CN116363192A

CN116363192A - Volume measurement method and device for warehouse goods, computer equipment and storage medium

Info

Publication number: CN116363192A
Application number: CN202111619487.8A
Authority: CN
Inventors: 岳阳雪
Original assignee: SF Technology Co Ltd
Current assignee: SF Technology Co Ltd
Priority date: 2021-12-27
Filing date: 2021-12-27
Publication date: 2023-06-30

Abstract

The application provides a volume measurement method, a volume measurement device, computer equipment and a storage medium for warehouse goods, wherein the method comprises the following steps: acquiring three-dimensional point cloud data of the warehouse goods to be tested; carrying out deep filtering treatment on the three-dimensional point cloud data based on a preset impurity influence sequence to obtain filtered three-dimensional point cloud data; performing point cloud filling processing on the three-dimensional point cloud data after filtering to obtain target three-dimensional point cloud data; and analyzing the target three-dimensional point cloud data to obtain the cargo volume information of the warehouse cargo to be tested. By adopting the method, the point cloud data of the stored goods to be detected can be accurately extracted and perfected, and the volume measurement accuracy of the stored goods is effectively improved.

Description

Volume measurement method and device for warehouse goods, computer equipment and storage medium

Technical Field

The embodiment of the application relates to the technical field of machine vision, in particular to a volume measurement method and device for warehouse goods, computer equipment and a storage medium.

Background

With the continuous development of the technical field of machine vision, the cargo volume measuring method is also greatly improved.

The traditional cargo volume measurement method generally adopts a manual measurement or planar two-dimensional vision technology measurement mode; the manual measurement mode mainly depends on the precision of a measuring ruler, and has large subjective difference, large workload and low efficiency; the measurement mode of the planar two-dimensional vision technology is mainly to calculate the actual size of an object by utilizing the conversion relation between the pixel length and the physical length under the fixed depth of field, but because of the limitation of the imaging principle, namely, the specific analysis cannot be carried out according to the actual situation of near-large and far-small, the measurement can only be carried out on single-specification goods, when the method is combined with a logistics application scene, the targeted measurement cannot be carried out according to the goods with different specifications, and the volume of the stored goods cannot be accurately measured.

Therefore, the conventional cargo volume measuring method has a problem of low measurement accuracy.

Disclosure of Invention

The invention aims to provide a volume measurement method, device, computer equipment and storage medium for stored goods, which are used for improving the volume measurement accuracy of the stored goods.

In a first aspect, the present application provides a method for measuring the volume of a warehouse cargo, comprising:

Acquiring three-dimensional point cloud data of the warehouse goods to be tested;

carrying out deep filtering treatment on the three-dimensional point cloud data based on a preset impurity influence sequence to obtain filtered three-dimensional point cloud data;

performing point cloud filling processing on the three-dimensional point cloud data after filtering to obtain target three-dimensional point cloud data;

and analyzing the target three-dimensional point cloud data to obtain the cargo volume information of the warehouse cargo to be tested.

In some embodiments of the present application, the order of the depth filter process includes: a first filtering process, a second filtering process, and a third filtering process; the first filtering process is used for screening out third target point cloud data in the three-dimensional point cloud data to obtain a second point cloud set; the second filtering process is used for screening out fifth target point cloud data in the second point cloud set to obtain a fourth point cloud set; and the third filtering process is used for screening out seventh target point cloud data in the fourth point cloud set so as to obtain filtered three-dimensional point cloud data.

In some embodiments of the present application, based on a preset impurity influence sequence, deep filtering is performed on three-dimensional point cloud data to obtain filtered three-dimensional point cloud data, including: acquiring first target point cloud data corresponding to the three-dimensional point cloud data to obtain a first point cloud set; responding to the fact that the first target point cloud data meets a preset coordinate threshold condition, clustering and screening the first target point cloud data to obtain second target point cloud data in each point cloud set; wherein the second target point cloud data includes Z-axis data; screening second target point cloud data with minimum Z-axis data as third target point cloud data aiming at each point cloud set, performing first filtering processing on the three-dimensional point cloud data, and counting to obtain a second point cloud set; and performing second filtering processing on the third target point cloud data to obtain filtered three-dimensional point cloud data.

In some embodiments of the present application, performing a second filtering process on the third target point cloud data to obtain filtered three-dimensional point cloud data, including: establishing a first K-D tree structure according to the cloud data of the third target point; based on the first K-D tree structure, performing nearest neighbor search on third target point cloud data to obtain a third point cloud set comprising K fourth target point cloud data; calculating the standard deviation of the third point cloud set according to the Z-axis data of the fourth target point cloud data; in response to the standard deviation being smaller than a preset standard deviation threshold, reserving fourth target point cloud data as fifth target point cloud data, performing second filtering processing on the third target point cloud data, and counting to obtain a fourth point cloud set; and performing third filtering processing on the fourth point cloud set to obtain three-dimensional point cloud data after filtering.

In some embodiments of the present application, the method for measuring the volume of the warehouse cargo further includes: responding to the standard deviation being greater than or equal to a preset standard deviation threshold value, and calculating a first Z-axis average value of the third point cloud set according to Z-axis data of the fourth point cloud data; and screening fourth target point cloud data with Z-axis data larger than the first Z-axis average value as fifth target point cloud data, performing second filtering processing on the third target point cloud data, and counting to obtain a fourth point cloud set.

In some embodiments of the present application, performing a third filtering process on the fourth point cloud set to obtain filtered three-dimensional point cloud data, including: screening out ground point cloud data in the fourth point cloud set to obtain a fifth point cloud set comprising sixth point cloud data; acquiring first average distance data among cloud data of each sixth target point, and updating a preset point distance threshold according to the first average distance data to obtain an updated point distance threshold; establishing a second K-D tree structure corresponding to the cloud data of the sixth target point, and acquiring second average distance data according to the second K-D tree structure; and in response to the second average distance data being less than the updated point distance threshold, preserving the sixth target point cloud data and the ground point cloud data as seventh target point cloud data to update the fifth point cloud set, and obtaining an updated fifth point cloud set.

In some embodiments of the present application, updating a preset point distance threshold according to the first average distance data to obtain an updated point distance threshold includes: obtaining a quotient between the first average distance data and a preset average distance to obtain a point distance threshold scaling factor; and obtaining a product value between the point distance threshold scaling factor and a preset point distance threshold to update the preset point distance threshold and obtain an updated point distance threshold.

In some embodiments of the present application, obtaining second average distance data according to a second K-D tree structure includes: performing nearest neighbor search on the cloud data of the sixth target point according to the second K-D tree structure to obtain a nearest neighbor point cloud set comprising K nearest neighbor point clouds; acquiring the point cloud distance between each sixth target point cloud data and each nearest neighbor point cloud to obtain a distance set; and obtaining the average distance corresponding to the point cloud distance, and obtaining second average distance data.

In some embodiments of the present application, the method for measuring the volume of the warehouse cargo further includes: responding to the fact that the second average distance data is larger than or equal to the updated distance threshold value, filtering out cloud data of a sixth target point to update a fifth point cloud set, and obtaining an updated fifth point cloud set; adding the ground point cloud data to the updated fifth point cloud set to perform third filtering processing on the fourth point cloud set; and taking the point cloud data in the updated fifth point cloud set as seventh target point cloud data, and carrying out statistics to obtain filtered three-dimensional point cloud data.

