Aircraft part surface polishing method and medium based on color point cloud camera

Abstract

This invention discloses a method and medium for polishing the surface of aircraft parts based on a color point cloud camera. A color 3D point cloud camera is used to acquire current color 3D point cloud data and a current color 2D image corresponding to the surface of the target aircraft part to be polished. Point cloud preprocessing and segmentation methods are used to process the point cloud data to obtain current color-selected 3D point cloud data. Combined with the current color 2D image, image mask preprocessing and morphological processing methods are used to obtain the target color 2D mask image. This mask image is then processed using image segmentation and paint layer recognition methods to obtain the target paint point cloud region. A polishing path planning method is then used to generate the target polishing path, and the surface of the target aircraft part is polished until the polishing operation is complete. This method solves the problems of damage to the aircraft primer and wasted polishing time caused by multiple full-scale polishing processes, protects the aircraft primer, and reduces polishing time.

Description

Technical Field

[0001] This invention relates to the field of aircraft parts surface treatment technology, and in particular to a method and medium for polishing aircraft parts based on a color point cloud camera. Background Technology

[0002] The coating on the surface of aircraft sheet metal parts typically includes a primer and a topcoat. When using a robotic arm to control a grinding wheel for sanding, multiple layers of sanding are usually applied to avoid over-sanding and damaging the substrate or primer.

[0003] In the process of developing this invention, the inventors discovered the following defects in the prior art: Currently, in the prior art, the first polishing is usually a full-scale polishing of the part surface, but in the subsequent second and third rounds of polishing, full-scale polishing is still performed. As the preceding polishing proceeds, the surface paint layer in some local areas becomes thin enough, and the amount of paint removed is small. Therefore, the polishing intensity in these areas should not be too high, as this would lead to damage to the aircraft surface primer and waste of polishing time. Summary of the Invention

[0004] This invention provides a method and medium for polishing the surface of aircraft parts based on a color point cloud camera, so as to protect the aircraft primer and reduce polishing time.

[0005] According to one aspect of the present invention, a method for surface polishing of aircraft parts based on a color point cloud camera is provided, comprising: The current color 3D point cloud data and current color 2D image corresponding to the surface of the target aircraft part to be polished are collected in real time by a pre-set color 3D point cloud camera. The current color 3D point cloud data is processed using a preset point cloud preprocessing and segmentation method to obtain the current color filtered 3D point cloud data. Based on the current color 2D image and the current color filtered 3D point cloud data, the target color 2D mask image is obtained by processing it through preset image mask preprocessing and morphological processing methods. The target color 2D mask image is processed by a preset image segmentation and paint layer recognition method to obtain the target surface paint dot cloud region, and then a preset polishing path planning method is used to generate the target polishing path. The surface of the target aircraft part is polished according to the target polishing path until the polishing operation on the surface of the target aircraft part is completed, and feedback is given to the user.

[0006] According to another aspect of the present invention, a surface polishing apparatus for aircraft parts based on a color point cloud camera is provided, comprising: The current color 3D point cloud data and current color 2D image acquisition module is used to acquire the current color 3D point cloud data and current color 2D image corresponding to the surface of the target aircraft part to be polished in real time through a pre-set color 3D point cloud camera. The current color screening 3D point cloud data determination module is used to process the current color 3D point cloud data using a preset point cloud preprocessing and segmentation method to obtain the current color screening 3D point cloud data. The target mask operation image determination module is used to process the current color 2D image and the current color filtered 3D point cloud data through preset image mask preprocessing and morphological processing methods to obtain the target color 2D mask image. The target polishing path generation module is used to process the target color 2D mask image through a preset image segmentation and paint layer recognition method to obtain the target surface paint point cloud region, and combine it with a preset polishing path planning method to generate the target polishing path. The grinding operation module is used to grind the surface of the target aircraft part according to the target grinding path until the grinding operation on the surface of the target aircraft part is completed, and to provide feedback to the user.

[0007] According to another aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the aircraft part surface polishing method based on a color point cloud camera as described in any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the aircraft part surface polishing method based on a color point cloud camera as described in any embodiment of the present invention.

