[0072] S2, preprocess the point cloud data information to obtain preprocessed point cloud data information;

[0073] S3 processes the preprocessed point cloud data to obtain the warehouse cargo volume value.

[0074] It should be noted that the obtained warehouse cargo volume value is the occupied volume within the warehouse. By combining the occupied volume with the current total warehouse volume, the placement of goods can be adjusted in real time, improving space utilization and operational efficiency. This also significantly enhances the intelligence level of warehouse management, reduces operating costs, and improves overall supply chain efficiency. Furthermore, by combining historical volume data, warehouse demand can be predicted, supporting intelligent warehouse scheduling.

[0075] It is evident that implementing the warehouse cargo data processing method described in the embodiments of the present invention is beneficial for optimizing the placement of warehouse cargo, improving space utilization and operational efficiency, and reducing costs.

[0076] In an optional embodiment, the point cloud data information is preprocessed to obtain preprocessed point cloud data information, including:

[0077] S21, Perform coordinate transformation on the point cloud data to obtain the transformed point cloud data; the transformed point cloud data includes several point cloud coordinate information;

[0078] S22, Denoise the converted point cloud data to obtain denoised point cloud data;

[0079] S23, downsample the denoised point cloud data to obtain preprocessed point cloud data; the preprocessed point cloud data includes several preprocessed point cloud coordinate information.

[0080] It should be noted that the above downsampling process can be performed using methods such as voxel grid downsampling algorithm and PCL. In particular, the embodiments of the present invention do not limit the specific methods.

[0081] It should be noted that by downsampling and merging adjacent points into a single voxel, the amount of data can be effectively reduced, computational efficiency can be improved, and the geometric structure of the point cloud can be preserved.

[0082] It is evident that implementing the warehouse cargo data processing method described in the embodiments of the present invention is beneficial for optimizing the placement of warehouse cargo, improving space utilization and operational efficiency, and reducing costs.

[0083] In another optional embodiment, coordinate transformation is performed on the point cloud data to obtain transformed point cloud data, including:

[0084] S211, obtain the horizontal angle value and the vertical angle value of the point cloud deviation;

[0085] It should be noted that the above-mentioned point cloud deviation horizontal angle value and point cloud deviation vertical angle value are obtained by the IMU (Inertial Measurement Unit) set on the LiDAR, and are respectively the horizontal angle offset value and vertical angle offset value of the IMU, which are used to provide attitude compensation, eliminate the error caused by the angle offset of the measuring equipment, and thus improve the accuracy of cargo volume calculation.

[0086] S212, using the point cloud coordinate transformation calculation model, calculates and processes the point cloud data information, the point cloud deviation horizontal angle value, and the point cloud deviation vertical angle value to obtain the transformed point cloud data information;

[0087] The point cloud coordinate transformation calculation model is as follows:

[0088]

[0089] In the formula, (X i ,Y i Z i R represents the coordinates of the i-th point cloud in the transformed point cloud data. i θ1 i and θ2 i These represent the distance measurement value, horizontal angle value, and vertical angle value corresponding to the i-th point cloud information in the point cloud data information, respectively. and These are the horizontal angle value and the vertical angle value of the point cloud deviation, respectively.

[0090] It should be noted that the above conversion can convert the polar coordinates in point cloud data into world coordinates.

[0091] It should be noted that due to factors such as installation offset, measurement error, and attitude change of the lidar equipment, the point cloud data may have deviations in horizontal and vertical angles. By correcting the horizontal and vertical angle values ​​of the point cloud deviation, the point cloud data can be made more accurate, so as to obtain more precise warehouse cargo volume values.

[0092] It is evident that implementing the warehouse cargo data processing method described in the embodiments of the present invention is beneficial for optimizing the placement of warehouse cargo, improving space utilization and operational efficiency, and reducing costs.

[0093] In another optional embodiment, the converted point cloud data is denoised to obtain denoised point cloud data, including:

[0094] S221, preset s=1, determines that the converted point cloud data information is the initial denoised point cloud data information;

[0095] S222, Obtain neighboring coordinate information; the neighboring coordinate information is the K adjacent point cloud coordinate information of the s-th point cloud coordinate information in the transformed point cloud data information;

[0096] It should be noted that the K neighboring point cloud coordinate information in the above-mentioned nearest coordinate information refers to the point cloud coordinate information in the K transformed point cloud data information that is closest to the s-th point cloud coordinate information in three-dimensional space.