In some embodiments of the present application, performing a point cloud filling process on the filtered three-dimensional point cloud data to obtain target three-dimensional point cloud data, including: acquiring starting point cloud data based on a preset bar frame length scaling factor and a preset bar frame step length; screening out filtered three-dimensional point cloud data within a preset bar frame range according to the starting point cloud data and a preset in-frame center point cloud to obtain in-frame point cloud data; acquiring a second Z-axis average value according to Z-axis data of the point cloud data in the frame; and performing point cloud filling processing on the three-dimensional point cloud data after filtering according to the second Z-axis average value and the in-frame center point cloud to obtain target three-dimensional point cloud data.

In some embodiments of the present application, according to the second Z-axis average value and the in-frame center point cloud, performing point cloud filling processing on the filtered three-dimensional point cloud data to obtain target three-dimensional point cloud data, including: performing point cloud boundary filling processing on the three-dimensional point cloud data after filtering according to the second Z-axis average value and the in-frame center point cloud to obtain preliminarily filled three-dimensional point cloud data; and interpolating and filling the primarily filled three-dimensional point cloud data based on a piecewise linear interpolation method to obtain target three-dimensional point cloud data.

In some embodiments of the present application, before acquiring the three-dimensional point cloud data of the warehouse cargo to be tested, the method further includes: acquiring initial three-dimensional point cloud data of the warehouse goods to be tested, and performing three-dimensional coordinate conversion on the initial three-dimensional point cloud data to obtain an initial plane normal vector; performing ground fitting on the initial three-dimensional point cloud data to obtain a real plane normal vector; acquiring the information of an included angle between a normal vector of a real plane and a normal vector of an initial plane; and carrying out coordinate correction on the initial three-dimensional point cloud data according to the included angle information to obtain three-dimensional point cloud data.

In some embodiments of the present application, analyzing target three-dimensional point cloud data to obtain cargo volume information of a warehouse cargo to be tested includes: accumulating Z-axis data of the target three-dimensional point cloud data to obtain cargo height information; obtaining the product value between the cargo height information and the step length square value to obtain cargo volume information; the square value of the step length is a square product value of the step length of the preset bar frame.

In a second aspect, the present application provides a volume measurement device for warehoused cargo, comprising:

the point cloud acquisition module is used for acquiring three-dimensional point cloud data of the warehouse goods to be tested;

the point cloud filtering module is used for performing deep filtering processing on the three-dimensional point cloud data based on a preset impurity influence sequence to obtain filtered three-dimensional point cloud data;

the point cloud filling module is used for carrying out point cloud filling processing on the filtered three-dimensional point cloud data to obtain target three-dimensional point cloud data;

and the volume analysis module is used for analyzing the target three-dimensional point cloud data to obtain the cargo volume information of the warehouse cargo to be tested.

In a third aspect, the present application also provides a computer device comprising:

one or more processors;

a memory; and one or more applications stored in the memory and configured to be executed by the processor to implement the method of measuring volume of the warehouse cargo of the first aspect.

In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program to be loaded by a processor for performing steps in a method of volumetric measurement of warehoused cargo.

In a fifth aspect, embodiments of the present application provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the method provided in the first aspect.

According to the volume measurement method, the volume measurement device, the computer equipment and the storage medium of the warehouse goods, the server obtains three-dimensional point cloud data of the warehouse goods to be measured, performs deep filtering processing on the three-dimensional point cloud data based on the preset impurity influence sequence, can obtain filtered three-dimensional point cloud data, further performs point cloud filling processing on the filtered three-dimensional point cloud data, can obtain target three-dimensional point cloud data, and finally analyzes the target three-dimensional point cloud data to obtain the goods volume information of the warehouse goods to be measured. By adopting the method, the point cloud data of the stored goods to be detected can be accurately extracted and perfected, and the volume measurement accuracy of the stored goods is effectively improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic view of a scenario of a method for measuring the volume of a warehouse cargo according to an embodiment of the present application;

fig. 2 is a flow chart of a method for measuring the volume of a warehouse cargo according to an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of an interface of three-dimensional point cloud data according to an embodiment of the present disclosure;

fig. 4 is a second schematic interface diagram of three-dimensional point cloud data provided in an embodiment of the present application;

fig. 5 is a third schematic interface diagram of three-dimensional point cloud data provided in an embodiment of the present application;

fig. 6 is a schematic diagram of an interface of three-dimensional point cloud data provided in an embodiment of the present application;

fig. 7 is a fifth interface schematic diagram of three-dimensional point cloud data provided in an embodiment of the present application;

FIG. 8 is a schematic diagram of a system for volumetric measurement of warehouse cargo provided in an embodiment of the present application;

fig. 9 is a schematic structural view of a volume measurement device for warehouse cargo provided in an embodiment of the present application;

fig. 10 is a schematic structural diagram of a computer device provided in an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.

In the description of the present application, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

In the description of the present application, the term "for example" is used to mean "serving as an example, instance, or illustration. Any embodiment described herein as "for example" is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the invention. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present invention may be practiced without these specific details. In other instances, well-known structures and processes have not been described in detail so as not to obscure the description of the invention with unnecessary detail. Thus, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

The method for measuring the volume of the warehouse goods mainly relates to a machine vision technology, which is an interdisciplinary subject related to the fields of artificial intelligence, computer science, image processing, pattern recognition and the like, and mainly uses a computer to simulate the visual function of a person, extract information from an image of an objective object, process and understand the information, and finally be used for actual detection, measurement and control. The machine vision technology specifically refers to that an optical imaging technology (usually using a camera) is adopted to acquire an image of a detected target, and then the information such as the size, the position, the direction, the spectral characteristics, the structure, the defects and the like of the target is acquired from the acquired image through a rapid image processing and pattern recognition algorithm, so that the tasks such as product inspection, classification and grouping can be performed.

In the embodiment of the present application, the method for measuring the volume of the warehouse cargo provided in the embodiment of the present application may be applied to a volume measurement system as shown in fig. 1. Wherein the volume measurement system comprises a terminal 102 and a server 104. The terminal 102 may be a device that includes both receive and transmit hardware, i.e., a device having receive and transmit hardware capable of performing bi-directional communications over a bi-directional communication link. Such a device may include: a cellular or other communication device having a single-line display or a multi-line display or a cellular or other communication device without a multi-line display. The terminal 102 may be a desktop terminal or a mobile terminal, and the terminal 102 may be one of a mobile phone, a tablet computer, and a notebook computer. The server 104 may be a stand-alone server, or may be a server network or a server cluster of servers, including but not limited to a computer, a network host, a single network server, a set of multiple network servers, or a cloud server of multiple servers. Wherein the Cloud server is composed of a large number of computers or web servers based on Cloud Computing (Cloud Computing). In addition, the terminal 102 and the server 104 establish a communication connection through a network, and the network may specifically be any one of a wide area network, a local area network, and a metropolitan area network.

