Bar direction identification method, device, equipment and storage medium

Abstract

The application provides a bar direction recognition method, device, equipment and storage medium, the method comprises the following steps: obtaining three-dimensional point cloud data of a target bar stack, the target bar stack is formed by bar bundles stacked in a cross shape; determining the top layer height value of the target bar stack according to the three-dimensional point cloud data, so as to cut the three-dimensional point cloud data once by the top layer height value, and obtain the contour point cloud data of the top layer bar bundle; cutting the contour point cloud data twice to determine a plurality of sub-point clouds, and the sub-point cloud is the point cloud data of each bar bundle in the top layer bar bundle; comparing the horizontal size and the vertical size of the target sub-point cloud, and determining the direction of the top layer bar bundle based on the comparison result, the target sub-point cloud is the largest sub-point cloud in each sub-point cloud. The application not only improves the accuracy of bar direction recognition, but also ensures the reliability and safety of bar hoisting.

Description

Technical Field

[0001] This invention relates to the field of orientation recognition technology, and specifically to a method, apparatus, device, and storage medium for identifying the orientation of bar stock. Background Technology

[0002] The steel industry plays a vital role in national economic development, with its industrial materials widely used in construction, machinery manufacturing, shipbuilding, and other sectors. With continuous technological innovation in the steel industry, bar stock, a major product of steel enterprises, has evolved from traditional manual lifting to unmanned aerial vehicle (UAV) lifting operations, improving production efficiency. However, during lifting, it's difficult to strictly adhere to standard placement; even when stacked in a grid pattern, the horizontal or vertical orientation of the bars is often non-standard. For example, when using electromagnetic lifting devices for unmanned bar lifting, the electromagnetic field can cause deviations in the stacking direction, and bars are prone to rolling and shifting during stacking. If the bar orientation is non-standard, the center of gravity will be at the edge of the lifting device, leading to lifting failure or the bar falling from the air during lifting, resulting in safety accidents. Therefore, identifying the bar orientation is crucial during unmanned lifting operations. In related technologies, the orientation recognition of bar stock is mainly achieved by obtaining image information of the top layer of the bar stock stack through image acquisition equipment, and then identifying the placement orientation of the top layer of bar stock bundles based on the image information, so that the unmanned crane can lift and transport according to the placement orientation obtained by image recognition, thereby improving the safety of unmanned lifting.

[0003] However, when using image recognition to determine the orientation of bar stock, the image information is planar, and its acquisition is limited by the environment at the hoisting site. Factors such as the shooting position and distance of the image acquisition equipment, as well as the lighting conditions during shooting, all affect the orientation recognition of the bar stock, resulting in low accuracy. Therefore, how to improve the accuracy of bar stock orientation recognition to ensure the reliability and safety of unmanned bar stock hoisting is an urgent problem to be solved. Summary of the Invention

[0004] In view of the shortcomings of the prior art described above, the present invention provides a method, apparatus, device and storage medium for identifying the orientation of bar stock, so as to solve at least one of the above-mentioned technical problems.

[0005] In a first aspect, the present invention provides a method for identifying the orientation of bar stock, comprising: acquiring three-dimensional point cloud data of a target bar stock stack, the target bar stock stack being formed by bar stock bundles stacked in a grid pattern; determining the top layer height value of the target bar stock stack based on the three-dimensional point cloud data, and performing a first-stage segmentation of the three-dimensional point cloud data using the top layer height value to obtain contour point cloud data of the top layer bar stock bundle; performing a second-stage segmentation of the contour point cloud data to determine multiple sub-point clouds, the sub-point clouds being the point cloud data of each bar stock bundle in the top layer bar stock bundle; comparing the horizontal and vertical dimensions of the target sub-point clouds, and determining the orientation of the top layer bar stock bundle based on the comparison result, the target sub-point cloud being the sub-point cloud with the largest size among the sub-point clouds.

[0006] In one embodiment of the present invention, comparing the lateral and vertical dimensions of the target sub-point cloud and determining the orientation of the top layer bar bundle based on the comparison result includes: if the lateral dimension of the target sub-point cloud is greater than the vertical dimension, then the orientation of the top layer bar bundle in the target bar stack is lateral; if the lateral dimension of the target sub-point cloud is less than the vertical dimension, then the orientation of the top layer bar bundle in the target bar stack is vertical.