[0097] S223, using the first distance calculation model, the coordinate information of the s-th point cloud and the coordinate information of its neighbors are calculated and processed to obtain the point cloud coordinate distance information; the point cloud coordinate distance information includes several point cloud distance values;

[0098] The first distance calculation model is as follows:

[0099]

[0100] Among them, DSK s,j1 Let j1 be the j1st point cloud distance value in the point cloud coordinate distance information, representing the distance between the sth point cloud coordinate information and the j1st point cloud coordinate information in the neighboring coordinate information, (x s ,y s ,z s ) represents the coordinate information of the s-th point cloud, (x j1 ,y j1 ,z j1 ) represents the coordinate information of the j1th point cloud in the neighboring coordinate information, and δ1 and δ2 are the first weight parameter and the second weight parameter, respectively;

[0101] It should be noted that the first weight parameter and the second weight parameter can be set by the user or obtained from historical data. Specifically, this embodiment of the invention does not limit the specifics.

[0102] It should be noted that the value of the first weight parameter ranges from [0.5, 1] ​​and is used to adjust the influence weight of distance calculation to adapt to point cloud data of different scales. When the first weight parameter is 1, it is the standard Euclidean distance model. When the first weight parameter is less than 1, it indicates distance scaling, which weakens the influence of distant points. However, if the first weight parameter is too small, the distance difference between near and far points will not be obvious, affecting the accuracy of subsequent warehouse volume calculation. If it is too large, the influence of distant points will be too large, which will introduce noise.

[0103] It should be noted that the value of the second weight parameter is between [0, 0.5], which can adjust the density of the point cloud to make the distance distribution more uniform.

[0104] S224, using the second distance calculation model, the point cloud coordinate distance information is calculated and processed to obtain the average distance value;

[0105] The second distance calculation model is as follows:

[0106]

[0107] In the formula, PJ s This is the average distance value;

[0108] S225, calculate the standard deviation of the average distance value and the point cloud coordinate distance information to obtain the point cloud standard deviation;

[0109] S226, Analyze and process the initial denoised point cloud data information, the coordinate information of the sth point cloud, the point cloud coordinate distance information, the average distance value and the point cloud standard deviation to obtain the denoised point cloud data information;

[0110] S227, determine whether s is greater than the number of point cloud coordinates in the transformed point cloud data information, and obtain the first judgment result;

[0111] If the result of the first judgment is negative, increment s by 1 and execute S222;

[0112] If the first judgment result is yes, execute S23.

[0113] It is evident that implementing the warehouse cargo data processing method described in the embodiments of the present invention is beneficial for optimizing the placement of warehouse cargo, improving space utilization and operational efficiency, and reducing costs.

[0114] In an optional embodiment, the initial denoised point cloud data information, the coordinate information of the s-th point cloud, the point cloud coordinate distance information, the average distance value, and the point cloud standard deviation are analyzed and processed to obtain the denoised point cloud data information, including:

[0115] S2261, determine whether the absolute value of any point cloud distance value and the average distance value in the point cloud coordinate distance information is greater than α1 times the point cloud standard deviation, and obtain the second judgment result;

[0116] When the second judgment result is negative, the initial denoised point cloud data information is determined to be the denoised point cloud data information.

[0117] When the second judgment result is yes, determine whether the absolute value of the point cloud distance value and the average distance value is greater than α2 times the point cloud standard deviation, and obtain the third judgment result;

[0118] If the result of the third judgment is negative, execute S2262;

[0119] If the result of the third judgment is yes, execute S2264;

[0120] S2262, using the point cloud coordinate information calculation model, calculate and process the point cloud coordinate information corresponding to the point cloud distance value and the s-th point cloud coordinate information to obtain the updated point cloud coordinate information;

[0121] The point cloud coordinate information calculation model is as follows:

[0122] DYG=δ3·DYZ+δ4·DYS 0≤δ3,δ4≤1;

[0123] δ3+δ4=1;

[0124] In the formula, DYG is the updated point cloud coordinate information, DYZ is the point cloud coordinate information corresponding to the point cloud distance value, DYS is the s-th point cloud coordinate information, and δ3 and δ4 are the third weight parameter and the fourth weight parameter, respectively.

