Point cloud data processing method, device, electronic device and storage medium

Abstract

The present disclosure provides a point cloud data processing method, apparatus, electronic device, and storage medium, relating to the field of computer technologies, and particularly to the field of big data. The specific implementation solution is as follows: in response to detecting an operation of selecting homonymous point data in the point cloud data, determine first position information corresponding to the selected target homonymous point data. Determine second position information corresponding to bounding box feature data, where the bounding box feature data corresponds to the target homonymous point data. In response to detecting that the position represented by the second position information is outside the target area range, determine the position of the target homonymous point data according to the second position information, where the target area includes the area determined according to the first position information.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and more particularly to the field of big data. Specifically, it relates to a method, apparatus, electronic device, and storage medium for processing point cloud data. Background Art

[0002] A high-precision map, that is, a high-precision map, is a core technology in the field of driverless driving. It can help a driverless vehicle pre-perceive complex road surface information, such as slope, curvature, heading, etc. Combined with intelligent path planning, the driverless vehicle can make correct decisions. Driverless driving needs to compare the information collected by sensors with the stored high-precision map to determine the position and driving direction of the driverless vehicle, thereby ensuring the safe driving of the driverless vehicle to the destination. Therefore, the accuracy of high-precision map data collection is very crucial for driverless driving. Summary of the Invention

[0003] The present disclosure provides a method, apparatus, electronic device, and storage medium for processing point cloud data.

[0004] According to one aspect of the present disclosure, there is provided a method for processing point cloud data, including: in response to detecting an operation of selecting homonymous point data in point cloud data, determining first position information corresponding to the selected target homonymous point data; determining second position information corresponding to bounding box feature data, where the bounding box feature data corresponds to the target homonymous point data; and in response to detecting that the position represented by the second position information is outside the target area range, determining the position of the target homonymous point data according to the second position information, where the target area includes the area determined according to the first position information.

[0005] According to another aspect of the present disclosure, there is provided a device for processing point cloud data, including: a first determination module, configured to determine first position information corresponding to the selected target homonymous point data in response to detecting an operation of selecting homonymous point data in point cloud data; a second determination module, configured to determine second position information corresponding to bounding box feature data, where the bounding box feature data corresponds to the target homonymous point data; and a third determination module, configured to determine the position of the target homonymous point data according to the second position information in response to detecting that the position represented by the second position information is outside the target area range, where the target area includes the area determined according to the first position information.

[0006] According to another aspect of the present disclosure, there is provided an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the point cloud data processing method of the present disclosure.

[0007] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the point cloud data processing method of the present disclosure.

[0008] According to another aspect of the present disclosure, there is provided a computer program product, including a computer program which, when executed by a processor, implements the point cloud data processing method of the present disclosure.

[0009] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0011] Figure 1 Schematically shows an exemplary system architecture to which the point cloud data processing method and apparatus according to embodiments of the present disclosure can be applied;

[0012] Figure 2 Schematically shows a flowchart of the point cloud data processing method according to embodiments of the present disclosure;

[0013] Figure 3 Schematically shows a schematic diagram for determining the positions of valid homologous points according to embodiments of the present disclosure;

[0014] Figure 4 Schematically shows a block diagram of the point cloud data processing apparatus according to embodiments of the present disclosure; and

[0015] Figure 5 Shows a schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, descriptions of well-known functions and structures are omitted in the following description for clarity and conciseness.

[0017] In the technical solution of the present disclosure, the processing of the user's personal information, such as collection, storage, use, processing, transmission, provision, disclosure, and application, complies with the provisions of relevant laws and regulations, takes necessary confidentiality measures, and does not violate public order and good customs.

[0018] In the technical solution of the present disclosure, the authorization or consent of the user is obtained before obtaining or collecting the user's personal information.

[0019] Point cloud is a massive set of points that represents the spatial distribution of an object and the characteristics of its surface in the same spatial reference system, and can represent the set of object positions in space. Point cloud fusion includes automatic algorithm fusion and manual fusion, which are used to improve the position accuracy of the point cloud and eliminate phenomena such as deviation, ghosting, and layering between different point clouds representing the same object. The high-precision map for autonomous driving relies heavily on the effect and accuracy of point cloud fusion. However, when automatically fusing the point clouds of multi-layer roads such as overpasses and double-deck roads, as well as scenes such as tunnels, intersections, and toll stations, the fusion effect is greatly affected by the field collection parameters. For example, the actually collected point cloud is affected by weather, vehicle speed, etc., and the collected point cloud may have phenomena such as distortion, deformation, and ghosting. For the point cloud data collected in the field, automatic algorithm fusion is first performed. If the effect of the automatic algorithm fusion does not meet the standard, then manual fusion is performed on the point cloud data with poor effect. Therefore, manual fusion plays an important role in point cloud fusion.