[0007] In one embodiment of the present invention, before comparing the lateral and vertical dimensions of the target sub-point cloud and determining the orientation of the top layer bar bundle based on the comparison result, the method includes: comparing the lateral and vertical dimensions of each sub-point cloud; if the lateral dimension of the sub-point cloud is greater than the vertical dimension of the sub-point cloud, then the lateral dimension of the sub-point cloud is used as the size of the sub-point cloud; if the lateral dimension of the sub-point cloud is less than the vertical dimension of the sub-point cloud, then the vertical dimension of the sub-point cloud is used as the size of the sub-point cloud.

[0008] In one embodiment of the present invention, before comparing the lateral and vertical dimensions of each of the sub-point clouds, the method further includes: determining the three-dimensional coordinates of each point in the sub-point cloud; comparing the values ​​of the three-dimensional coordinates of each point in the sub-point cloud on the X-axis to determine the maximum and minimum values ​​of the sub-point cloud on the X-axis; calculating the lateral dimension of the sub-point cloud based on the maximum and minimum values ​​of the sub-point cloud on the X-axis; comparing the values ​​of the three-dimensional coordinates of each point in the sub-point cloud on the Y-axis to determine the maximum and minimum values ​​of the sub-point cloud on the Y-axis; and calculating the vertical dimension of the sub-point cloud based on the maximum and minimum values ​​of the sub-point cloud on the Y-axis.

[0009] In one embodiment of the present invention, determining the top layer height of the target bar stack based on the three-dimensional point cloud data includes: performing noise reduction processing on the three-dimensional point cloud data and determining the three-dimensional coordinates of each point in the three-dimensional point cloud data; comparing the values ​​of the three-dimensional coordinates of each point in the three-dimensional point cloud data on the Z-axis and determining the maximum value of the three-dimensional point cloud data on the Z-axis; and using the maximum value of the three-dimensional point cloud data on the Z-axis as the top layer height of the target bar stack.

[0010] In one embodiment of the present invention, the step of cutting the three-dimensional point cloud data by the top layer height value to obtain the outline point cloud data of the top layer bar bundle includes: cutting the three-dimensional point cloud data downward from the position located at the top layer height value of the target bar stack until the cutting height reaches a preset height threshold; and using the three-dimensional point cloud data of the portion of the cut preset height threshold as the outline point cloud data of the top layer bar bundle.

[0011] In one embodiment of the present invention, obtaining the three-dimensional point cloud data of the target bar stack includes: determining a region to be identified, wherein the target bar stack is placed in the region to be identified; and using a scanning device to scan the external shape of the target bar stack in the region to be identified to obtain the three-dimensional point cloud data of the target bar stack.

[0012] In a second aspect, the present invention also provides a bar orientation identification device, comprising: an acquisition module for acquiring three-dimensional point cloud data of a target bar stack, the target bar stack being formed by bar bundles stacked in a grid pattern; a primary cutting module for determining the top layer height value of the target bar stack based on the three-dimensional point cloud data, and performing a primary cutting on the three-dimensional point cloud data using the top layer height value to obtain the contour point cloud data of the top layer bar bundle; a secondary cutting module for performing a secondary cutting on the contour point cloud data to determine multiple sub-point clouds, the sub-point clouds being the point cloud data of each bar bundle in the top layer bar bundle; and an orientation identification module for comparing the lateral and vertical dimensions of the target sub-point clouds, and determining the orientation of the top layer bar bundle based on the comparison result, the target sub-point cloud being the largest sub-point cloud among the sub-point clouds.

[0013] In a third aspect, the present invention also provides an electronic device, comprising: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the bar orientation recognition method as described in the above embodiments.

[0014] In a fourth aspect, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a computer processor, causes the computer to perform the bar orientation identification method as described in the above embodiments.