[0125] It should be noted that the third and fourth weight parameters can be set by the user or obtained from historical data. In particular, the embodiments of the present invention do not limit the specifics.

[0126] Furthermore, the value range of δ3 is [0.5, 0.8]. In this case, the updated point cloud coordinate information depends more on the point cloud coordinate information corresponding to the point cloud distance value, rather than the s-th point cloud coordinate information. This prevents excessive smoothing during noise processing, thus avoiding the loss of point cloud details after denoising. This is especially suitable for point clouds with high noise or complex environments.

[0127] S2263, using the updated point cloud coordinate information, update the initial denoised point cloud data information to obtain the updated initial denoised point cloud data information;

[0128] It should be noted that the above update process updates the point cloud coordinates corresponding to the point cloud distance value in the initial denoised point cloud data to the updated point cloud coordinates.

[0129] S2264, delete the point cloud coordinate information corresponding to the point cloud distance value from the initial denoised point cloud data information to obtain the updated initial denoised point cloud data information;

[0130] S2265, confirm that the updated initial denoised point cloud data information is the denoised point cloud data information.

[0131] It should be noted that the values ​​of α1 and α2 are in the ranges of [1.5, 3] and [2.5-4], respectively. For example, α1 and α2 are 2 and 3, respectively, and α1 < α2. When the values ​​of α1 and α2 are in the ranges of [1.5, 3] and [2.5-4], setting α1 ≥ 1.5 can effectively filter out outliers that are more than 1.5 times the average distance, ensuring that 95% of normal point cloud data can pass. By setting an appropriate α1, erroneous data caused by measurement errors and environmental factors can be reduced to a certain extent, improving the reliability of point cloud data. By setting α2 ≥ 2.5, the screening of outliers is further strengthened, and the vast majority of outliers can be filtered out, which helps to maintain the accuracy of subsequent data processing.

[0132] It should be noted that steps S2261-S2265 employ a two-step screening using dual thresholds α1 and α2, which effectively distinguishes between normal points, slightly outliers, and extreme outliers, preventing the accidental deletion of critical point cloud coordinate information. Slightly outliers are corrected using neighboring points for smoothing, while extreme outliers are directly deleted, avoiding data loss caused by simple and brute-force deletion and improving data quality. The point cloud coordinate information calculation model can correct slightly outliers, reduce data fragmentation, and improve the smoothness of point cloud data. At the same time, the weight parameters δ3 and δ4 can be flexibly adjusted between retaining the original point cloud information and correcting based on neighboring points to adapt to data with different noise levels.

[0133] It is evident that implementing the warehouse cargo data processing method described in the embodiments of the present invention is beneficial for optimizing the placement of warehouse cargo, improving space utilization and operational efficiency, and reducing costs.

[0134] In an optional embodiment, the preprocessed point cloud data is processed to obtain the warehouse cargo volume value, including:

[0135] S31, Analyze and process the preprocessed point cloud data information to obtain the point cloud data information to be processed, normal vector information (a,b,c) and offset d;

[0136] S32, Based on the normal vector information (a,b,c) and offset d, perform projection processing on the point cloud data information to be processed to obtain the point cloud data projection information; the point cloud data projection information includes several point cloud projection coordinate information;

[0137] S33 calculates and processes the projection information of the point cloud data to obtain the volume value of the warehouse goods.

[0138] It is evident that implementing the warehouse cargo data processing method described in the embodiments of the present invention is beneficial for optimizing the placement of warehouse cargo, improving space utilization and operational efficiency, and reducing costs.

[0139] In an optional embodiment, the preprocessed point cloud data information is analyzed and processed to obtain point cloud data information to be processed, including:

[0140] S311, Fit the preprocessed point cloud data to obtain normal vector information (a,b,c) and offset d;

[0141] It should be noted that the above fitting process is obtained by fitting using the RANSAC algorithm. The direction of the normal vector information points to the direction perpendicular to the ground, the offset represents the vertical distance of the ground from the origin, and the origin represents the coordinate origin in the world coordinate system. In a warehouse, the origin can be set as the bottom center point or entrance point of a certain shelf to facilitate measurement and navigation.