[0009] The technical solution of this invention uses a pre-set color 3D point cloud camera to acquire in real time the current color 3D point cloud data and the current color 2D image corresponding to the surface of the target aircraft part to be polished; a preset point cloud preprocessing and segmentation method is used to process the current color 3D point cloud data to obtain current color-selected 3D point cloud data; based on the current color 2D image and the current color-selected 3D point cloud data, a preset image mask preprocessing and morphological processing method is used to obtain the target color 2D mask image; and a preset image segmentation and paint layer identification method is used... Another method processes the target color 2D mask image to obtain the target paint point cloud region, and combines it with a preset sanding path planning method to generate the target sanding path; the target aircraft part surface is sanded according to the target sanding path until the sanding operation of the target aircraft part surface is determined to be completed, and feedback is given to the user; this method solves the problems of damage to the aircraft primer and wasted sanding time caused by multiple full sanding, protects the aircraft primer, reduces sanding time, improves the flexibility and comprehensiveness of aircraft surface sanding, and improves the efficiency and accuracy of aircraft surface sanding.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1a This is a flowchart of a surface polishing method for aircraft parts based on a color point cloud camera, according to Embodiment 1 of the present invention. Figure 1b This is a schematic diagram of the structure of the current color 3D point cloud data corresponding to the surface of the target aircraft part according to Embodiment 1 of the present invention; Figure 1c This is a structural schematic diagram of the current color 2D image corresponding to the surface of the target aircraft part according to Embodiment 1 of the present invention; Figure 1d This is a schematic diagram of the structure of multiple clustered partition point clouds provided in Embodiment 1 of the present invention; Figure 1e This is a schematic diagram of the structure of a target clustering partition point cloud provided in Embodiment 1 of the present invention; Figure 1fThis is a schematic diagram of the structure of front-color screening 3D point cloud data provided according to Embodiment 1 of the present invention; Figure 1g This is a schematic diagram of the structure of the initial segmentation mask provided in Embodiment 1 of the present invention; Figure 1h This is a schematic diagram of the target segmentation mask image provided in Embodiment 1 of the present invention; Figure 1i This is a schematic diagram of the structure of a target color 2D mask image provided in Embodiment 1 of the present invention; Figure 1j This is a schematic diagram of the current color segmentation result provided in Embodiment 1 of the present invention; Figure 1k This is a schematic diagram of the structure of the target paint dot cloud region according to Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the structure of an aircraft part surface polishing device based on a color point cloud camera according to Embodiment 2 of the present invention. Figure 3 This is a schematic diagram of the structure of an electronic device provided according to Embodiment 3 of the present invention. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0014] It should be noted that the terms "target," "current," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0015] It is worth noting that the information collected in the technical solution of this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse; if the user chooses to refuse, the process will proceed to the expert decision-making process.

[0016] Example 1 Figure 1a The present invention provides a flowchart of a method for polishing the surface of aircraft parts based on a color point cloud camera. This embodiment is applicable to the case where the surface of aircraft parts is polished multiple times. The method can be executed by an aircraft part surface polishing device based on a color point cloud camera, which can be implemented in hardware and / or software.

[0017] Correspondingly, such as Figure 1a As shown, the method includes: S110: Using a pre-set color 3D point cloud camera, the current color 3D point cloud data and current color 2D image corresponding to the surface of the target aircraft part to be polished are collected in real time.

[0018] In this embodiment, the color 3D point cloud camera is a high-resolution color 3D camera; the target aircraft part surface can be the surface of an aircraft sheet metal part. Through camera acquisition, color 3D point cloud data and color 2D images of the aircraft sheet metal part surface can be obtained; wherein, each point cloud in the color 3D point cloud data contains not only X, Y, Z coordinate information, but also R, G, B color information.

[0019] With the camera properly calibrated, each 3D point in the color 3D point cloud data is directly associated with a pixel in the color 2D image, and the corresponding RGB value comes from the color information of that pixel. This point cloud data and image pixels have a strict one-to-one correspondence. Relying on the camera's intrinsic and extrinsic parameters, calibration and data fusion are used to precisely align the depth map and RGB image, achieving the matching of the depth value and color value of each spatial point. For example... Figure 1b This is a structural diagram of the current color 3D point cloud data corresponding to the surface of the target aircraft part; such as... Figure 1c This is a structural schematic diagram of the current color 2D image corresponding to the surface of the target aircraft part.

[0020] Using a color 3D point cloud camera not only accurately captures the three-dimensional shape of parts but also simultaneously collects rich color information, providing a solid data foundation for subsequent accurate identification and path planning. Furthermore, the one-to-one correspondence between points in the point cloud data and image pixels ensures rapid location of specific regions within the image in three-dimensional space, significantly improving the efficiency of data processing and analysis.