Those skilled in the art will appreciate that the application environment shown in fig. 1 is only one application scenario applicable to the present application, and is not limited to the application scenario of the present application, and other application environments may include more or fewer devices than those shown in fig. 1. For example, only 1 server 104 is shown in FIG. 1. It will be appreciated that the volume measurement system of the warehouse cargo may also include one or more other servers, particularly without limitation. In addition, as shown in fig. 1, the volume measurement system may further include a memory for storing data, such as three-dimensional point cloud data of the warehouse cargo to be measured.

It should be noted that, the schematic view of the scenario of the volumetric measurement system shown in fig. 1 is only an example, and the volumetric measurement system and scenario described in the embodiment of the present invention are for more clearly describing the technical solution of the embodiment of the present invention, and do not constitute a limitation on the technical solution provided by the embodiment of the present invention, and those skilled in the art can know that, with the evolution of the volumetric measurement system and the appearance of a new service scenario, the technical solution provided by the embodiment of the present invention is equally applicable to similar technical problems.

Referring to fig. 2, an embodiment of the present application provides a method for measuring the volume of a warehouse cargo, and the embodiment is mainly exemplified by the method being applied to the server 104 in fig. 1, and the method includes steps S201 to S204, which are specifically as follows:

s201, acquiring three-dimensional point cloud data of the warehouse goods to be tested.

The warehouse goods to be tested can be the volume goods to be tested which are stored in a warehouse, the warehouse can be any shape and size, and the goods can also be any shape and size. For example, the warehouse cargo to be tested may be grains, coal, etc.

The point cloud refers to a point data set of the appearance surface of a product obtained by a measuring instrument in reverse engineering, and can be divided into sparse point cloud and dense point cloud according to the degree of density of the number of points. The three-dimensional point cloud is a set of point clouds in three dimensional directions in a space dimension, namely a set of point clouds existing in a left space, a right space, an up space, a down space and a front space and a back space. It should be noted that, the format of the three-dimensional point cloud data related to the embodiment of the present application is "XYZI", where "XYZ" is a spatial position point of the point cloud in the world coordinate system, and "I" is the intensity of the radar point cloud.

In a specific implementation, three-dimensional point cloud data of the warehouse cargo to be detected can be derived from a laser radar, and a beam of light pulse is mainly generated and emitted by a laser of the laser radar, and is beaten on an object and reflected back to be received by a receiver. In this way, the receiver can accurately measure the propagation time of the light pulse from the emission to the reflection, and in view of the fact that the light speed is known, the propagation time can be converted into the measurement of the distance, and finally, the three-dimensional coordinate X, Y, Z of each ground light spot can be accurately calculated by combining the height of the laser and the laser scanning angle.

Therefore, the server 104 may obtain the three-dimensional point cloud data of the warehouse goods to be tested through the laser radar with the communication connection established in advance, and the obtaining mode may be waiting for real-time transmission of the laser radar, or active access based on the preset time, or forwarding through other intermediate medium devices, which is not limited in the application. However, it should be noted that the three-dimensional point cloud data acquired by the server 104 at this time may be three-dimensional point cloud data transferred to the world coordinate system, as shown in fig. 3, the direction of the warehouse broadside is the X direction, the direction of the warehouse long side is the Y direction, the direction of the warehouse wall height is the Z direction, and the intersection point of the long side, the broadside and the ground in the lower right corner of the warehouse is the origin O.

In one embodiment, before this step, further comprising: acquiring initial three-dimensional point cloud data of the warehouse goods to be tested, and performing three-dimensional coordinate conversion on the initial three-dimensional point cloud data to obtain an initial plane normal vector; performing ground fitting on the initial three-dimensional point cloud data to obtain a real plane normal vector; acquiring the information of an included angle between a normal vector of a real plane and a normal vector of an initial plane; and carrying out coordinate correction on the initial three-dimensional point cloud data according to the included angle information to obtain three-dimensional point cloud data.

In particular, the embodiment proposes that the three-dimensional point cloud data obtained by the server 104 is not only data converted by a coordinate system, but also data corrected by the coordinate system, and how to perform coordinate correction on the initial three-dimensional point cloud data will be described in detail in the embodiment.

Specifically, after the server 104 initially obtains the three-dimensional point cloud data of the warehouse cargo to be measured, the three-dimensional point cloud data is first transferred to the world coordinate system to determine the origin O of the three-dimensional point cloud data, so that the volume can be measured and calculated conveniently by analyzing coordinates based on the origin O, but since the three-dimensional point cloud data cannot be accurately transferred to the world coordinate system, the server 104 also corrects the coordinates, such as fitting the ground by using "random", thereby eliminating the conversion error of the Z axis and improving the precision of the subsequent volume measurement and calculation.

Further, "ransac" is an abbreviation for random sample consensus algorithm (Random Sample Consensus), which is an algorithm that calculates model parameters of data from a set of sample data sets containing outlier data, resulting in valid sample data. Before the server 104 performs the coordinate correcting operation by adopting the algorithm, the initially obtained three-dimensional point cloud data can be used as initial three-dimensional point cloud data, so as to perform "random" ground fitting on the initial three-dimensional point cloud data to obtain a real plane normal vector "v1", and three-dimensional coordinate conversion which is subjected to coordinate conversion before fitting can also determine an initial plane normal vector "v2" based on an initial conversion result, and it is noted that the steps of obtaining the real plane normal vector "v1" and the initial plane normal vector "v2" can be performed in different order.

Further, after the server 104 obtains the real plane normal vector "v1" and the initial plane normal vector "v2", the difference between "v1" and "v2" may be calculated as the angle information "θ" between the real plane normal vector and the initial plane normal vector. Thus, the primarily converted three-dimensional point cloud data is rotated according to the included angle information 'theta', and coordinate correction of the three-dimensional point cloud data can be achieved.

S202, deep filtering is carried out on the three-dimensional point cloud data based on a preset impurity influence sequence, and filtered three-dimensional point cloud data are obtained.

The impurity influence sequence may be a sequence preset according to the influence of the volume measurement from large to small, for example, the impurity influence sequence is as follows: other surfaces of the warehouse body except the ground, working vehicles, storage racks, suspended matters in the air and the like.

In a specific implementation, in order to accurately measure the volume of the warehouse cargo, after the server 104 obtains the three-dimensional point cloud data of the warehouse cargo to be measured, the point cloud data belonging to the warehouse and the point cloud data of other impurities affecting the volume measurement of the cargo are also removed. Therefore, the application provides three filtering modes, which comprise: the first filtering process, the second filtering process and the third filtering process to implement the deep filtering process on the three-dimensional point cloud data through these three processes, and the specific implementation steps will be described in detail below.

In one embodiment, the order of the depth filter process includes: a first filtering process, a second filtering process, and a third filtering process; the first filtering process is used for screening out third target point cloud data in the three-dimensional point cloud data to obtain a second point cloud set; the second filtering process is used for screening out fifth target point cloud data in the second point cloud set to obtain a fourth point cloud set; and the third filtering process is used for screening out seventh target point cloud data in the fourth point cloud set so as to obtain filtered three-dimensional point cloud data.

In a specific implementation, the first filtering process, the second filtering process and the third filtering process are sequentially implemented, the first filtering process mainly comprises clipping filtering and vertical direction de-duplication, the second filtering process mainly comprises nearest neighbor filtering in the Z-axis direction, and the third filtering process mainly comprises self-adaptive density filtering. The third target point cloud data, the fifth target point cloud data, and the seventh target point cloud data related in the present embodiment, and specific acquisition steps and processing steps will be sequentially described in the following embodiments.