[0142] S312, using the point cloud preprocessing calculation model, calculates and processes the preprocessed point cloud data information, normal vector information, and offset to obtain point cloud planar distance information; the point cloud planar distance information includes several point cloud planar distance values.

[0143] The point cloud preprocessing calculation model is as follows:

[0144]

[0145] In the formula, JL i2 For the i2th point cloud planar distance value in the point cloud planar distance information, (x i2 ,y i2 ,z i2 ) represents the i2th preprocessed point cloud coordinate information in the preprocessed point cloud data information, ∈1 represents the first deviation coefficient, and N2 represents the number of preprocessed point cloud coordinate information in the preprocessed point cloud data information;

[0146] It should be noted that the first deviation coefficient can be set by the user or obtained from historical data. Specifically, this embodiment of the invention does not limit the specific value.

[0147] It should be noted that by using the normal vector and offset, the distance from each preprocessed point cloud coordinate information to the ground can be accurately calculated. The first deviation coefficient has a value range of [0.001, 0.1]. Adding the first deviation coefficient in the distance calculation can prevent the result deviation caused by numerical calculation error, making the calculation more stable. At the same time, it can adjust the sensitivity to noise, which can improve the impact of noise on the final result to a certain extent.

[0148] S313, determine whether any point cloud plane distance value in the point cloud plane distance information is greater than the preset point cloud plane distance threshold, and obtain the fourth judgment result;

[0149] When the fourth judgment result is yes, the preprocessed point cloud data information is determined to be the point cloud data information to be processed.

[0150] When the fourth judgment result is negative, the preprocessed point cloud coordinate information corresponding to the point cloud plane distance value is removed from the preprocessed point cloud data information to obtain the updated preprocessed point cloud data information, and the updated preprocessed point cloud data information is determined as the point cloud data information to be processed.

[0151] It should be noted that the point cloud plane distance threshold ranges from [0.05, 0.1], in meters. By calculating the distance from each point cloud point to the ground plane, it is possible to identify which point cloud points are located on the ground and which are points of other objects. This allows point cloud data on the ground to be removed, eliminating interference from the ground in subsequent data processing and focusing more on the subsequent calculation and processing of warehouse goods. This improves the accuracy and efficiency of the algorithm.

[0152] It is evident that implementing the warehouse cargo data processing method described in the embodiments of the present invention is beneficial for optimizing the placement of warehouse cargo, improving space utilization and operational efficiency, and reducing costs.

[0153] In an optional embodiment, the point cloud data to be processed is projected based on the normal vector information (a,b,c) and the offset d to obtain the point cloud data projection information, including:

[0154] Using the point cloud projection calculation model, the point cloud data to be processed is projected based on the normal vector information (a,b,c) and the offset d to obtain the point cloud data projection information.

[0155] The point cloud projection calculation model is as follows:

[0156] (xx i3 yy i3 ,zz i3 )=(x i3 -a·JLY·ω,y i3 -b·JLY·ω,z i3 -c·JLY·ω);

[0157]

[0158] In the formula, (xx i3 yy i3 ,zz i3 (x) represents the i-th point cloud projection coordinate information in the point cloud data projection information, (x) i3 ,y i3 ,z i3 ) represents the coordinate information of the i3rd preprocessed point cloud in the point cloud data to be processed, JLY is the distance factor, ω is the weight factor, and θ1 and γ2 are the first regularization parameter and the second regularization parameter, respectively.

[0159] It should be noted that the first regularization parameter and the second regularization parameter can be set by the user or obtained from historical data. Specifically, this embodiment of the invention does not limit the specific parameters.

[0160] It should be noted that the values ​​of the first and second regularization parameters are both between [0.01, 0.1], which can improve computational stability.