[0020] The operation methods of manual fusion mainly include: trajectory deletion, homologous point registration, ICP (Iterative Closest Point) registration, and trajectory smoothing, etc. The operation method with the highest frequency of use and the greatest impact on operation efficiency in repairable scenarios is homologous point registration. Homologous points are the representations of the same points at the same position in the real world in different point cloud data. In the form of a polyhedron or points, homologous points are marked at the same positions of multiple trajectories of traffic elements displayed in the actual point cloud data. The methods of homologous point registration include, for example: for point cloud data with ghosting, select multiple homologous points for manual marking, and eliminate the ghosting by pulling the homologous points.

[0021] The registration of homologous points depends on the extraction of the features of all traffic elements within the road acquisition range. The features of traffic elements are extracted in the form of bounding boxes, and the extraction results include the set of point cloud coordinates corresponding to the bounding boxes. For example, for traffic elements such as lane lines, diversion areas, and poles, a bounding box that basically encloses the object can be used to extract the relevant traffic element features. Only when the position of the marked homologous point matches the position of the bounding box corresponding to the element features extracted for that homologous point can the homologous point be dragged and registered.

[0022] In the process of implementing the concept of the present disclosure, the inventors found that there is an incomplete match between the size, position, etc. of the bounding boxes of the extracted traffic element features and the size, position, etc. of the actual point cloud data. Especially when preventing the client from having too much bearing capacity and causing the client to be unable to operate, only the point cloud data is displayed at the front end of the client, and the bounding box feature data is not displayed. During manual fusion operations, it is impossible for the operator to determine whether the selected homologous points are valid, and it is easy to mark many invalid homologous points. For example, the homologous points marked during manual fusion are marked based on the position of the actual point cloud data. There may be some deviations in the size and position of the bounding box corresponding to the element features extracted for that homologous point, resulting in the position corresponding to the bounding box not completely matching the marked position of the homologous point. For example, the bounding box corresponding to the lane line element feature will be slightly larger than the edge of the actual point cloud data, resulting in the failure of homologous point feature extraction, making the homologous point unable to be pulled and registered, and thus unable to perform effective fusion. For example, for an element object that is not recognized as a bounding box, such as due to the omission of the feature extraction algorithm, the element features of some point cloud data are not extracted, and there is no corresponding bounding box. When the marked homologous point is this part of the point cloud data, it will also lead to the failure of homologous point feature extraction, making the marked homologous point invalid, affecting the manual fusion effect at the corresponding position, and increasing the cost of repeatedly operating and debugging the program and the time-consuming cost.

[0023] The present disclosure provides a point cloud data processing method, apparatus, electronic device, and storage medium. The point cloud data processing method includes: in response to detecting an operation of selecting homologous point data in the point cloud data, determining first position information corresponding to the selected target homologous point data. Determining second position information corresponding to the bounding box feature data, where the bounding box feature data corresponds to the target homologous point data. In response to detecting that the position represented by the second position information is outside the target area range, determining the position of the target homologous point data according to the second position information, where the target area includes the area determined according to the first position information.

[0024] Figure 1 Schematically shows an exemplary system architecture to which the point cloud data processing method and apparatus according to embodiments of the present disclosure can be applied.

[0025] It should be noted thatFigure 1 The figure shown is only an example of the system architecture to which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios. For example, in another embodiment, the exemplary system architecture to which the point cloud data processing method and apparatus can be applied may include a terminal device, but the terminal device can implement the point cloud data processing method and apparatus provided by the embodiments of the present disclosure without interacting with the server.

[0026] As Figure 1 shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0027] Users can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the terminal devices 101, 102, 103, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (only as examples).

[0028] The terminal devices 101, 102, 103 may be various electronic devices with a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, and desktop computers, etc.