[0015] The beneficial effects of this invention are as follows: This invention proposes a method, apparatus, device, and storage medium for identifying the orientation of bar stock. The method acquires three-dimensional point cloud data of a target bar stock stack, which is formed by bundling bars in a grid pattern. Based on the three-dimensional point cloud data, the top layer height of the target bar stock stack is determined. The top layer height value is then used to cut the three-dimensional point cloud data once to obtain the outline point cloud data of the top layer bar stock bundle. The outline point cloud data is then cut a second time to determine multiple sub-point clouds, which are the point cloud data of each bar stock bundle within the top layer. The lateral and vertical dimensions of the target sub-point clouds are compared, and the orientation of the top layer bar stock bundle is determined based on the comparison result. The target sub-point cloud is the largest sub-point cloud among all sub-point clouds. On the one hand, by comparing the lateral and vertical dimensions of the largest sub-point cloud, the orientation of the bar stock can be automatically identified, improving the efficiency of unmanned bar stock handling. On the other hand, the accuracy of bar stock orientation identification is improved, ensuring the reliability and safety of unmanned bar stock handling.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0018] Figure 1 This is a flowchart illustrating a bar orientation identification method according to an exemplary embodiment of the present invention;

[0019] Figure 2 This is a schematic diagram of three-dimensional point cloud data of a target bar stack, as shown in an exemplary embodiment of the present invention;

[0020] Figure 3 This is a schematic diagram of the contour point cloud data of the top layer bar bundle shown in an exemplary embodiment of the present invention;

[0021] Figure 4 This is a schematic diagram of point cloud data of each bar bundle in the top bar bundle, as shown in an exemplary embodiment of the present invention.

[0022] Figure 5This is a schematic diagram of a target sub-point cloud illustrating an exemplary embodiment of the present invention;

[0023] Figure 6 This is a block diagram illustrating a rod orientation identification device according to an exemplary embodiment of the present invention;

[0024] Figure 7 This is a schematic diagram illustrating the structure of a computer system suitable for implementing the electronic device of the present invention, as shown in an exemplary embodiment of the present invention. Detailed Implementation

[0025] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0026] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0027] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0028] Please see Figure 1 The above is a flowchart illustrating a bar orientation identification method as an exemplary embodiment of the present invention. Figure 1 As shown, in an exemplary embodiment, the bar orientation identification method includes at least steps S110 to S140, which are described in detail below:

[0029] Step S110: Obtain the three-dimensional point cloud data of the target bar stack, which is formed by the bar bundles stacked in a grid pattern.

[0030] Specifically, acquiring 3D point cloud data includes: determining the area to be identified, where a stack of target bars is placed; and using a scanning device to scan the external shape of the stack of target bars in the area to be identified to obtain 3D point cloud data of the stack of target bars.

[0031] In one embodiment of the present invention, the bar bundles in the area to be identified are stacked layer by layer to form a target bar stack. That is, the direction of the bars in the target bar stack is horizontal or vertical, and the two directions are perpendicular to each other, forming a grid pattern. After measuring the data of the points on the external shape of the target bar stack surface, the scanning device can output three-dimensional point cloud data of the target bar stack. The target bar stack can also be formed directly from the bar stack without the bars being bundled, in order to identify the direction of the top bar of the target bar stack. The point cloud data is a set of vectors in a three-dimensional coordinate system. Each point contains three-dimensional coordinates, and some points may also include color information or reflection intensity information, etc. The smaller the angular interval between two adjacent points, the denser they appear, and the stronger the resolution of the target object, that is, the target bar stack.

[0032] In one embodiment of the present invention, the scanning device can be installed on the autonomous vehicle or independently of the autonomous vehicle, and its type includes a two-dimensional laser scanner, a three-dimensional laser scanner, a lidar, etc. During scanning, the scanning device can move alongside the autonomous vehicle to perform single-line or multi-line scanning. This embodiment does not limit the specific number, type, or method of the scanning device.

[0033] The above method enables the rapid and stable acquisition of three-dimensional point cloud data of the target bar stack, automating data acquisition and facilitating subsequent bar orientation identification.

[0034] Step S120: Determine the top layer height value of the target bar stack based on the three-dimensional point cloud data, and then cut the three-dimensional point cloud data once using the top layer height value to obtain the outline point cloud data of the top layer bar bundle.

[0035] Specifically, the top floor height value is determined in the following way:

[0036] The 3D point cloud data is denoised, and the 3D coordinates of each point in the 3D point cloud data are determined. The 3D coordinates of each point in the 3D point cloud data are compared with the Z-axis values, and the maximum value of the 3D point cloud data in the Z-axis is determined. The maximum value of the 3D point cloud data in the Z-axis is used as the top layer height value of the target bar stack.