[0161] It should be noted that the point cloud projection calculation model projects the point cloud data to be processed onto the ground. By calculating the vertical distance from each preprocessed point cloud coordinate to the plane, the model can effectively eliminate the influence of the ground on the point cloud data. By setting a distance factor, the relationship between each point and the ground can be determined, ensuring the accuracy and effectiveness of the projection. By setting a weight factor, the influence of points on the final result during the projection process is adjusted. When the distance is large, the weight is reduced, and vice versa. This mechanism can prevent abnormal points far from the plane from interfering with the projection result, thereby improving the overall quality and accuracy of point cloud projection.

[0162] It is evident that implementing the warehouse cargo data processing method described in the embodiments of the present invention is beneficial for optimizing the placement of warehouse cargo, improving space utilization and operational efficiency, and reducing costs.

[0163] In an optional embodiment, the projection information of the point cloud data is calculated to obtain the warehouse cargo volume value, including:

[0164] S331, obtain the initial grid scale value, maximum grid scale value, and grid step size value; the initial grid scale value is less than the maximum grid scale value;

[0165] It should be noted that the initial grid scale value mentioned above can be the average spacing between all point cloud projection coordinates in the point cloud data projection information. This ensures that the grid scale matches the density of the point cloud, thereby better capturing the structural features of the point cloud and helping to obtain more refined results during analysis. The maximum grid scale value can be one-third of the distance between the two farthest point cloud projection coordinates in the point cloud data projection information. This ensures that the grid is not too large to avoid losing details, while still covering the entire point cloud range, so that point cloud data far from the center area can be taken into account during calculation. The grid step size is one-WG, which is the difference between the maximum grid scale value and the initial grid scale value, where WG is the number of grids set by the user. For example, WG is greater than 10000.

[0166] S332, set t=1;

[0167] S333: Using the initial grid scale value, the projection information of the point cloud data is divided into grids to obtain several point cloud grid information.

[0168] The aforementioned mesh division can be processed using algorithms such as Delaunay triangulation and uniform mesh division. Specific methods are not limited in the embodiments of this invention. Mesh division allows the projection information of point cloud data to be divided into several point cloud meshes, that is, into several small, finite regions (mesh units). Each mesh unit can be considered as a small region containing a small portion of the final projection information of the point cloud data. These small regions can be used to better analyze, process, or visualize the point cloud data.

[0169] S334, calculates and processes several point cloud grid information to obtain the t-th cargo volume value of the warehouse cargo, and adds the cargo volume value to the cargo volume set;

[0170] It should be noted that the above calculations can be performed using methods such as PCL and MATLAB, and the specific implementation of this invention is not limited thereto.

[0171] S335, determine whether the sum of the initial grid scale value and the grid step size value is greater than the maximum grid scale value, and obtain the fifth judgment result;

[0172] When the result of the fifth judgment is negative, t is increased by 1, the sum of the initial grid scale value and the grid step size value is determined to be the initial grid scale value, and S333 is executed;

[0173] S336, If the result of the fifth judgment is yes, execute S337;

[0174] S337, calculates and processes the cargo volume set to obtain the volume mean and volume standard deviation;

[0175] The above container mean and volume standard deviation are the mean and standard deviation of the volume values ​​of all goods in the set of goods volumes.

[0176] S338, using the volume mean and volume standard deviation, the cargo volume set is filtered to obtain the filtered cargo volume set;

[0177] It should be noted that the above filtering process uses the volume mean and standard deviation to set a threshold range for filtering volume values. The effective range can be determined using the following formula:

[0178] Threshold = [mean - k × standard deviation, mean + k × standard deviation];

[0179] Where k is a chosen coefficient (e.g., 2.5 or 4), indicating that the volume value should be within a few standard deviations of the mean.

[0180] The filtered set: The values ​​that fall within this threshold range are retained to form the filtered cargo volume set.

[0181] S339: The average value of all cargo volume values ​​in the filtered cargo volume set is calculated to obtain the warehouse cargo volume value.

[0182] It should be noted that by using S337-S339, a more reliable warehouse cargo volume value can be calculated, eliminating outliers and noisy data, making the final warehouse cargo volume value more accurate and representative.

[0183] It is evident that implementing the warehouse cargo data processing method described in the embodiments of the present invention is beneficial for optimizing the placement of warehouse cargo, improving space utilization and operational efficiency, and reducing costs.