In one embodiment, the step includes: acquiring first target point cloud data corresponding to the three-dimensional point cloud data to obtain a first point cloud set; responding to the fact that the first target point cloud data meets a preset coordinate threshold condition, clustering and screening the first target point cloud data to obtain second target point cloud data in each point cloud set; wherein the second target point cloud data includes Z-axis data; screening second target point cloud data with minimum Z-axis data as third target point cloud data aiming at each point cloud set, performing first filtering processing on the three-dimensional point cloud data, and counting to obtain a second point cloud set; and performing second filtering processing on the third target point cloud data to obtain filtered three-dimensional point cloud data.

In a specific implementation, the server 104 may perform downsampling on the three-dimensional point cloud data to obtain downsampled three-dimensional point cloud data as the first target point cloud data, and statistics is used as the first point cloud set. The downsampled sampling radius may be "0.1m", or may be set to another parameter, which is not limited in the present application.

Further, before analyzing the cloud data of each first target point included in the first point cloud set, the server 104 has a size coordinate threshold of the warehouse in the world coordinate system, specifically: X_MIN, X_MAX, Y_MIN, Y_MAX, Z_MIN, Z_MAX. With the above size coordinate threshold, the server 104 may further analyze and determine whether each first target point cloud data meets a preset coordinate threshold condition, where the coordinate threshold condition is composed of the above size coordinate threshold, specifically: the point cloud p satisfies the conditions of "(p.x > x_min) & (p.x < x_max) & (p.y > y_min) & (p.y < y_max) & (p.z > z_max) & (p.z < z_max)", where "&" means "and" p.x, p.y, p.z "are the X-axis coordinate value, Y-axis coordinate value, and Z-axis coordinate value of the first target point cloud data" p "currently determined.

For example, after acquiring the first target point cloud data, the server 104 will determine whether each of the first target point cloud data "p" satisfies: the X-axis coordinate values are between the dimension coordinate thresholds (x_min to x_max), the Y-axis coordinate values are between the dimension coordinate thresholds (y_min to y_max), and the Z-axis coordinate values are between the dimension coordinate thresholds (z_min to z_max); if the coordinate threshold condition is satisfied, the first target point cloud data "p" may be retained; and if the coordinate threshold condition is not met, removing. Thus, all the first target point cloud data "p" are traversed, and the reserved first target point cloud data can be obtained.

Furthermore, the above steps are all considered to be the influence of each warehouse to the measurement of the cargo volume, and in addition, the point cloud may have the same (x, y) coordinates in the vertical direction (the Z axis direction), but different points in Z, but in order to improve the accuracy of the measurement of the cargo volume, only one point needs to be reserved in this case.

For example, for the first target point cloud data that is retained, cluster screening may be further performed on the first target point cloud data, where if all points satisfying "(p_ f.x = p.x) & (p_ f.y = p.y)" in the first target point cloud data that is retained are searched, each point cloud set "p_f" is searched (the first target point cloud data that belongs to the same p_f may be used as the second target point cloud data, and the coordinates of the second target point cloud data in the same "p_f" in the X axis and the Y axis are the same, then "p_ f.x, p_ f.y" may be used as the cluster center). After that, the server 104 may filter, for each point cloud set "p_f", the second target point cloud data in which the Z-axis data is the minimum value as the third target point cloud data one by one, that is, the second target point cloud data in each point cloud set "p_f" includes the Z-axis data "p_ f.z", and the filtered third target point cloud data has the Z-axis data of "p_f_min". After that, the server 104 may perform a second filtering process on the third target point cloud data, and a specific second filtering process step will be described in detail below.

In one embodiment, the step includes: establishing a first K-D tree structure according to the cloud data of the third target point; based on the first K-D tree structure, performing nearest neighbor search on third target point cloud data to obtain a third point cloud set comprising K fourth target point cloud data; calculating the standard deviation of the third point cloud set according to the Z-axis data of the fourth target point cloud data; in response to the standard deviation being smaller than a preset standard deviation threshold, reserving fourth target point cloud data as fifth target point cloud data, performing second filtering processing on the third target point cloud data, and counting to obtain a fourth point cloud set; and performing third filtering processing on the fourth point cloud set to obtain three-dimensional point cloud data after filtering.

In a specific implementation, in order to better separate noise of the types of working vehicles, racks, suspended matters in the air and the like possibly included in the warehouse, in this embodiment, a nearest neighbor filtering based on a vertical direction (z direction) is provided for efficiently filtering the point cloud noise. Specifically, the server 104 may first establish a KDTree for the third target point cloud data, resulting in a first K-D tree structure. Wherein a K-D tree (K-dimension) is a data structure that partitions K-Dimensional data space.

Further, the server 104 may perform nearest neighbor search on a certain point cloud in the third point cloud data based on the first K-D tree structure, "k=30", obtain a third point cloud set "p_n", calculate an average value "z_mean" and/or a standard deviation "z_std" for the z coordinate in the third point cloud set "p_n", and if the standard deviation "z_std is less than thres_std", respond to the standard deviation being less than a preset standard deviation threshold "thres_std", and reserve all fourth point cloud data in the third point cloud set "p_n" as fifth point cloud data, and obtain a fourth point cloud set through statistics. After that, the server 104 also performs a third filtering process on the fourth point cloud set, and a specific third filtering process step will be described in detail below.

In one embodiment, the step includes: responding to the standard deviation being greater than or equal to a preset standard deviation threshold value, and calculating a first Z-axis average value of the third point cloud set according to Z-axis data of the fourth point cloud data; and screening fourth target point cloud data with Z-axis data larger than the first Z-axis average value as fifth target point cloud data, performing second filtering processing on the third target point cloud data, and counting to obtain a fourth point cloud set.

In specific implementation, this embodiment will supplement the description that the standard deviation "z_std" is not less than the standard deviation threshold "thres_std", that is, if the server 104 detects that "z_std is greater than or equal to thres_std", the third point cloud set "p_n" is traversed, only the fourth target point cloud data with z value greater than the average value "z_mean" in "p_n" is reserved as the fifth target point cloud data, and the fourth point cloud set is obtained through statistics, where the second filtering effect can refer to fig. 4.

In one embodiment, the step includes: screening out ground point cloud data in the fourth point cloud set to obtain a fifth point cloud set comprising sixth point cloud data; acquiring first average distance data among cloud data of each sixth target point, and updating a preset point distance threshold according to the first average distance data to obtain an updated point distance threshold; establishing a second K-D tree structure corresponding to the cloud data of the sixth target point, and acquiring second average distance data according to the second K-D tree structure; and in response to the second average distance data being less than the updated point distance threshold, preserving the sixth target point cloud data and the ground point cloud data as seventh target point cloud data to update the fifth point cloud set, and obtaining an updated fifth point cloud set.

In a specific implementation, in order to better separate noise of types such as a working vehicle, a rack, and an air suspension, which may be included in a warehouse, and avoid that part of the noise remained in the previous step is not sufficiently filtered, an adaptive density filtering is provided in the embodiment, so as to supplement and filter the point cloud noise.