[0037] In one embodiment of the present invention, during the acquisition of 3D point cloud data, due to the influence of factors such as the surface of the object under test (target bar stack) and the scanning environment, some noise inevitably gets mixed in with the 3D point cloud data. This noise is useless for bar orientation identification, and its presence will affect subsequent processing. For example, the Z-axis value of the noise is the maximum value of the 3D point cloud data on the Z-axis, which will lead to incorrect judgment of the top layer height of the target bar stack, resulting in an error in the first cut and thus causing deviation in bar orientation identification. Therefore, in order to ensure the accuracy of bar orientation identification, it is necessary to denoise the 3D point cloud data to remove noise and avoid it interfering with subsequent cutting processing. The denoising methods can include statistical filtering, radius filtering, bilateral filtering, and Gaussian filtering, etc., and this embodiment does not limit this.

[0038] Please see Figure 2 This is a schematic diagram of three-dimensional point cloud data of a target bar stack, illustrating an exemplary embodiment of the present invention. Figure 2 The point cloud data shown is the 3D point cloud data of the target bar stack after noise removal. Figure 2 Each point in the data contains a three-dimensional coordinate. The value of the Z-axis in the three-dimensional coordinate represents the height value of the corresponding point. In other words, by comparing the Z-axis values ​​of each point in the three-dimensional point cloud data, the point with the largest Z-axis value in the three-dimensional point cloud data can be determined, and the height value of that point can be used as the top layer height value of the target bar stack.

[0039] Specifically, a single cut includes: cutting the three-dimensional point cloud data downwards from the position of the top layer height value of the target bar stack until the cut height reaches a preset height threshold; and using the three-dimensional point cloud data of the cut preset height threshold portion as the contour point cloud data of the top bar bundle.

[0040] In one embodiment of the present invention, since the orientation of the top layer of the target bar stack needs to be identified, to avoid interference from the point cloud data of other layers of bar bundles besides the top layer, the three-dimensional point cloud data of the target bar stack needs to be cut once. That is, the three-dimensional point cloud data is cut downwards from the height value of the top layer of the target bar stack, and the portion with a height of a preset height threshold is used as the contour point cloud data of the top layer of the target bar stack. To ensure the accuracy of the cutting, the preset height threshold can be adjusted according to the actual type of bar being hoisted; this embodiment does not limit it.

[0041] Please see Figure 3 This is a schematic diagram of the contour point cloud data of the top layer bar bundle, which is an exemplary embodiment of the present invention. Figure 3 for Figure 2 The 3D point cloud data shown is the contour point cloud data after one cutting process, which is... Figure 3As can be seen, the cutting height does not need to include the entire top layer of the target bar stack; it is sufficient that the cutting height does not affect the orientation recognition.

[0042] By using the above method, the height value of the top layer can be accurately obtained, ensuring the accuracy of the first cut and thus preventing deviations in the bar orientation identification results.

[0043] Step S130: Perform secondary cutting on the contour point cloud data to determine multiple sub-point clouds. The sub-point clouds are the point cloud data of each bar bundle in the top bar bundle.

[0044] Specifically, since the arrangement of each bar bundle may be very close together or independent of each other, in order to facilitate segmentation and improve the efficiency of orientation recognition, the point cloud data of the closely arranged bar bundles is used as a sub-point cloud. That is, each sub-point cloud can be the point cloud data of one or more bundles of bars in the top layer bar bundle.

[0045] In one embodiment of the present invention, the sub-point cloud can be obtained by secondary segmentation using methods such as Euclidean distance segmentation and DBSACN (i.e., density-based clustering algorithm). For example, if Euclidean distance segmentation is performed on the contour sub-point cloud, it is necessary to determine a certain point in the contour sub-point cloud, determine the distance between the other points close to that point and that point, and group the points whose distance is less than a preset distance threshold into the same sub-point cloud, thereby quickly achieving secondary segmentation of the contour point cloud data. If the DBSACN algorithm is used for secondary segmentation of the contour sub-point cloud, the points within the preset distance threshold are clustered into the same sub-point cloud. The preset distance threshold can be adjusted according to the actual situation, and the value of the preset threshold is not limited here. This embodiment can quickly segment the contour point cloud data into multiple sub-point clouds, improving the efficiency of bar orientation recognition.