[0184] Example 2

[0185] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of a data processing device for warehouse goods disclosed in an embodiment of the present invention. Figure 2 The described warehouse cargo data processing device is applied in a warehouse cargo data processing optimization system, such as a local server or cloud server for warehouse cargo data processing, etc., and the embodiments of the present invention are not limited thereto. Figure 2 As shown, the data processing device for warehouse goods includes:

[0186] The acquisition module 201 is used to acquire point cloud data information of warehouse goods; the point cloud data information includes several point cloud information.

[0187] The first calculation module 202 is used to preprocess the point cloud data information to obtain preprocessed point cloud data information;

[0188] The second calculation module 203 is used to process the preprocessed point cloud data information to obtain the warehouse cargo volume value.

[0189] It is evident that implementing the warehouse cargo data processing device described in the embodiments of the present invention is beneficial for optimizing the placement of warehouse cargo, improving space utilization and operational efficiency, and reducing costs.

[0190] Example 3

[0191] Please see Figure 3 , Figure 3 This is a schematic diagram of another warehouse cargo data processing device disclosed in an embodiment of the present invention. Figure 3 The described warehouse cargo data processing device is applied in a warehouse cargo data processing optimization system, such as a local server or cloud server for warehouse cargo data processing, etc., and the embodiments of the present invention are not limited thereto. Figure 3 As shown, the data processing device for warehouse goods includes:

[0192] Processor 301;

[0193] A memory 302 containing executable program code is coupled to the processor 301;

[0194] The processor 301 calls the executable program code stored in the memory 302 to execute some or all of the steps of the warehouse cargo data processing method of Embodiment 1.

[0195] It is evident that implementing the warehouse cargo data processing device described in the embodiments of the present invention is beneficial for optimizing the placement of warehouse cargo, improving space utilization and operational efficiency, and reducing costs.

[0196] Example 4

[0197] This invention discloses a computer-readable storage medium storing computer instructions. When the computer instructions are invoked, they are used to execute some or all of the steps of the data processing method for warehouse goods in Embodiment 1.

[0198] Example 5

[0199] This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform some or all of the steps in the data processing method for warehouse goods described in Embodiment 1.

[0200] The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0201] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0202] Finally, it should be noted that the data processing method and apparatus for warehouse goods disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data processing method for warehouse goods, characterized in that, The method includes: S1, acquire point cloud data information of warehouse goods; the point cloud data information includes several point cloud information; S2, preprocess the point cloud data information to obtain preprocessed point cloud data information; S3, process the preprocessed point cloud data information to obtain the warehouse cargo volume value, including; S31, the preprocessed point cloud data information is analyzed and processed to obtain the point cloud data information to be processed, the normal vector information (a,b,c) and the offset d; the direction of the normal vector information (a,b,c) points to the direction perpendicular to the ground, the offset d is the vertical distance of the ground from the origin, and the origin is the coordinate origin in the world coordinate system; S32, according to the normal vector information (a,b,c) and the offset d, the point cloud data information to be processed is projected to obtain point cloud data projection information; the point cloud data projection information includes several point cloud projection coordinate information; S33, Calculate and process the projection information of the point cloud data to obtain the warehouse cargo volume value; S32 includes: Using a point cloud projection calculation model, the point cloud data to be processed is projected based on the normal vector information (a,b,c) and the offset d to obtain point cloud data projection information. The point cloud projection calculation model is as follows: (xx i3 ,y Y i3 ,zz i3 )=(x i3 -a·JLY·ω,y i3 -b·JLY·ω,z i3 -c·JLY·ω); 1≤i3≤N3; In the formula, (xx i3 yy i3 ,zz i3 ) represents the i-th point cloud projection coordinate information in the point cloud data projection information, (x i3 ,y i3 ,z i3 ) represents the i3rd preprocessed point cloud coordinate information in the point cloud data information to be processed, JLY is the distance factor, ω is the weight factor, and θ1 and θ2 are the first regularization parameter and the second regularization parameter, respectively.