[0021] S120. Using a preset point cloud preprocessing and segmentation method, process the current color 3D point cloud data to obtain the current color filtered 3D point cloud data.

[0022] The point cloud preprocessing and segmentation method can be a method for downsampling, clustering, and segmenting color 3D point cloud data. The current color-filtered 3D point cloud data can be points filtered from the preprocessed current color 3D point cloud data.

[0023] Optionally, the step of processing the current color 3D point cloud data using a preset point cloud preprocessing and segmentation method to obtain the current color-selected 3D point cloud data includes: using the point cloud preprocessing and segmentation method to downsample the current color 3D point cloud data according to a preset voxel grid size parameter to obtain the current color-downsampled 3D point cloud data; performing clustering and partitioning processing on the current color-downsampled 3D point cloud data using a preset point cloud clustering algorithm to obtain multiple clustered partition point clouds, and determining the largest selected clustered partition point cloud as the target clustered partition point cloud; wherein, the point cloud clustering algorithm is the DBSCAN clustering algorithm; searching for at least one related point cloud data located around the target clustered partition point cloud in the current color 3D point cloud data, and adding each of the related point cloud data to the target clustered partition point cloud to obtain the current color-selected 3D point cloud data.

[0024] In this embodiment, due to the large amount of data in the current color 3D point cloud data, direct processing would lead to excessive consumption of computational resources and affect processing efficiency. Therefore, it is necessary to set appropriate voxel grid size parameters (different voxel grid sizes can be set according to the point cloud situation) to downsample the current color 3D point cloud data, resulting in current color downsampled 3D point cloud data. This reduces the number of points by downsampling, significantly improving the running speed of subsequent algorithms while preserving necessary spatial information. For example, assuming the number of points in the current color 3D point cloud data is 2,332,800; after downsampling, the number of points in the current color downsampled 3D point cloud data is 1,021,772.

[0025] Furthermore, the DBSCAN clustering algorithm is used to cluster and partition the current color downsampled 3D point cloud data, resulting in multiple clustered partition point clouds. The largest selected cluster partition point cloud is then determined as the target cluster partition point cloud. Specifically, the DBSCAN clustering algorithm can effectively handle noise points and identify clusters of arbitrary shapes, making it suitable for complex sheet metal parts surfaces. Through clustering, the parts to be polished can be separated from a large number of point clouds, ensuring the accuracy of subsequent processing. The DBSCAN clustering algorithm is used to cluster and partition the downsampled color downsampled 3D point cloud data. Due to the large number and density of point clouds on the sheet metal parts to be polished, the point clouds of the parts to be polished are identified and extracted based on the number of point clouds in each cluster. After the DBSCAN clustering algorithm, the current color downsampled 3D point cloud data is divided into n clustered regions, such as... Figure 1d The image shown is a schematic diagram of the structure of point clouds with multiple clustering partitions. From... Figure 1d In the image, we can see that the area where the part is located (dark blue dots) is the largest point cloud. By segmenting the blue point cloud in the image, we obtain the target clustering partition point cloud, as shown below. Figure 1e The diagram shown is a schematic representation of the target clustering partition point cloud.

[0026] Since the DBSCAN clustering algorithm is performed on the downsampled point cloud, to obtain the surface point cloud at the original resolution, it is necessary to locate and extract relevant points in the original point cloud (i.e., the current color 3D point cloud data). Specifically, in the current color 3D point cloud data, at least one relevant point cloud data located around the target cluster partition point cloud is searched, and each relevant point cloud data is added to the target cluster partition point cloud to obtain the current color-selected 3D point cloud data. More specifically, a kd-tree structure can be used to search for all points near the target cluster partition point cloud in the original point cloud, separating the point cloud of the surface of the part to be polished, thus obtaining the current color-selected 3D point cloud data. Figure 1f The diagram shown illustrates the current structure of color-filtered 3D point cloud data. This ensures that the separated surface point cloud has sufficient detail for subsequent image processing and path planning.

[0027] S130. Based on the current color 2D image and the current color filtered 3D point cloud data, the target color 2D mask image is obtained by processing it through a preset image mask preprocessing and morphological processing method.

[0028] Optionally, the step of processing the current color 2D image and the current color-filtered 3D point cloud data using a preset image mask preprocessing and morphological processing method to obtain a target mask operation image includes: determining an initial segmentation mask image region based on the size information corresponding to the current color 2D image using the image mask preprocessing sub-method in the image mask preprocessing and morphological processing method; setting the image pixels corresponding to the current color-filtered 3D point cloud data in the initial segmentation mask image region according to the correspondence between the current color-filtered 3D point cloud data and the current color 2D image to obtain the initial segmentation mask image; obtaining a target segmentation mask image based on the initial segmentation mask image; and processing the current color 2D image using the target segmentation mask image to obtain a target color 2D mask image.