[0029] The server 105 may be a server that provides various services, such as a background management server that supports the content browsed by users using the terminal devices 101, 102, 103 (only as an example). The background management server may analyze and process data such as user requests received, and feedback the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services (″Virtual Private Server″, or simply ″VPS″). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0030] It should be noted that the point cloud data processing method provided by the embodiments of the present disclosure can generally be executed by the terminal devices 101, 102, or 103. Correspondingly, the point cloud data processing device provided by the embodiments of the present disclosure can also be disposed in the terminal devices 101, 102, or 103.

[0031] Alternatively, the point cloud data processing method provided by the embodiments of the present disclosure can generally also be executed by the server 105. Correspondingly, the point cloud data processing device provided by the embodiments of the present disclosure can generally be disposed in the server 105. The point cloud data processing method provided by the embodiments of the present disclosure can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and / or the server 105. Correspondingly, the point cloud data processing device provided by the embodiments of the present disclosure can also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and / or the server 105.

[0032] For example, when it is necessary to process point cloud data, the terminal devices 101, 102, 103 can detect an operation of selecting the same-name point data in the point cloud data, and the server 105 can, in response to detecting the operation of selecting the same-name point data in the point cloud data, determine first position information corresponding to the selected target same-name point data, determine second position information corresponding to the bounding box feature data, where the bounding box feature data corresponds to the target same-name point data, and in response to detecting that the position represented by the second position information is outside the target area range, determine the position of the target same-name point data according to the second position information, where the target area includes the area determined according to the first position information. Or a server or a server cluster capable of communicating with the terminal devices 101, 102, 103 and / or the server 105 responds to the relevant operation and realizes determining the position of the target same-name point data.

[0033] It should be understood that Figure 1 the numbers of the terminal devices, the network, and the servers in

[0034] Figure 2 are merely illustrative. According to the implementation requirements, there can be any number of terminal devices, networks, and servers. Schematically shows a flowchart of the point cloud data processing method according to an embodiment of the present disclosure.

[0035] As Figure 2 shown, the method includes operations S210 to S230.

[0036] In operation S210, in response to detecting an operation of selecting the same-name point data in the point cloud data, determine first position information corresponding to the selected target same-name point data.

[0037] In operation S220, determine second position information corresponding to the bounding box feature data, where the bounding box feature data corresponds to the target homologous point data.

[0038] In operation S230, in response to detecting that the position characterized by the second position information is outside the target area range, determine the position of the target homologous point data according to the second position information, where the target area includes the area determined according to the first position information.

[0039] According to an embodiment of the present disclosure, the point cloud data may represent the point cloud information of the environmental objects collected by the acquisition vehicle. The point cloud information may, for example, include the spatial position information of each point corresponding to the environmental object. The spatial position information may be the position information relative to the WGS-84 (World Geodetic System) coordinate system, and the position information may represent the true position information of the point in the world coordinate system. The point cloud data may include the data obtained after the acquisition vehicle performs one or more acquisitions on the same environmental object. The all-element feature objects may be extracted from the point cloud data collected by the acquisition vehicle based on the feature extraction algorithm, and the extracted element feature objects may be displayed in the form of a point cloud at the front end of the client. The point cloud data displayed at the front end may include the point cloud data obtained after automatically fusing the point cloud data collected by the acquisition vehicle through an algorithm. The point cloud data may have point cloud features such as deviation, ghosting, stratification, and deformation that require further manual fusion. The homologous point data may represent the information of the points selected by the user from the point cloud data when manual fusion operations such as homologous point registration of the point cloud data are required. The homologous point data may include the position information of the homologous point relative to the WGS-84 coordinate system. The first position information may represent the true position information of the corresponding target homologous point.

[0040] According to an embodiment of the present disclosure, the extraction result obtained after extracting the all-element feature objects from the point cloud data may further include the bounding box feature data, and the bounding box feature data is not displayed at the front end of the client. After feature extraction is performed on each homologous point data, a corresponding bounding box feature data can be obtained. The bounding box feature data may include the second position information corresponding to the bounding box and the feature information of the homologous point data corresponding to the bounding box, etc. The second position information and the first position information may be the same or different. In the case where the second position information is different from the first position information, it may indicate that the position of the bounding box feature data obtained by feature extraction is deviated from the position of the point cloud data corresponding to the bounding box feature data.

[0041] According to an embodiment of the present disclosure, the target area range can be determined according to the position characterized by the first position information. For example, the target area range can include the range located according to the position characterized by the first position information, or can include the range centered on the first position information and located with a predefined value as the radius.