Specifically, the server 104 may first screen out the ground point cloud data in the fourth point cloud set, and the remaining point cloud data is used as the sixth target point cloud data to obtain a fifth point cloud set including the sixth target point cloud data. Further, the server 104 may calculate an average distance between cloud data of each sixth target point to obtain first average distance data "volume_size", so as to update the preset point distance threshold "distance_threshold_orgin" according to the first average distance data "volume_size", and obtain an updated point distance threshold "distance_threshold", where a calculation relationship between each data will be described in detail below.

Further, the server 104 may establish a KDTree for the sixth target point cloud data to obtain a second K-D tree structure, and may further perform nearest neighbor search on a point cloud in the sixth target point cloud data based on the second K-D tree structure to obtain second average distance data "distance_mean", where specific implementation steps will be described in detail below.

Still further, if the server 104 detects "distance_mean < distance_threshold", the point cloud performing the nearest neighbor search described above may be retained, and all the sixth target point cloud data in the fifth point cloud set is traversed until the sixth target point cloud data of all the retained point clouds is obtained and used as the seventh target point cloud data.

In one embodiment, the step includes: obtaining a quotient between the first average distance data and a preset average distance to obtain a point distance threshold scaling factor; and obtaining a product value between the point distance threshold scaling factor and a preset point distance threshold to update the preset point distance threshold and obtain an updated point distance threshold.

In a specific implementation, for updating a preset point distance threshold, the server 104 may calculate a quotient of the first average distance data "volume_size" and the preset average distance "mean_distance" to obtain a point distance threshold scaling factor "ratio", i.e., "ratio=volume_size/mean_distance", and further calculate a product value between the point distance threshold scaling factor "ratio" and the point distance threshold "distance_threshold_orgin" to obtain an updated point distance threshold "distance_threshold", i.e., "distance_threshold=distance_threshold_orgin".

In one embodiment, the step includes: performing nearest neighbor search on the cloud data of the sixth target point according to the second K-D tree structure to obtain a nearest neighbor point cloud set comprising K nearest neighbor point clouds; acquiring the point cloud distance between each sixth target point cloud data and each nearest neighbor point cloud to obtain a distance set; and obtaining the average distance corresponding to the point cloud distance, and obtaining second average distance data.

In a specific implementation, before the server 104 obtains the second average distance data, nearest neighbor searching may be performed on a certain sixth target point cloud data in the fifth point cloud set according to the second K-D tree structure, that is, K points nearest to each sixth target point cloud data are searched, so as to obtain a neighboring point cloud set "p_n". Then, the distances between the cloud data of each sixth target point and k neighboring points of the cloud data of each sixth target point are calculated, a distance set (nn_dist) can be obtained, and the average distance of the distance set (nn_dist) is obtained, so that second average distance data (distance_mean) is obtained.

In one embodiment, the step includes: responding to the fact that the second average distance data is larger than or equal to the updated distance threshold value, filtering out cloud data of a sixth target point to update a fifth point cloud set, and obtaining an updated fifth point cloud set; adding the ground point cloud data to the updated fifth point cloud set to perform third filtering processing on the fourth point cloud set; and taking the point cloud data in the updated fifth point cloud set as seventh target point cloud data, and carrying out statistics to obtain filtered three-dimensional point cloud data.

In a specific implementation, if the second average distance data "distance_mean" is greater than or equal to the updated distance threshold "distance_threshold", the sixth target point cloud data is filtered, so that each sixth target point cloud data in the fifth point cloud set is traversed, which remain and which filter are analyzed to update the fifth point cloud set, and an updated fifth point cloud set is obtained.

Further, after the updated fifth point cloud set is obtained based on the analysis of the present embodiment, or after the updated fifth point cloud set is obtained based on the analysis of the foregoing embodiment, the ground point cloud data that is filtered initially may be added back, that is, the ground point cloud data is added to the updated fifth point cloud set, to obtain a point cloud set "p_g" including the seventh target point cloud data, and the third filtering effect may refer to fig. 5.

And S203, performing point cloud filling processing on the three-dimensional point cloud data after filtering to obtain target three-dimensional point cloud data.

In a specific implementation, the point cloud filling includes not only boundary filling of the point cloud, but also coverage filling of the point cloud, and a specific sequence can be preset for filling steps of different positions, which is not specifically limited in the embodiment of the present application, but will be described in detail below with the boundary filling being first and the coverage filling being later.

In one embodiment, the step includes: acquiring starting point cloud data based on a preset bar frame length scaling factor and a preset bar frame step length; screening out filtered three-dimensional point cloud data within a preset bar frame range according to the starting point cloud data and a preset in-frame center point cloud to obtain in-frame point cloud data; acquiring a second Z-axis average value according to Z-axis data of the point cloud data in the frame; and performing point cloud filling processing on the three-dimensional point cloud data after filtering according to the second Z-axis average value and the in-frame center point cloud to obtain target three-dimensional point cloud data.

Wherein the bar frame length scale factor is denoted "mult" and the bar frame step size is denoted "delta".

In specific implementation, the three filtering steps are processed to obtain a point cloud set "p_g" including filtered three-dimensional point cloud data, and the size coordinate threshold is: X_MIN, X_MAX, Y_MIN, Y_MAX, Z_MIN, Z_MAX. First, on the boundary line of x=x_min, cloud data "begin_point" as a starting point, which is somewhat within a (delta) bar region, is found.

Further, the preset in-frame center point cloud includes: (x=x_min, y=y), (x=x, y=y_min), (x=x, y=y_max), (x=x_max), and (x=x_max, y=y). Acquiring in-frame point cloud data according to the start point cloud data 'begin_point' and the center point clouds in each frame, and further acquiring a second Z-axis average value to acquire target three-dimensional point cloud data, wherein the steps of acquiring the target three-dimensional point cloud data comprise the following steps:

(1) Finding out in-frame point cloud data in the range of 'begin_point' rightwards (y+ direction), taking the coordinate point as a center point by using an adaptive bar frame, forming a point set 'P_t', averaging Z-axis data (Z values) of all points in the point set 'P_t', obtaining a second Z-axis average value 'z_p_mean', adding (X_MIN, y, z_p_mean) into the point cloud 'P' of the fillable boundary point, and traversing all coordinate values of the direction (y+).

(2) From "begin_point" to the left (y-direction), the operation in (1) above traverses all coordinate values in this direction (y-).

(3) Starting from the (x=x_min, y=y_min) coordinate point, finding in the frame center point cloud (x=x, y=y_min) by using the adaptive bar frame, taking the coordinate point as the center point, and adding (y_min-delta) mult +.y +.y_min+delta +.mu +.x+delta) in the frame point cloud data in the range of (X-delta +.x +.delta), forming a point set "p_t", then averaging the Z-axis data (Z-value) of all points in the point set "p_t" to obtain a second Z-axis average value "z_p_mean", and finally adding (X, y_min, z_p_mean) to the point cloud set "P" of fillable boundary points, and traversing all coordinate values in the direction (x+).