[0029] Specifically, obtaining the target segmentation mask based on the initial segmentation mask includes: using the morphological closing operation processing sub-method in the image mask preprocessing and morphological processing method to denoise the initial segmentation mask using a preset target structuring element, and combining the morphological erosion operation processing sub-method to optimize the denoised mask to obtain the target segmentation mask.

[0030] In this embodiment, an image mask preprocessing sub-method is first used to delineate the corresponding area of ​​the part to be polished in the image based on the size information corresponding to the current color 2D image, thus determining the initial segmentation mask area. The size of the determined initial segmentation mask area is consistent with that of the 2D image. Next, utilizing the one-to-one correspondence between the current color-filtered 3D point cloud data (point cloud) and the current color 2D image (pixels), the image pixels corresponding to the current color-filtered 3D point cloud data are set in the initial segmentation mask area to obtain the initial segmentation mask, as shown below. Figure 1g The diagram shown is a schematic representation of the initial segmentation mask.

[0031] Furthermore, after determining the initial segmentation mask, the morphological closing operation sub-method is used during data processing to fill in small black dots in the segmentation mask and eliminate noise. By using appropriate structuring elements (such as circles or rectangles), this operation can effectively fill in noise, improve the continuity and integrity of the mask, and thus ensure the accuracy of subsequent processing. Since point cloud data often contains noise, the closing operation is an important step in improving data quality. In addition, to address the problem of poor point cloud quality in the edge areas of the part surface, the morphological erosion operation sub-method is used to process the mask to remove edge noise. Through appropriate erosion operations, misidentified areas can be effectively reduced, the mask can be optimized, and finally, the processed mask is obtained, i.e., as shown below. Figure 1h A schematic diagram of the target segmentation mask image.

[0032] Accordingly, the current color 2D image is processed using the target segmentation mask image to obtain the target color 2D mask image. That is, as follows... Figure 1i The image shown is a schematic diagram of the structure of the target color 2D mask image.

[0033] S140. The target color 2D mask image is processed by a preset image segmentation and paint layer recognition method to obtain the target surface paint dot cloud region, and the target polishing path is generated by combining the preset polishing path planning method.

[0034] Optionally, the step of processing the target color 2D mask image using a preset image segmentation and paint layer recognition method to obtain the target surface paint point cloud region, and generating the target polishing path in conjunction with a preset polishing path planning method, includes: performing clustering and color segmentation processing on the target color 2D mask image using the clustering algorithm region segmentation sub-method in the image segmentation and paint layer recognition method to obtain the current color segmentation result; determining the current surface paint region based on the current color segmentation result, and obtaining the target surface paint point cloud region corresponding to the current surface paint region in the current color 3D point cloud data; and generating the target polishing path based on the target surface paint point cloud region using the polishing path planning method.

[0035] Specifically, the step of generating a target polishing path based on the target paint dot cloud region using the polishing path planning method includes: based on the current color-filtered 3D point cloud data, using the polishing path planning method to plan a polishing path for the target paint dot cloud region to generate the target polishing path; wherein, the polishing path planning method is a polishing path planning method based on an equal-spacing planning algorithm.

[0036] In this embodiment, since there is a difference between the primer and the topcoat in the aircraft parts, for example, the primer is set to yellow-green and the topcoat to white, the color difference between the primer and the topcoat in the image can be analyzed.

[0037] Specifically, the clustering algorithm for region segmentation can be the K-Means clustering analysis method, which performs clustering and color segmentation processing on the target color 2D mask image to obtain the current color segmentation result. Through clustering, the primer and topcoat regions can be identified more accurately, automatically determining the optimal segmentation for color distribution, reducing errors caused by manually setting thresholds, improving the reliability and stability of color segmentation, and ensuring the accuracy of subsequent polishing paths. The K-Means clustering algorithm divides all colors in the image into two clusters, replacing each with a single color to generate the clustered image. Based on the current color segmentation result, the primer and topcoat regions in the image need to be identified to determine the current topcoat region, i.e., ... Figure 1jThis is a structural diagram of the current color segmentation result. Further, in the current color 3D point cloud data, the target paint point cloud region corresponding to the current paint region is obtained; such as... Figure 1k A schematic diagram of the structure of the target paint dot cloud region.