[0042] According to an embodiment of the present disclosure, when the position characterized by the second position information is outside the target area range, it can be determined that the position of the bounding box feature data deviates from the position of the homologous point data. After the user selects the homologous point data, the position of the homologous point data can be adjusted according to the position of the bounding box feature data. For example, after the user selects a certain homologous point data, the selection result can be displayed at the position of the bounding box feature data corresponding to the homologous point data, and the feature corresponding to the homologous point data can be obtained according to the adjustment result.

[0043] Through the above embodiments of the present disclosure, when the position of the homologous point data does not match the position of the bounding box feature data corresponding to the homologous point data, the position of the homologous point data can be automatically adjusted. After the adjustment, the position of the homologous point data matches the position of the bounding box feature data, so that each time the homologous point data is selected, the feature corresponding to the homologous point data can be extracted according to the corresponding bounding box feature data, improving the success rate of extracting the feature of the homologous point and ensuring the effectiveness of the homologous point. And it can effectively optimize the effect of manual fusion, reduce the time-consuming cost of repeated operation and debugging, and achieve cost reduction and efficiency improvement of manual fusion.

[0044] The following will further illustrate the Figure 2 method shown with specific embodiments.

[0045] According to an embodiment of the present disclosure, when the position characterized by the second position information is within the target area range, the point cloud data processing method may further include: in response to detecting that the position characterized by the second position information is within the target area range, determining the position of the target homologous point data according to the first position information.

[0046] According to an embodiment of the present disclosure, when the second position information is the same as the first position information, it can be characterized that the position of the bounding box feature data obtained by feature extraction has no deviation from the position of the point cloud data corresponding to the bounding box feature data. In this case, after the user selects the homologous point, the feature corresponding to the homologous point data can be determined according to the bounding box feature data.

[0047] It should be noted that when the position characterized by the second position information is within the target area range, the second position information can be regarded as the same as the first position information.

[0048] According to an embodiment of the present disclosure, when performing an artificial fusion operation, a user may first select target homologous point data to be artificially fused from the point cloud data displayed on the front end of the client. The client may record the position information of each piece of homologous point data selected by the user, i.e., the above-mentioned first position information. Then, the client may determine whether there is bounding box feature data corresponding to the homologous point data selected by the user within a region range determined with the first position information as the center and a predefined value as the radius. If not, first, based on the foregoing method, the position of the homologous point data may be adjusted according to the position of the bounding box feature data. Then, the feature characteristics of the homologous point data may be extracted according to the bounding box feature data. If so, the feature characteristics of the homologous point data may be directly extracted according to the bounding box feature data. The predefined value may be 0.2 m, that is, the value of the radius used to determine the target region range may be 0.2 m. The value of the predefined value is not limited thereto.

[0049] Through the above embodiment of the present disclosure, when the position represented by the second position information is within the target region range, the position of the target homologous point data may not be adjusted. On the basis of effectively extracting the feature characteristics of the homologous point data, the number of adjustments may also be reduced, and the operating energy consumption of the client may be reduced.

[0050] According to an embodiment of the present disclosure, in response to detecting that the position represented by the second position information is outside the target region range, determining the position of the target homologous point data according to the second position information may include: in response to detecting that the position represented by the second position information is outside the target region range, generating a prompt message for selecting automatic adjustment. In response to receiving an operation of selecting automatic adjustment, determining the position of the target homologous point data according to the second position information.

[0051] According to an embodiment of the present disclosure, when the client determines that there is no bounding box feature data corresponding to the homologous point data selected by the user within a region range determined with the first position information as the center and a predefined value as the radius, it may indicate that the bounding box feature data with the second position information is outside this region range. In this case, the client may output a prompt message such as "Feature extraction is invalid. Do you want to perform automatic adjustment?" If the user confirms to select automatic adjustment, the client may continue to increment the radius range of the predefined value in sequence and determine whether there is bounding box feature data corresponding to the homologous point data selected by the user within the new region range until the bounding box feature data is found. After that, the client may automatically adjust the position of the homologous point data according to the position of the bounding box feature data and extract the feature characteristics of the homologous point data according to the bounding box feature data.

[0052] Through the above embodiments of the present disclosure, a prompt message for selecting automatic deviation adjustment can be generated, allowing users to freely choose whether to adjust the position of the same-name point data, enabling selective deviation adjustment in combination with user needs, which is beneficial to improving the user experience.