[0046] Please see Figure 4 This is a schematic diagram illustrating point cloud data of each bar bundle in the top layer of a top bar bundle, as shown in an exemplary embodiment of the present invention. Figure 4 As shown, for Figure 3 After secondary cutting of the outline point cloud data of the top layer bar bundle, two sub-point clouds were obtained. It can be seen that the distance between adjacent points in the two sub-point clouds is relatively far.

[0047] Step S140: Compare the horizontal and vertical dimensions of the target sub-point cloud, and determine the direction of the top layer bar bundle based on the comparison results. The target sub-point cloud is the sub-point cloud with the largest size among all sub-point clouds.

[0048] Determining the orientation of the top bar bundle includes: if the horizontal dimension of the target sub-point cloud is greater than the vertical dimension, the orientation of the top bar bundle in the target bar stack is horizontal; if the horizontal dimension of the target sub-point cloud is less than the vertical dimension, the orientation of the top bar bundle in the target bar stack is vertical.

[0049] Specifically, during the stacking of bar bundles, the bars may not necessarily be arranged in a pre-defined grid pattern. The pre-defined standard is set to a 90-degree angle between the horizontal and vertical directions of each layer of bars, which can be adjusted according to actual conditions, for example, to between 88 and 92 degrees. Furthermore, the bars may shift after placement. Determining the bar orientation based on the horizontal and vertical dimensions of the target sub-point cloud ignores any angular deviations from the pre-defined standard during the initial stacking. In other words, even if the placement does not conform to the pre-defined standard, the bar orientation can be accurately identified by directly comparing the horizontal and vertical dimensions of the target sub-point cloud. For example, if the angular deviation of the bar orientation is 10 degrees, and the horizontal dimension of the target sub-point cloud is smaller than its vertical dimension, then the orientation of the top layer of bars in the target bar stack is vertical, meaning the top layer of bars has an angular deviation of 10 degrees from the pre-defined standard. In this embodiment, the adaptability and accuracy of bar orientation identification for non-standard bar placement are improved, ensuring the reliability and safety of unmanned bar handling.

[0050] Please see Figure 5 This is a schematic diagram of a target sub-point cloud, illustrating an exemplary embodiment of the present invention. From Figure 4 It can be seen that the size difference between the two sub-point clouds, i.e., the size of the sub-point cloud inside the box is larger than the size of the sub-point cloud outside the box, and the target sub-point cloud is the largest among the multiple sub-point clouds obtained after the secondary segmentation. Therefore... Figure 4 The target sub-point cloud in the middle is Figure 5 The sub-point cloud shown.

[0051] Before step S240, determining the size of each sub-point cloud includes: comparing the horizontal and vertical dimensions of each sub-point cloud; if the horizontal dimension of the sub-point cloud is greater than the vertical dimension of the sub-point cloud, then the horizontal dimension of the sub-point cloud is used as the size of the sub-point cloud; if the horizontal dimension of the sub-point cloud is less than the vertical dimension of the sub-point cloud, then the vertical dimension of the sub-point cloud is used as the size of the sub-point cloud.

[0052] That is, the horizontal and vertical dimensions of each sub-point cloud are compared, and the larger of the horizontal and vertical dimensions of each sub-point cloud is taken as the size of the sub-point cloud.

[0053] Specifically, calculating the horizontal and vertical dimensions of each sub-point cloud includes: determining the three-dimensional coordinates of each point in the sub-point cloud; comparing the values ​​of the three-dimensional coordinates of each point in the sub-point cloud on the X-axis to determine the maximum and minimum values ​​of the sub-point cloud on the X-axis; calculating the horizontal dimension of the sub-point cloud based on the maximum and minimum values ​​of the sub-point cloud on the X-axis; comparing the values ​​of the three-dimensional coordinates of each point in the sub-point cloud on the Y-axis to determine the maximum and minimum values ​​of the sub-point cloud on the Y-axis; and calculating the vertical dimension of the sub-point cloud based on the maximum and minimum values ​​of the sub-point cloud on the Y-axis.