[0038] Correspondingly, no further sanding is needed for the primer area to avoid over-sanding. Therefore, a target sanding path needs to be generated based on the target topcoat point cloud area using a sanding path planning method. An equal-spacing planning algorithm can be used to plan the sanding path for the target topcoat point cloud area to generate the target sanding path.

[0039] S150. Grind the surface of the target aircraft part according to the target grinding path until the grinding operation on the surface of the target aircraft part is completed, and provide feedback to the user.

[0040] Optionally, the step of polishing the surface of the target aircraft part according to the target polishing path until the polishing operation on the surface of the target aircraft part is determined to be completed includes: polishing the surface of the target aircraft part according to the target polishing path to obtain the current polishing result of the part surface; determining whether the current polishing result of the part surface meets the requirements of the preset target polishing result image; if yes, then determining that the polishing operation on the surface of the target aircraft part is completed; if no, then returning to the operation of acquiring the current color 3D point cloud data and the current color 2D image corresponding to the surface of the target aircraft part to be polished in real time through a preset color 3D point cloud camera, until the requirements of the target polishing result image are met or a stop polishing command is received.

[0041] In this embodiment, the surface of the part is actually sanded according to the planned sanding path to ensure that the amount of sanding is appropriate and to achieve the expected surface quality. The actual sanding operation is performed to verify and apply the planned path, complete the paint treatment, and ensure that the actual effect of the sanding process meets expectations.

[0042] After completing the current grinding cycle, the grinding result of the current part surface can be obtained. It is necessary to determine whether the current grinding result of the current part surface meets the requirements of the preset target grinding result image. If so, the grinding operation on the target aircraft part surface is completed, and the user is informed that the grinding is complete.

[0043] If not, it is necessary to use a pre-set color 3D point cloud camera to collect the current color 3D point cloud data and the current color 2D image of the target aircraft part surface to be polished in real time, and then perform the next polishing process (re-identification and path planning) until the polishing result meets the requirements of the target polishing result image or a stop polishing command is received.

[0044] This multi-layered sanding process ensures overall paint quality, gradually optimizes the sanding path, reduces the sanding area, and ultimately achieves precise control of the sanding depth, avoiding over-sanding and forming a closed-loop intelligent sanding control system.

[0045] The technical solution of this invention uses a pre-set color 3D point cloud camera to acquire in real time the current color 3D point cloud data and the current color 2D image corresponding to the surface of the target aircraft part to be polished; a preset point cloud preprocessing and segmentation method is used to process the current color 3D point cloud data to obtain current color-selected 3D point cloud data; based on the current color 2D image and the current color-selected 3D point cloud data, a preset image mask preprocessing and morphological processing method is used to obtain the target color 2D mask image; and a preset image segmentation and paint layer identification method is used... Another method processes the target color 2D mask image to obtain the target paint point cloud region, and combines it with a preset sanding path planning method to generate the target sanding path; the target aircraft part surface is sanded according to the target sanding path until the sanding operation of the target aircraft part surface is determined to be completed, and feedback is given to the user; this method solves the problems of damage to the aircraft primer and wasted sanding time caused by multiple full sanding, protects the aircraft primer, reduces sanding time, improves the flexibility and comprehensiveness of aircraft surface sanding, and improves the efficiency and accuracy of aircraft surface sanding.

[0046] Example 2 Figure 2 This is a schematic diagram of a surface polishing device for aircraft parts based on a color point cloud camera, provided in Embodiment 2 of the present invention. The surface polishing device for aircraft parts based on a color point cloud camera provided in this embodiment can be implemented through software and / or hardware, and can be configured in a terminal device or server to implement a surface polishing method for aircraft parts based on a color point cloud camera according to an embodiment of the present invention. Figure 2 As shown, the device includes: a current color 3D point cloud data and current color 2D image acquisition module 210, a current color 3D point cloud data determination module 220, a target mask operation map determination module 230, a target polishing path generation module 240, and a polishing operation module 250.