(4) Starting from the (x=x_min, y=y_max) coordinate point, finding out in the frame the in-frame center point cloud (x=x, y=y_max) by using the self-adaptive bar frame, taking the coordinate point as the center point, forming a point set "p_t" by using the in-frame point cloud data in the range of "(y_max-delta +.y +.y_max+delta +.mut)/(X-delta +.x+delta)", and then averaging the Z-axis data (Z values) of all points in the point set "p_t" to obtain a second Z-axis average value "z_p_mean", adding (X, y_max, z_p_mean) to the point cloud set "P" of fillable boundary points, and traversing all coordinate values in the direction (x+).

(5) From (x=x_max, y=y_min) to the right (y+ direction), finding an in-frame center point cloud (x=x_max, y=y) using an adaptive bar frame, taking the coordinate point as a center point, forming a point set "p_t" by using in-frame point cloud data in the range of "(x_max-delta x_max+delta_mut) & (Y-delta y+delta) & lt)", and then averaging Z-axis data (Z values) of all points in the point set "p_t" to obtain a second Z-axis average value "z_p_mean", adding (x_max, Y x_p_mean) to the point cloud set "P" of fillable boundary points, and traversing all coordinate values in the direction (y+).

In this way, the point cloud set "P" is obtained through the above analysis, where the point cloud data can be all the target three-dimensional point cloud data, and the target three-dimensional point cloud data includes the point cloud data in the point cloud set "p_g", and the effect of the point cloud boundary filling process can be referred to fig. 6.

In one embodiment, the step includes: performing point cloud boundary filling processing on the three-dimensional point cloud data after filtering according to the second Z-axis average value and the in-frame center point cloud to obtain preliminarily filled three-dimensional point cloud data; and interpolating and filling the primarily filled three-dimensional point cloud data based on a piecewise linear interpolation method to obtain target three-dimensional point cloud data.

In a specific implementation, the foregoing embodiment has described the detailed steps of the point cloud boundary filling process, after that, the server 104 may also perform interpolation filling on the point cloud data output in the previous step by using a piecewise linear interpolation method, so as to obtain sufficiently complete and accurate target three-dimensional point cloud data, and the effect of the interpolation filling process may refer to fig. 7.

S204, analyzing the target three-dimensional point cloud data to obtain the cargo volume information of the warehouse cargo to be tested.

In a specific implementation, after performing the preamble operation on the three-dimensional point cloud data of the warehouse goods to be tested, the server 104 obtains the target three-dimensional point cloud data with sufficient integrity and accuracy, and uses the target three-dimensional point cloud data as an analysis basis for volume measurement, and analyzes to obtain the volume of the goods to be tested stored in the warehouse, and specific steps will be described in detail below.

In one embodiment, the step includes: accumulating Z-axis data of the target three-dimensional point cloud data to obtain cargo height information; obtaining the product value between the cargo height information and the step length square value to obtain cargo volume information; the square value of the step length is a square product value of the step length of the preset bar frame.

In specific implementation, the Z-axis data (Z-value) of the target three-dimensional point cloud data is accumulated to obtain cargo height information "H", and then "h×delta×delta" is calculated to obtain cargo volume information. The value of the step length delta of the bar frame can be 0.01, even smaller than the value of 0.01, and the accuracy is higher as the value is smaller.

According to the volume measurement method for the warehouse goods, the server obtains three-dimensional point cloud data of the warehouse goods to be measured, performs deep filtering processing on the three-dimensional point cloud data based on a preset impurity influence sequence, and can obtain filtered three-dimensional point cloud data, further performs point cloud filling processing on the filtered three-dimensional point cloud data, can obtain target three-dimensional point cloud data, and finally analyzes the target three-dimensional point cloud data to obtain the goods volume information of the warehouse goods to be measured. By adopting the method, the point cloud data of the stored goods to be detected can be accurately extracted and perfected, and the volume measurement accuracy of the stored goods is effectively improved.

In order to facilitate a thorough understanding of the embodiments of the present application, a specific example will be described below in connection with fig. 8.

Referring to fig. 8, a correction module, a filtering module, a filling boundary module, a filling module and a volume measuring module may be integrated in a volume measuring system of the warehouse goods, and the volume measuring system is installed in the server 104, after three-dimensional point cloud data of the warehouse goods to be measured are acquired by an operating system of the server 104, the three-dimensional point cloud data are firstly input into the volume measuring system of the integrated module, coordinate correction of a z-axis is sequentially performed through the correction module, noise, suspended matters and the like are filtered through the filtering module and the filling boundary module, and point cloud boundary is filled through the filling module, and the goods volume information of the warehouse goods to be measured can be obtained through calculation of a volume result by the volume calculating module.

In this embodiment, the server obtains three-dimensional point cloud data of the warehouse goods to be tested, performs deep filtering processing on the three-dimensional point cloud data based on a preset impurity influence sequence, and can obtain filtered three-dimensional point cloud data, further performs point cloud filling processing on the filtered three-dimensional point cloud data, can obtain target three-dimensional point cloud data, and finally analyzes the target three-dimensional point cloud data to obtain the goods volume information of the warehouse goods to be tested. By adopting the method, the point cloud data of the stored goods to be detected can be accurately extracted and perfected, and the volume measurement accuracy of the stored goods is effectively improved.

It should be understood that, although the steps in the flowchart of fig. 2 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.

In order to better implement the method for measuring the volume of the stored goods according to the embodiment of the present application, on the basis of the method for measuring the volume of the stored goods according to the embodiment of the present application, the embodiment of the present application further provides a device for measuring the volume of the stored goods, as shown in fig. 9, where the volume measuring device 900 includes:

the point cloud acquisition module 910 is configured to acquire three-dimensional point cloud data of the warehouse cargo to be tested;

The point cloud filtering module 920 is configured to perform deep filtering processing on the three-dimensional point cloud data based on a preset impurity influence sequence, so as to obtain filtered three-dimensional point cloud data;

the point cloud filling module 930 is configured to perform point cloud filling processing on the filtered three-dimensional point cloud data to obtain target three-dimensional point cloud data;

the volume analysis module 940 is configured to analyze the target three-dimensional point cloud data to obtain cargo volume information of the warehouse cargo to be tested.

In one embodiment, the point cloud filtering module 920 is further configured to obtain first target point cloud data corresponding to the three-dimensional point cloud data, to obtain a first point cloud set; responding to the fact that the first target point cloud data meets a preset coordinate threshold condition, clustering and screening the first target point cloud data to obtain second target point cloud data in each point cloud set; wherein the second target point cloud data includes Z-axis data; screening second target point cloud data with minimum Z-axis data as third target point cloud data aiming at each point cloud set, performing first filtering processing on the three-dimensional point cloud data, and counting to obtain a second point cloud set; and performing second filtering processing on the third target point cloud data to obtain filtered three-dimensional point cloud data.

In one embodiment, the point cloud filtering module 920 is further configured to establish a first K-D tree structure according to the third target point cloud data; based on the first K-D tree structure, performing nearest neighbor search on third target point cloud data to obtain a third point cloud set comprising K fourth target point cloud data; calculating the standard deviation of the third point cloud set according to the Z-axis data of the fourth target point cloud data; in response to the standard deviation being smaller than a preset standard deviation threshold, reserving fourth target point cloud data as fifth target point cloud data, performing second filtering processing on the third target point cloud data, and counting to obtain a fourth point cloud set; and performing third filtering processing on the fourth point cloud set to obtain three-dimensional point cloud data after filtering.