[0054] In one embodiment of the present invention, the lateral distance between two points can be calculated using the X-axis values ​​of one point and another point in the sub-point cloud, and the longitudinal distance between them can be calculated using the Y-axis values ​​of one point and another point in the sub-point cloud. Therefore, the maximum lateral distance between two points in the sub-point cloud can be calculated using the point with the largest X-axis value and the point with the smallest X-axis value, and this maximum lateral distance is used as the lateral dimension of the sub-point cloud; similarly, the maximum vertical distance between two points in the sub-point cloud can be calculated using the point with the largest Y-axis value and the point with the smallest Y-axis value, and this maximum vertical distance is used as the vertical dimension of the sub-point cloud.

[0055] The above method enables rapid and accurate identification of the orientation of the top layer of bar bundles, improving the reliability and safety of unmanned bar lifting.

[0056] In one embodiment of the present invention, to ensure that the target bar stack conforms to a preset standard to the greatest extent possible, thereby improving the efficiency of subsequent unmanned bar handling, the orientation of each layer of bar bundles can be identified during the stacking process to determine whether the placement orientation of each layer of bars conforms to the preset standard. Specifically, when each layer of bar bundles is stacked, the resulting bar stack is designated as the bar stack to be identified; the orientation of the top layer of bar bundles in the bar stack to be identified is identified; it is then checked whether the orientation of the top layer of bar bundles conforms to the preset standard; if it does, the stacking of the next layer of bar bundles continues until the target bar stack is formed; if it does not conform, the orientation of the top layer of bar bundles in the bar stack to be identified is adjusted.

[0057] In one embodiment of the present invention, various processing of point cloud data, such as noise reduction and segmentation, can be implemented by PCL (Point Cloud Library) and Open3D (i.e., 3D data processing library).

[0058] Please see Figure 6The diagram illustrates a block diagram of a bar orientation identification device according to an exemplary embodiment of the present invention. This exemplary bar orientation identification device includes: an acquisition module 601, a primary cutting module 602, a secondary cutting module 603, and an orientation identification module 604.

[0059] The acquisition module 601 is used to acquire the three-dimensional point cloud data of the target bar stack, which is formed by the bar bundles stacked in a grid pattern.

[0060] The first-cut module 602 is used to determine the top layer height value of the target bar stack based on the three-dimensional point cloud data, so as to cut the three-dimensional point cloud data once based on the top layer height value to obtain the outline point cloud data of the top layer bar bundle;

[0061] The secondary cutting module 603 is used to perform secondary cutting on the contour point cloud data to determine multiple sub-point clouds, which are the point cloud data of each bar bundle in the top bar bundle.

[0062] The orientation recognition module 604 is used to compare the horizontal and vertical dimensions of the target sub-point cloud and determine the orientation of the top layer bar bundle based on the comparison result. The target sub-point cloud is the sub-point cloud with the largest size among all sub-point clouds.

[0063] In another exemplary embodiment, the acquisition module includes: a scanning unit, configured to determine a region to be identified, wherein a stack of target bars is placed in the region to be identified; and to scan the external shape of the stack of target bars in the region to be identified using a scanning device to obtain three-dimensional point cloud data of the stack of target bars.

[0064] In another exemplary embodiment, the primary cutting module includes: a top-level height determination unit, used to perform noise reduction processing on the three-dimensional point cloud data and determine the three-dimensional coordinates of each point in the three-dimensional point cloud data; compare the values ​​of the three-dimensional coordinates of each point in the three-dimensional point cloud data on the Z-axis to determine the maximum value of the three-dimensional point cloud data on the Z-axis; and use the maximum value of the three-dimensional point cloud data on the Z-axis as the top-level height value of the target bar stack.

[0065] In another exemplary embodiment, the primary cutting module further includes: a contour point cloud data unit, used to cut the three-dimensional point cloud data downward from the position of the height value of the top layer of the target bar stack until the cutting height reaches a preset height threshold; and to use the three-dimensional point cloud data of the cut preset height threshold portion as the contour point cloud data of the top layer bar bundle.

[0066] In another exemplary embodiment, the direction recognition module includes: a direction determination unit, configured to determine the direction of the top layer of bar bundles in the target bar stack as horizontal if the horizontal dimension of the target sub-point cloud is greater than the vertical dimension; and to determine the direction of the top layer of bar bundles in the target bar stack as vertical if the horizontal dimension of the target sub-point cloud is less than the vertical dimension.