[0053] According to an embodiment of the present disclosure, determining the position of the target same-name point data based on the second position information may include: highlighting the area occupied by the bounding box feature data corresponding to the second position information. In response to receiving an operation of selecting target point data in the highlighted area, the position corresponding to the target point data is determined as the position of the target same-name point data.

[0054] According to an embodiment of the present disclosure, when the client searches for the bounding box feature data corresponding to the same-name point data selected by the user, the point cloud data corresponding to the range occupied by the bounding box feature data may be highlighted. The user can select target point data within the highlighted point cloud data range. The client can automatically adjust the position of the same-name point data according to the position of the target point data and extract the feature features of the same-name point data.

[0055] Through the above embodiments of the present disclosure, before adjusting the position of the target same-name point data, highlighting the relevant area of the target position to be adjusted first can provide an additional guarantee for the user before selecting deviation adjustment. The user can further determine whether to adjust the position of the same-name point data according to the highlighted area, enabling selective deviation adjustment in combination with the proposed deviation adjustment position and user needs, which is beneficial to improving the user experience.

[0056] According to an embodiment of the present disclosure, determining the position corresponding to the target point data as the position of the target same-name point data in response to receiving an operation of selecting target point data in the highlighted area may include: generating a prompt message for selecting and determining the position of the target same-name point data to be adjusted in response to receiving an operation of selecting target point data in the highlighted area. In response to receiving an operation of selecting and determining the position of the target same-name point data to be adjusted, the position corresponding to the target point data is determined as the position of the target same-name point data.

[0057] According to an embodiment of the present disclosure, after the user selects target point data within the highlighted point cloud data range, the client may further generate a prompt message for further determining the position of the target same-name point data to be adjusted. In the case where the user determines that the position of the target same-name point data needs to be adjusted, the position of the target same-name point data can be automatically adjusted according to the position corresponding to the target point data.

[0058] Through the above embodiments of the present disclosure, after the user selects the target point data according to the highlighted area and before adjusting the position of the target same-name point data, a prompt message for the user to confirm the adjustment again can be added. By adding the condition for the user to confirm the adjustment, the situation of incorrect adjustment caused by the user's incorrect confirmation can be reduced, which is beneficial to improving the user experience.

[0059] According to an embodiment of the present disclosure, to visually confirm whether each same-name point data selected by the user is valid same-name point data, the point cloud data processing method may further include: in response to detecting that the position represented by the second position information is within the target area range, displaying first identification information at the position corresponding to the first position information. In response to detecting that the position represented by the second position information is outside the target area range, displaying second identification information at the position corresponding to the first position information.

[0060] According to an embodiment of the present disclosure, the first identification information and the second identification information may be different, and the differences between the two may include at least one of different colors, different shapes, different styles, etc. For example, the first identification information may be a solid dot, and the second identification information may be a hollow dot. After the user selects a certain same-name point data, if a solid dot is displayed on the same-name point number, it may indicate that the same-name point data is valid same-name point data, and it is not necessary to adjust the position of the same-name point data. The feature elements related to the same-name point data can be extracted and manually fused. After the user selects a certain same-name point data, if a hollow dot is displayed on the same-name point number, it may indicate that the same-name point data is invalid same-name point data. Taking the position corresponding to the same-name point data as the center, the range can be gradually expanded to search for the bounding box feature data corresponding to the same-name point data. Then, according to the found bounding box feature data, the position of the same-name point data is adjusted, and according to the found bounding box feature data, the feature elements related to the same-name point data are extracted, and then manual fusion can be performed.

[0061] Through the above embodiments of the present disclosure, each selected same-name point data can be identified, and different identifications can determine whether the corresponding same-name point data is valid, enabling the user to intuitively determine whether the position of the corresponding same-name point data needs to be adjusted, saving time for the entire adjustment process.

[0062] Figure 3 Schematically shows a schematic diagram of determining the position of valid same-name points according to an embodiment of the present disclosure.

[0063] As Figure 3 shown, the point cloud data displayed on the front end of the client 300 may represent the point cloud data obtained by the acquisition vehicle collecting the same arrow multiple times and automatically fusing through an algorithm. By Figure 3It can be obtained that there are ghosts in the fused point cloud data. For example, Figure 3 there are ghosts between the point cloud data composed of solid points and the point cloud data composed of hollow points in Figure 3 , and further manual fusion is required to eliminate the ghosts.