[0047] The current color 3D point cloud data and current color 2D image acquisition module 210 is used to acquire the current color 3D point cloud data and current color 2D image corresponding to the surface of the target aircraft part to be polished in real time through a pre-set color 3D point cloud camera. The current color screening 3D point cloud data determination module 220 is used to process the current color 3D point cloud data using a preset point cloud preprocessing and segmentation method to obtain the current color screening 3D point cloud data. The target mask operation image determination module 230 is used to process the current color 2D image and the current color filtered 3D point cloud data through a preset image mask preprocessing and morphological processing method to obtain the target color 2D mask image. The target polishing path generation module 240 is used to process the target color 2D mask image through a preset image segmentation and paint layer recognition method to obtain the target surface paint dot cloud region, and combine it with a preset polishing path planning method to generate the target polishing path. The grinding operation module 250 is used to grind the surface of the target aircraft part according to the target grinding path until the grinding operation on the surface of the target aircraft part is completed, and to provide feedback to the user.

[0048] The technical solution of this invention uses a pre-set color 3D point cloud camera to acquire in real time the current color 3D point cloud data and the current color 2D image corresponding to the surface of the target aircraft part to be polished; a preset point cloud preprocessing and segmentation method is used to process the current color 3D point cloud data to obtain current color-selected 3D point cloud data; based on the current color 2D image and the current color-selected 3D point cloud data, a preset image mask preprocessing and morphological processing method is used to obtain the target color 2D mask image; and a preset image segmentation and paint layer identification method is used... Another method processes the target color 2D mask image to obtain the target paint point cloud region, and combines it with a preset sanding path planning method to generate the target sanding path; the target aircraft part surface is sanded according to the target sanding path until the sanding operation of the target aircraft part surface is determined to be completed, and feedback is given to the user; this method solves the problems of damage to the aircraft primer and wasted sanding time caused by multiple full sanding, protects the aircraft primer, reduces sanding time, improves the flexibility and comprehensiveness of aircraft surface sanding, and improves the efficiency and accuracy of aircraft surface sanding.

[0049] Based on the above embodiments, the current color-selected 3D point cloud data determination module 220 can be specifically used to: use the point cloud preprocessing and segmentation method to downsample the current color 3D point cloud data according to a preset voxel grid size parameter to obtain current color-downsampled 3D point cloud data; use a preset point cloud clustering algorithm to cluster and partition the current color-downsampled 3D point cloud data to obtain multiple clustered partition point clouds, and determine the largest selected clustered partition point cloud as the target clustered partition point cloud; wherein, the point cloud clustering algorithm is the DBSCAN clustering algorithm; search for at least one related point cloud data located around the target clustered partition point cloud in the current color 3D point cloud data, and add each of the related point cloud data to the target clustered partition point cloud to obtain the current color-selected 3D point cloud data.

[0050] Based on the above embodiments, the target mask operation map determination module 230 can be specifically used to: determine an initial segmentation mask map region according to the size information corresponding to the current color 2D image through the image mask preprocessing sub-method in the image mask preprocessing and morphological processing method; set the image pixels corresponding to the current color filter 3D point cloud data in the initial segmentation mask map region according to the correspondence between the current color filter 3D point cloud data and the current color 2D image to obtain the initial segmentation mask map; obtain a target segmentation mask map according to the initial segmentation mask map; and process the current color 2D image using the target segmentation mask map to obtain a target color 2D mask image.

[0051] Based on the above embodiments, the target mask operation map determination module 230 can also be specifically used to: use the morphological closing operation processing sub-method in the image mask preprocessing and morphological processing method to perform noise reduction processing on the initial segmentation mask map using preset target structuring elements, and combine the morphological erosion operation processing sub-method to optimize the denoised mask map to obtain the target segmentation mask map.

[0052] Based on the above embodiments, the target polishing path generation module 240 can be specifically used to: perform clustering and color segmentation processing on the target color 2D mask image using the clustering algorithm region segmentation sub-method in the image segmentation and paint layer recognition method to obtain the current color segmentation result; determine the current paint area based on the current color segmentation result, and obtain the target paint point cloud area corresponding to the current paint area in the current color 3D point cloud data; and generate the target polishing path based on the target paint point cloud area using the polishing path planning method.

[0053] Based on the above embodiments, the target polishing path generation module 240 can also be specifically used to: based on the current color screening 3D point cloud data, use a polishing path planning method to plan the polishing path for the target paint point cloud area to generate a target polishing path; wherein, the polishing path planning method is a polishing path planning method based on an equal spacing planning algorithm.