[0067] In another exemplary embodiment, the orientation recognition module further includes: a size determination unit, used to compare the horizontal and vertical dimensions of each sub-point cloud; if the horizontal dimension of the sub-point cloud is greater than the vertical dimension of the sub-point cloud, then the horizontal dimension of the sub-point cloud is used as the size of the sub-point cloud; if the horizontal dimension of the sub-point cloud is less than the vertical dimension of the sub-point cloud, then the vertical dimension of the sub-point cloud is used as the size of the sub-point cloud.

[0068] In another exemplary embodiment, the size determination unit includes: a size calculation subunit, configured to: determine the three-dimensional coordinates of each point in the sub-point cloud; compare the values ​​of the three-dimensional coordinates of each point in the sub-point cloud on the X-axis to determine the maximum and minimum values ​​of the sub-point cloud on the X-axis; calculate the lateral size of the sub-point cloud based on the maximum and minimum values ​​of the sub-point cloud on the X-axis; compare the values ​​of the three-dimensional coordinates of each point in the sub-point cloud on the Y-axis to determine the maximum and minimum values ​​of the sub-point cloud on the Y-axis; and calculate the vertical size of the sub-point cloud based on the maximum and minimum values ​​of the sub-point cloud on the Y-axis.

[0069] It should be noted that the bar orientation identification device and the bar orientation identification method provided in the above embodiments belong to the same concept. The specific operation methods of each module and unit have been described in detail in the method embodiments and will not be repeated here. In practical applications, the bar orientation identification device provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here.

[0070] Embodiments of the present invention also provide an electronic device, including: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device implements the vehicle fuel level display correction method provided in the above embodiments.

[0071] Please see Figure 7 This is a schematic diagram illustrating the structure of a computer system suitable for implementing the electronic device of the present invention, as shown in an exemplary embodiment of the present invention. It should be noted that... Figure 7 The computer system 700 of the illustrated electronic device is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0072] like Figure 7As shown, the computer system 700 includes a Central Processing Unit (CPU) 701, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, based on programs stored in Read-Only Memory (ROM) 702 or programs loaded from storage portion 708 into Random Access Memory (RAM) 703. The RAM 703 also stores various programs and data required for system operation. The CPU 701, ROM 702, and RAM 703 are interconnected via a bus 704. An Input / Output (I / O) interface 705 is also connected to the bus 704.

[0073] The following components are connected to I / O interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to I / O interface 705 as needed. Removable media 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 710 as needed so that computer programs read from them can be installed into storage section 708 as needed.

[0074] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 709, and / or installed from removable medium 711. When the computer program is executed by central processing unit (CPU) 701, it performs various functions defined in the system of the present invention.

[0075] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program thereon, which, when executed by a computer processor, causes the computer to perform the bar orientation identification method as described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not assembled into the electronic device.

[0076] It should be noted that the computer-readable medium shown in the embodiments of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0077] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0078] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method for identifying the orientation of a bar, characterized in that, include: Acquire three-dimensional point cloud data of the target bar stack, wherein the target bar stack is formed by bar bundles stacked in a grid pattern; The top layer height value of the target bar stack is determined based on the three-dimensional point cloud data, and the three-dimensional point cloud data is cut once using the top layer height value to obtain the outline point cloud data of the top layer bar bundle. The contour point cloud data is further segmented to determine multiple sub-point clouds, which are the point cloud data of each of the bar bundles in the top layer bar bundle; The horizontal and vertical dimensions of the target sub-point cloud are compared, and the orientation of the top layer bar bundle is determined based on the comparison result. The target sub-point cloud is the sub-point cloud with the largest size among all the sub-point clouds. in, The step of cutting the three-dimensional point cloud data using the top layer height value to obtain the contour point cloud data of the top layer bar bundle includes: The three-dimensional point cloud data is cut downwards from the position of the height value of the top layer of the target bar stack until the cutting height reaches the preset height threshold. The three-dimensional point cloud data of the portion cut at a preset height threshold is used as the contour point cloud data of the top bar bundle.