2. The data processing method for warehouse goods according to claim 1, characterized in that, The preprocessing of the point cloud data information to obtain preprocessed point cloud data information includes: S21, Perform coordinate transformation on the point cloud data information to obtain transformed point cloud data information; the transformed point cloud data information includes several point cloud coordinate information; S22, Denoise the converted point cloud data information to obtain denoised point cloud data information; S23, the denoised point cloud data information is downsampled to obtain preprocessed point cloud data information; the preprocessed point cloud data information includes several preprocessed point cloud coordinate information.

3. The data processing method for warehouse goods according to claim 2, characterized in that, The coordinate transformation process performed on the point cloud data to obtain the transformed point cloud data includes: S211, obtain the horizontal angle value and the vertical angle value of the point cloud deviation; S212, using the point cloud coordinate transformation calculation model, the point cloud data information, the point cloud deviation horizontal angle value and the point cloud deviation vertical angle value are calculated and processed to obtain the transformed point cloud data information; The point cloud coordinate transformation calculation model is as follows: 1≤i≤N; In the formula, (X i ,Y i Z i R represents the i-th point cloud coordinate information in the transformed point cloud data information. i θ1 i and θ2 i These are the distance measurement value, horizontal angle value, and vertical angle value corresponding to the i-th point cloud information in the point cloud data information, respectively. and These are the horizontal angle value and the vertical angle value of the point cloud deviation, respectively.

4. The data processing method for warehouse goods according to claim 1, characterized in that, The step of analyzing and processing the preprocessed point cloud data to obtain the point cloud data to be processed includes: S311, The preprocessed point cloud data information is fitted to obtain normal vector information (a,b,c) and offset d; S312, using a point cloud preprocessing calculation model, the preprocessed point cloud data information, the normal vector information, and the offset are calculated to obtain point cloud planar distance information; the point cloud planar distance information includes several point cloud planar distance values. The point cloud preprocessing calculation model is as follows: In the formula, JL i2 For the i2th point cloud planar distance value in the point cloud planar distance information, (x i2 ,y i2 ,z i2 ) represents the i2th preprocessed point cloud coordinate information in the preprocessed point cloud data information, ∈1 represents the first deviation coefficient, and N2 represents the number of preprocessed point cloud coordinate information in the preprocessed point cloud data information; S313, determine whether any of the point cloud plane distance values ​​in the point cloud plane distance information is greater than a preset point cloud plane distance threshold, and obtain a fourth determination result; When the fourth determination result is yes, the preprocessed point cloud data information is determined to be the point cloud data information to be processed; When the fourth judgment result is negative, the preprocessed point cloud coordinate information corresponding to the point cloud plane distance value is removed from the preprocessed point cloud data information to obtain updated preprocessed point cloud data information, and the updated preprocessed point cloud data information is determined to be the point cloud data information to be processed.

5. The data processing method for warehouse goods according to claim 1, characterized in that, The step of calculating and processing the projection information of the point cloud data to obtain the warehouse cargo volume value includes: S331, Obtain the initial grid scale value, the maximum grid scale value, and the grid step size value; the initial grid scale value is less than the maximum grid scale value; S332, set t=1; S333, using the initial grid scale value, perform grid division processing on the point cloud data projection information to obtain several point cloud grid information; S334, Calculate and process the several point cloud grid information to obtain the t-th cargo volume value of the warehouse cargo, and add the cargo volume value to the cargo volume set; S335, determine whether the sum of the initial grid scale value and the grid step size value is greater than the maximum grid scale value, and obtain the fifth determination result; When the fifth judgment result is negative, t is increased by 1, the sum of the initial grid scale value and the grid step size value is determined to be the initial grid scale value, and S333 is executed; S336, When the fifth judgment result is yes, execute S337; S337, Perform calculations on the cargo volume set to obtain the volume mean and volume standard deviation; S338, The cargo volume set is filtered using the volume mean and the volume standard deviation to obtain the filtered cargo volume set; S339, the average value of all the cargo volume values ​​in the filtered cargo volume set is calculated to obtain the warehouse cargo volume value.

6. A data processing device for warehouse goods, characterized in that, The device includes: processor; A memory coupled to the processor stores executable program code; The processor calls the executable program code stored in the memory to execute the data processing method for warehouse goods as described in any one of claims 1-5.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which, when invoked, are used to execute the data processing method for warehouse goods as described in any one of claims 1-5.

Images