[0054] Based on the above embodiments, the polishing operation module 250 can be specifically used to: polish the surface of the target aircraft part according to the target polishing path to obtain the current polishing result of the part surface; determine whether the current polishing result of the part surface meets the requirements of the preset target polishing result image; if so, determine that the polishing operation on the surface of the target aircraft part is completed; if not, return to execute the operation of acquiring the current color 3D point cloud data and the current color 2D image corresponding to the surface of the target aircraft part to be polished in real time through a preset color 3D point cloud camera, until the requirements of the target polishing result image are met or a stop polishing command is received.

[0055] The aircraft part surface polishing device based on a color point cloud camera provided in this embodiment of the invention can perform the aircraft part surface polishing method based on a color point cloud camera provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0056] Example 3 Figure 3 A schematic diagram of an electronic device 10, which can be used to implement Embodiment 3 of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0057] like Figure 3 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0058] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0059] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a surface polishing method for aircraft parts based on a color point cloud camera.

[0060] In some embodiments, the aircraft part surface polishing method based on a color point cloud camera can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the aircraft part surface polishing method based on a color point cloud camera described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the aircraft part surface polishing method based on a color point cloud camera by any other suitable means (e.g., by means of firmware).

[0061] The method includes: acquiring, in real time, current color 3D point cloud data and current color 2D image corresponding to the surface of the target aircraft part to be polished using a pre-set color 3D point cloud camera; processing the current color 3D point cloud data using a pre-set point cloud preprocessing and segmentation method to obtain current color filtered 3D point cloud data; processing the current color 2D image and the current color filtered 3D point cloud data using a pre-set image mask preprocessing and morphological processing method to obtain a target color 2D mask image; processing the target color 2D mask image using a pre-set image segmentation and paint layer recognition method to obtain the target paint point cloud region, and generating a target polishing path by combining it with a pre-set polishing path planning method; polishing the surface of the target aircraft part according to the target polishing path until the polishing operation on the surface of the target aircraft part is determined to be completed, and providing feedback to the user.

[0062] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0063] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0064] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0065] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0066] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0067] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0068] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and no limitation is imposed herein.

[0069] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

[0070] Example 4 Embodiment 4 of the present invention also provides a computer-readable storage medium, wherein the computer-readable instructions, when executed by a computer processor, are used to execute a method for polishing the surface of an aircraft part based on a color point cloud camera. The method includes: acquiring, in real time, current color 3D point cloud data and a current color 2D image corresponding to the surface of the target aircraft part to be polished using a pre-set color 3D point cloud camera; processing the current color 3D point cloud data using a pre-set point cloud preprocessing and segmentation method to obtain current color filtered 3D point cloud data; processing the current color 2D image and the current color filtered 3D point cloud data using a pre-set image mask preprocessing and morphological processing method to obtain a target color 2D mask image; processing the target color 2D mask image using a pre-set image segmentation and paint layer recognition method to obtain a target paint point cloud region, and generating a target polishing path using a pre-set polishing path planning method; polishing the surface of the target aircraft part according to the target polishing path until the polishing operation on the surface of the target aircraft part is determined to be completed, and providing feedback to the user.

[0071] Of course, the computer-executable instructions provided in the embodiments of the present invention, which include a computer-readable storage medium, are not limited to the method operations described above, but can also perform related operations in the aircraft part surface polishing method based on a color point cloud camera provided in any embodiment of the present invention.

[0072] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0073] It is worth noting that in the above embodiments of the aircraft part surface polishing method based on color point cloud camera, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0074] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for surface polishing of aircraft parts based on a color point cloud camera, characterized in that, include: The current color 3D point cloud data and current color 2D image corresponding to the surface of the target aircraft part to be polished are collected in real time by a pre-set color 3D point cloud camera. The current color 3D point cloud data is processed using a preset point cloud preprocessing and segmentation method to obtain the current color filtered 3D point cloud data. Based on the current color 2D image and the current color filtered 3D point cloud data, the target color 2D mask image is obtained by processing it through preset image mask preprocessing and morphological processing methods. The target color 2D mask image is processed by a preset image segmentation and paint layer recognition method to obtain the target surface paint dot cloud region, and then a preset polishing path planning method is used to generate the target polishing path. The surface of the target aircraft part is polished according to the target polishing path until the polishing operation on the surface of the target aircraft part is completed, and feedback is given to the user.