2. The bar orientation identification method as described in claim 1, characterized in that, The step of comparing the horizontal and vertical dimensions of the target sub-point cloud and determining the orientation of the top layer of bar bundle based on the comparison result includes: If the horizontal dimension of the target sub-point cloud is greater than the vertical dimension, then the direction of the top layer of bar bundle in the target bar stack is horizontal; If the horizontal dimension of the target sub-point cloud is smaller than its vertical dimension, then the direction of the top layer of bar bundle in the target bar stack is vertical.

3. The bar orientation identification method as described in claim 1, characterized in that, Before comparing the lateral and vertical dimensions of the target sub-point cloud and determining the orientation of the top layer of bar bundle based on the comparison result, the method further includes: Compare the horizontal and vertical dimensions of each sub-point cloud; If the horizontal dimension of the sub-point cloud is greater than the vertical dimension of the sub-point cloud, then the horizontal dimension of the sub-point cloud is taken as the size of the sub-point cloud; If the horizontal dimension of the sub-point cloud is smaller than the vertical dimension of the sub-point cloud, then the vertical dimension of the sub-point cloud is taken as the size of the sub-point cloud.

4. The bar orientation identification method as described in claim 3, characterized in that, Before comparing the horizontal and vertical dimensions of each of the sub-point clouds, the method further includes: Determine the three-dimensional coordinates of each point in the sub-point cloud; Compare the values ​​of the three-dimensional coordinates of each point in the sub-point cloud on the X-axis to determine the maximum and minimum values ​​of the sub-point cloud on the X-axis; The lateral dimension of the sub-point cloud is calculated based on the maximum and minimum values ​​of the sub-point cloud on the X-axis. Compare the 3D coordinates of each point in the sub-point cloud on the Y-axis to determine the maximum and minimum values ​​of the sub-point cloud on the Y-axis; The vertical dimension of the sub-point cloud is calculated based on the maximum and minimum values ​​of the sub-point cloud on the Y-axis.

5. The bar orientation identification method as described in claim 1, characterized in that, Determining the top layer height value of the target bar stack based on the three-dimensional point cloud data includes: The 3D point cloud data is denoised, and the 3D coordinates of each point in the 3D point cloud data are determined. By comparing the values ​​of the three-dimensional coordinates of each point in the three-dimensional point cloud data on the Z-axis, the maximum value of the three-dimensional point cloud data on the Z-axis is determined; The maximum value of the three-dimensional point cloud data on the Z-axis is used as the top layer height value of the target bar stack.

6. The bar orientation identification method as described in any one of claims 1 to 5, characterized in that, The acquisition of the three-dimensional point cloud data of the target bar stack includes: Determine the area to be identified, where the target bar stack is placed; The external shape of the target bar stack in the area to be identified is scanned using a scanning device to obtain the three-dimensional point cloud data of the target bar stack.

7. A rod orientation identification device, characterized in that, include: The acquisition module is used to acquire three-dimensional point cloud data of the target bar stack, which is formed by stacking bar bundles in a grid pattern. A single-cutting module is used to determine the top layer height value of the target bar stack based on the three-dimensional point cloud data, so as to cut the three-dimensional point cloud data once using the top layer height value to obtain the outline point cloud data of the top layer bar bundle; The secondary cutting module is used to perform secondary cutting on the contour point cloud data to determine multiple sub-point clouds, wherein the sub-point clouds are the point cloud data of each of the bar bundles in the top layer bar bundle; The orientation recognition module is used to compare the horizontal and vertical dimensions of the target sub-point cloud and determine the orientation of the top layer bar bundle based on the comparison result. The target sub-point cloud is the sub-point cloud with the largest size among all the sub-point clouds. in, The step of cutting the three-dimensional point cloud data using the top layer height value to obtain the contour point cloud data of the top layer bar bundle includes: The three-dimensional point cloud data is cut downwards from the position of the height value of the top layer of the target bar stack until the cutting height reaches the preset height threshold. The three-dimensional point cloud data of the portion cut at a preset height threshold is used as the contour point cloud data of the top bar bundle.

8. An electronic device, characterized in that, The electronic device includes; One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to implement the bar orientation identification method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It stores a computer program that enables a computer to perform the bar orientation identification method as described in any one of claims 1 to 6.

Images