In one embodiment, the point cloud filtering module 920 is further configured to calculate a first Z-axis average value of the third point cloud set according to the Z-axis data of the fourth target point cloud data in response to the standard deviation being greater than or equal to a preset standard deviation threshold; and screening fourth target point cloud data with Z-axis data larger than the first Z-axis average value as fifth target point cloud data, performing second filtering processing on the third target point cloud data, and counting to obtain a fourth point cloud set.

In one embodiment, the point cloud filtering module 920 is further configured to screen out ground point cloud data in the fourth point cloud set to obtain a fifth point cloud set including the sixth target point cloud data; acquiring first average distance data among cloud data of each sixth target point, and updating a preset point distance threshold according to the first average distance data to obtain an updated point distance threshold; establishing a second K-D tree structure corresponding to the cloud data of the sixth target point, and acquiring second average distance data according to the second K-D tree structure; and in response to the second average distance data being less than the updated point distance threshold, preserving the sixth target point cloud data and the ground point cloud data as seventh target point cloud data to update the fifth point cloud set, and obtaining an updated fifth point cloud set.

In one embodiment, the point cloud filtering module 920 is further configured to obtain a quotient between the first average distance data and the preset average distance, to obtain a point distance threshold scaling factor; and obtaining a product value between the point distance threshold scaling factor and a preset point distance threshold to update the preset point distance threshold and obtain an updated point distance threshold.

In one embodiment, the point cloud filtering module 920 is further configured to perform nearest neighbor searching on the sixth target point cloud data according to the second K-D tree structure, to obtain a nearest neighbor point cloud set including K nearest neighbor point clouds; acquiring the point cloud distance between each sixth target point cloud data and each nearest neighbor point cloud to obtain a distance set; and obtaining the average distance corresponding to the point cloud distance, and obtaining second average distance data.

In one embodiment, the point cloud filtering module 920 is further configured to, in response to the second average distance data being greater than or equal to the updated distance threshold, filter the sixth target point cloud data to update the fifth point cloud set to obtain an updated fifth point cloud set; adding the ground point cloud data to the updated fifth point cloud set to perform third filtering processing on the fourth point cloud set; and taking the point cloud data in the updated fifth point cloud set as seventh target point cloud data, and carrying out statistics to obtain filtered three-dimensional point cloud data.

In one embodiment, the point cloud filling module 930 is further configured to obtain starting point cloud data based on a preset bar frame length scaling factor and a preset bar frame step size; screening out filtered three-dimensional point cloud data within a preset bar frame range according to the starting point cloud data and a preset in-frame center point cloud to obtain in-frame point cloud data; acquiring a second Z-axis average value according to Z-axis data of the point cloud data in the frame; and performing point cloud filling processing on the three-dimensional point cloud data after filtering according to the second Z-axis average value and the in-frame center point cloud to obtain target three-dimensional point cloud data.

In one embodiment, the point cloud filling module 930 is further configured to perform a point cloud boundary filling process on the filtered three-dimensional point cloud data according to the second Z-axis average value and the in-frame center point cloud, to obtain preliminarily filled three-dimensional point cloud data; and interpolating and filling the primarily filled three-dimensional point cloud data based on a piecewise linear interpolation method to obtain target three-dimensional point cloud data.

In one embodiment, the volume measurement device 900 further includes a coordinate correction module, configured to obtain initial three-dimensional point cloud data of the warehouse cargo to be measured, and perform three-dimensional coordinate transformation on the initial three-dimensional point cloud data to obtain an initial plane normal vector; performing ground fitting on the initial three-dimensional point cloud data to obtain a real plane normal vector; acquiring the information of an included angle between a normal vector of a real plane and a normal vector of an initial plane; and carrying out coordinate correction on the initial three-dimensional point cloud data according to the included angle information to obtain three-dimensional point cloud data.

In one embodiment, the volume analysis module 940 is further configured to accumulate Z-axis data of the target three-dimensional point cloud data to obtain cargo height information; obtaining the product value between the cargo height information and the step length square value to obtain cargo volume information; the square value of the step length is a square product value of the step length of the preset bar frame.

In the embodiment, the point cloud data of the stored goods to be detected can be accurately extracted and perfected, so that the volume measurement accuracy of the stored goods is effectively improved.

It should be noted that, the specific limitation of the volume measurement device for the stored goods may be referred to the limitation of the volume measurement method for the stored goods hereinabove, and will not be described herein. The modules in the volume measuring device for the warehouse goods can be realized in whole or in part by software, hardware and a combination thereof. The above modules may be embedded in hardware or independent of a processor in the electronic device, or may be stored in software in a memory in the electronic device, so that the processor may call and execute operations corresponding to the above modules.

In some embodiments of the present application, the volume measurement device 900 of the warehouse cargo may be implemented in the form of a computer program that is executable on a computer device as shown in fig. 10. The memory of the computer device may store various program modules of the volume measurement device 900 that compose the warehouse cargo, such as the point cloud acquisition module 910, the point cloud filtering module 920, the point cloud filling module 930, and the volume analysis module 940 shown in fig. 9; the computer program of each program module makes the processor execute the steps in the method for measuring the volume of the warehouse goods according to each embodiment of the present application described in the present specification. For example, the computer apparatus shown in fig. 10 may perform step S201 through the point cloud acquisition module 910 in the volume measurement device 900 of the stocked cargo as shown in fig. 9. The computer device may perform step S202 through the point cloud filtering module 920. The computer device may perform step S203 through the point cloud filling module 930. The computer device may perform step S204 through the volume resolution module 940. The computer device includes a processor, a memory, and a network interface coupled by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external computer device through a network connection. The computer program is executed by the processor to implement a method of volumetric measurement of warehouse cargo.

It will be appreciated by those skilled in the art that the structure shown in fig. 10 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In some embodiments of the present application, a computer device is provided that includes one or more processors; a memory; and one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to perform the steps of the method for measuring volume of warehoused cargo described above. The step of the method for measuring the volume of the stored goods may be the step of the method for measuring the volume of the stored goods in the above embodiments.

In some embodiments of the present application, a computer readable storage medium is provided, in which a computer program is stored, where the computer program is loaded by a processor, so that the processor performs the steps of the method for measuring the volume of the warehouse cargo. The step of the method for measuring the volume of the stored goods may be the step of the method for measuring the volume of the stored goods in the above embodiments.

Those of ordinary skill in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein can include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can take many forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), among others.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The foregoing has described in detail the method, apparatus, computer device and storage medium for measuring the volume of stored goods according to the embodiments of the present application, and specific examples have been applied to illustrate the principles and embodiments of the present invention, where the foregoing examples are only for aiding in understanding the method and core idea of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in light of the ideas of the present invention, the present description should not be construed as limiting the present invention.