2. The method according to claim 1, characterized in that, The process of using a preset point cloud preprocessing and segmentation method to process the current color 3D point cloud data to obtain the current color-selected 3D point cloud data includes: Using the point cloud preprocessing and segmentation method, the current color 3D point cloud data is downsampled according to the preset voxel mesh size parameters to obtain the current color downsampled 3D point cloud data. The current color downsampled 3D point cloud data is clustered and partitioned using a preset point cloud clustering algorithm to obtain multiple clustered partition point clouds, and the largest selected clustered partition point cloud is determined as the target clustered partition point cloud. The point cloud clustering algorithm is the DBSCAN clustering algorithm. In the current color 3D point cloud data, at least one related point cloud data located around the target cluster partition point cloud is searched, and each of the related point cloud data is added to the target cluster partition point cloud to obtain the current color filtered 3D point cloud data.

3. The method according to claim 2, characterized in that, The step involves processing the current color 2D image and the current color-filtered 3D point cloud data using a preset image mask preprocessing and morphological processing method to obtain a target mask operation map, including: The image mask preprocessing sub-method in the image mask preprocessing and morphological processing method is used to determine the initial segmentation mask region based on the size information corresponding to the current color 2D image; Based on the correspondence between the current color-filtered 3D point cloud data and the current color 2D image, the image pixels corresponding to the current color-filtered 3D point cloud data are set in the initial segmentation mask area to obtain the initial segmentation mask. Based on the initial segmentation mask image, the target segmentation mask image is obtained; The target segmentation mask image is used to process the current color 2D image to obtain the target color 2D mask image.

4. The method according to claim 3, characterized in that, The step of obtaining the target segmentation mask based on the initial segmentation mask image includes: The initial segmentation mask image is denoised using the morphological closing operation sub-method in the image mask preprocessing and morphological processing method. The denoised mask image is then optimized using the morphological erosion operation sub-method to obtain the target segmentation mask image.

5. The method according to claim 4, characterized in that, The process involves processing the target color 2D mask image using a preset image segmentation and paint layer recognition method to obtain the target surface paint point cloud region, and then combining this with a preset polishing path planning method to generate the target polishing path, including: The clustering algorithm region segmentation sub-method in the image segmentation and paint layer recognition method is used to perform clustering and color segmentation processing on the target color 2D mask image to obtain the current color segmentation result; Based on the current color segmentation result, the current paint area is determined, and the target paint point cloud area corresponding to the current paint area is obtained from the current color 3D point cloud data. Based on the target surface paint dot cloud area, the target polishing path is generated using the aforementioned polishing path planning method.

6. The method according to claim 5, characterized in that, The step of generating a target sanding path based on the target paint dot cloud region using the sanding path planning method includes: Based on the current color screening 3D point cloud data, a polishing path planning method is used to plan the polishing path for the target paint point cloud area to generate the target polishing path. The polishing path planning method is a polishing path planning method based on the equal spacing planning algorithm.

7. The method according to claim 6, characterized in that, The step of polishing the surface of the target aircraft part according to the target polishing path until the polishing operation on the surface of the target aircraft part is determined to be completed includes: The surface of the target aircraft part is polished according to the target polishing path to obtain the current polishing result of the part surface; Determine whether the current part surface polishing result meets the requirements of the preset target polishing result image. If so, determine that the polishing operation on the target aircraft part surface is completed. If not, then return to the operation of using a pre-set color 3D point cloud camera to collect the current color 3D point cloud data and the current color 2D image corresponding to the surface of the target aircraft part to be polished in real time, until the requirements of the target polishing result image are met or a stop polishing command is received.

8. A surface polishing device for aircraft parts based on a color point cloud camera, characterized in that, include: The current color 3D point cloud data and current color 2D image acquisition module is used to acquire the current color 3D point cloud data and current color 2D image corresponding to the surface of the target aircraft part to be polished in real time through a pre-set color 3D point cloud camera. The current color screening 3D point cloud data determination module is used to process the current color 3D point cloud data using a preset point cloud preprocessing and segmentation method to obtain the current color screening 3D point cloud data. The target mask operation image determination module is used to process the current color 2D image and the current color filtered 3D point cloud data through preset image mask preprocessing and morphological processing methods to obtain the target color 2D mask image. The target polishing path generation module is used to process the target color 2D mask image through a preset image segmentation and paint layer recognition method to obtain the target surface paint point cloud region, and combine it with a preset polishing path planning method to generate the target polishing path. The grinding operation module is used to grind the surface of the target aircraft part according to the target grinding path until the grinding operation on the surface of the target aircraft part is completed, and to provide feedback to the user.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements a surface polishing method for aircraft parts based on a color point cloud camera as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute a surface polishing method for aircraft parts based on a color point cloud camera as described in any one of claims 1-7.

Images