Claims

1. A method of volumetric measurement of stored goods, comprising:

based on a preset impurity influence sequence, carrying out deep filtering treatment on the three-dimensional point cloud data to obtain filtered three-dimensional point cloud data;

performing point cloud filling processing on the filtered three-dimensional point cloud data to obtain target three-dimensional point cloud data;

2. The method of claim 1, wherein the order of the depth filter process comprises: a first filtering process, a second filtering process, and a third filtering process; wherein,,

The first filtering process is used for screening out third target point cloud data in the three-dimensional point cloud data so as to obtain a second point cloud set;

the second filtering process is used for screening out fifth target point cloud data in the second point cloud set to obtain a fourth point cloud set;

and the third filtering process is used for screening out seventh target point cloud data in the fourth point cloud set so as to obtain the three-dimensional point cloud data after filtering.

3. The method of claim 2, wherein the deep filtering the three-dimensional point cloud data based on the preset impurity influence sequence to obtain filtered three-dimensional point cloud data comprises:

acquiring first target point cloud data corresponding to the three-dimensional point cloud data to obtain a first point cloud set;

responding to the fact that the first target point cloud data meets a preset coordinate threshold condition, and carrying out clustering screening on the first target point cloud data to obtain second target point cloud data in each point cloud set; wherein the second target point cloud data includes Z-axis data;

screening second target point cloud data with the minimum Z-axis data as third target point cloud data aiming at each point cloud set, performing first filtering processing on the three-dimensional point cloud data, and counting to obtain a second point cloud set;

And performing second filtering processing on the third target point cloud data to obtain the three-dimensional point cloud data after filtering.

4. The method of claim 3, wherein performing a second filtering process on the third target point cloud data to obtain the filtered three-dimensional point cloud data comprises:

establishing a first K-D tree structure according to the third target point cloud data;

based on the first K-D tree structure, nearest neighbor searching is conducted on the third target point cloud data, and a third point cloud set comprising K fourth target point cloud data is obtained;

calculating the standard deviation of the third point cloud set according to the Z-axis data of the fourth target point cloud data;

in response to the standard deviation being smaller than a preset standard deviation threshold, reserving fourth target point cloud data as fifth target point cloud data, performing second filtering processing on the third target point cloud data, and counting to obtain a fourth point cloud set;

and performing third filtering processing on the fourth point cloud set to obtain the three-dimensional point cloud data after filtering.

5. The method of claim 4, wherein the method further comprises:

responding to the standard deviation being greater than or equal to a preset standard deviation threshold, and calculating a first Z-axis average value of the third point cloud set according to the Z-axis data of the fourth target point cloud data;

And screening out fourth target point cloud data of which the Z-axis data is larger than the first Z-axis average value, and taking the fourth target point cloud data as fifth target point cloud data, so as to perform second filtering processing on the third target point cloud data, and obtaining a fourth point cloud set through statistics.

6. The method of claim 5, wherein performing a third filtering process on the fourth point cloud set to obtain the filtered three-dimensional point cloud data comprises:

screening out the ground point cloud data in the fourth point cloud set to obtain a fifth point cloud set comprising sixth point cloud data;

acquiring first average distance data between cloud data of each sixth target point, and updating a preset point distance threshold according to the first average distance data to obtain an updated point distance threshold;

establishing a second K-D tree structure corresponding to the cloud data of the sixth target point, and acquiring second average distance data according to the second K-D tree structure;

and in response to the second average distance data being less than the updated point distance threshold, reserving the sixth target point cloud data and the ground point cloud data as seventh target point cloud data to update the fifth point cloud set to obtain an updated fifth point cloud set.

7. The method of claim 6, wherein updating the preset point distance threshold based on the first average distance data to obtain the updated point distance threshold comprises:

obtaining a quotient between the first average distance data and a preset average distance to obtain a point distance threshold scaling factor;

and obtaining a product value between the point distance threshold scaling factor and a preset point distance threshold to update the preset point distance threshold and obtain the updated point distance threshold.

8. The method of claim 6, wherein the obtaining second average distance data from the second K-D tree structure comprises:

performing nearest neighbor search on the sixth target point cloud data according to the second K-D tree structure to obtain a nearest neighbor point cloud set comprising K nearest neighbor point clouds;

acquiring the point cloud distance between the cloud data of each sixth target point and each nearest neighbor point cloud to obtain a distance set;

and obtaining the average distance corresponding to the point cloud distance, and obtaining the second average distance data.

9. The method of claim 6, wherein the method further comprises:

filtering the sixth target point cloud data in response to the second average distance data being greater than or equal to the updated distance threshold value to update the fifth point cloud set to obtain an updated fifth point cloud set;

Adding the ground point cloud data to the updated fifth point cloud set to perform third filtering processing on the fourth point cloud set;

and taking the point cloud data in the updated fifth point cloud set as seventh target point cloud data, and obtaining the filtered three-dimensional point cloud data through statistics.

10. The method of any one of claims 1-9, wherein performing a point cloud filling process on the filtered three-dimensional point cloud data to obtain target three-dimensional point cloud data includes:

acquiring starting point cloud data based on a preset bar frame length scaling factor and a preset bar frame step length;

screening out the filtered three-dimensional point cloud data within a preset bar frame range according to the starting point cloud data and a preset in-frame center point cloud to obtain in-frame point cloud data;

acquiring a second Z-axis average value according to the Z-axis data of the in-frame point cloud data;

and performing point cloud filling processing on the filtered three-dimensional point cloud data according to the second Z-axis average value and the in-frame center point cloud to obtain the target three-dimensional point cloud data.

11. The method of claim 10, wherein performing a point cloud filling process on the filtered three-dimensional point cloud data according to the second Z-axis average value and the in-frame center point cloud to obtain the target three-dimensional point cloud data, comprising:

Performing point cloud boundary filling processing on the filtered three-dimensional point cloud data according to the second Z-axis average value and the in-frame center point cloud to obtain preliminarily filled three-dimensional point cloud data;

and interpolating and filling the preliminarily filled three-dimensional point cloud data based on a piecewise linear interpolation method to obtain the target three-dimensional point cloud data.

12. The method of claim 1, further comprising, prior to said acquiring three-dimensional point cloud data of the warehouse cargo to be tested:

acquiring initial three-dimensional point cloud data of the warehouse goods to be tested, and performing three-dimensional coordinate conversion on the initial three-dimensional point cloud data to obtain an initial plane normal vector; and

performing ground fitting on the initial three-dimensional point cloud data to obtain a real plane normal vector;

acquiring the included angle information between the real plane normal vector and the initial plane normal vector;

and carrying out coordinate correction on the initial three-dimensional point cloud data according to the included angle information to obtain the three-dimensional point cloud data.

13. The method of claim 1, wherein the analyzing the target three-dimensional point cloud data to obtain the cargo volume information of the warehouse cargo to be tested comprises:

Accumulating Z-axis data of the target three-dimensional point cloud data to obtain cargo height information;

obtaining the product value between the cargo height information and the step length square value to obtain the cargo volume information;

the step length square value is a square product value of a preset bar frame step length.

14. A volume measurement device for a warehouse cargo, comprising:

and the volume analysis module is used for analyzing the target three-dimensional point cloud data to obtain the cargo volume information of the to-be-detected warehouse cargo.

15. A computer device, the computer device comprising:

one or more processors;

a memory; and one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the method of volumetric measurement of warehoused cargo of any of claims 1-13.

16. A computer readable storage medium, characterized in that it has stored thereon a computer program, which is loaded by a processor to perform the steps of the method for measuring the volume of a warehouse cargo as claimed in any one of claims 1 to 13.