[0064] According to an embodiment of the present disclosure, as Figure 3 shown, at least one of the homologous point data 310, 320, etc. can be selected during manual fusion. For each selected homologous point data, feature extraction can be performed, and the obtained bounding box feature data includes, for example, bounding box feature data 311, 322. The bounding box feature data 311 corresponds to the homologous point data 310, and the bounding box feature data 322 corresponds to the homologous point data 320. It should be noted that before the user selects the homologous point data 310, 320, the bounding box feature data 311, 322 is not displayed at the front end of the client 300.

[0065] According to an embodiment of the present disclosure, in the case where the user selects the homologous point data 310, the position information of the homologous point data 310 can be recorded first. Then, it is determined whether there is bounding box feature data 311 corresponding to the homologous point data 310 within a region range centered on the position of the homologous point data 310 and with a predefined value as the radius. Combining Figure 3 shown, the client can determine that the position information of the homologous point data 310 matches the position information of the bounding box feature data 311 through determination. That is, it can be determined that there is bounding box feature data corresponding to the homologous point data 310 within a region range centered on the position of the homologous point data 310 and with a predefined value as the radius. In this case, after the user selects the homologous point data 310, the position corresponding to the bounding box feature data 311 can be displayed in the form of a solid bounding box at the front end of the client 300, indicating that the selected homologous point data 310 by the user is a valid homologous point and no position adjustment is required. In addition, the element features corresponding to the homologous point data 310 can also be extracted based on the bounding box feature data 311.

[0066] According to an embodiment of the present disclosure, in the case where the user selects the homologous point data 320, the position information of the homologous point data 320 can be recorded first. Then, it is determined whether there is bounding box feature data 322 corresponding to the homologous point data 320 within a region range 330 centered on the position of the homologous point data 320 and with a predefined value as the radius. Combining Figure 3 shown, the client can determine through determination that there is no bounding box feature data 322 within the region range 330. In this case, for example, the region range 330 can be further expanded to 340, and it is further determined whether there is bounding box feature data 322 corresponding to the homologous point data 320 within the region range 340. Combining Figure 3In the example shown, the client can determine that there is bounding box feature data 322 within the area range 340. Since the bounding box feature data 322 is not within the area range 330, it can be determined that there is a deviation in the position of the bounding box feature data 322 relative to the position of the homonymous point data 320. In this case, after the user selects the homonymous point data 320, the position corresponding to the bounding box feature data 322 can be displayed in the form of a dotted-line bounding box 321 at the front end of the client 300, indicating that the selected homonymous point data 320 by the user is an invalid homonymous point and needs to be position-adjusted. After determining that the selected homonymous point data 320 by the user is an invalid homonymous point, the user can control the client to continue searching for the bounding box feature data 322 by expanding the search range, and after finding the bounding box feature data 322, adjust the position of the homonymous point data 320 to the position corresponding to the bounding box feature data 322. As Figure 3 shown, the position of the homonymous point data 320 can be adjusted to the position located by the solid-line bounding box representing the position of the bounding box feature data 322. Thereafter, the feature corresponding to the homonymous point data 320 can be extracted based on the bounding box feature data 322.

[0067] Through the above embodiments of the present disclosure, a method for automatically correcting the position of homonymous points is implemented, which can automatically adjust the position of homonymous point data after the user selects invalid homonymous point data, and improve the success rate of the user selecting valid homonymous point data.

[0068] Figure 4 Schematically shows a block diagram of a point cloud data processing device according to an embodiment of the present disclosure.

[0069] As Figure 4 shown, the point cloud data processing device 400 includes a first determination module 410, a second determination module 420, and a third determination module 430.

[0070] The first determination module 410 is configured to determine first position information corresponding to the selected target homonymous point data in response to detecting an operation of selecting homonymous point data in the point cloud data.

[0071] The second determination module 420 is configured to determine second position information corresponding to the bounding box feature data, where the bounding box feature data corresponds to the target homonymous point data.

[0072] The third determination module 430 is configured to, in response to detecting that the position represented by the second position information is outside the target area range, determine the position of the target homonymous point data according to the second position information, where the target area includes the area determined according to the first position information.

[0073] According to an embodiment of the present disclosure, the third determination module includes a generation unit and a first determination unit.

[0074] A generating unit, configured to generate a prompt message for selecting automatic adjustment in response to detecting that the position represented by the second position information is outside the target area range.

[0075] A first determining unit, configured to determine the position of the target homologous point data according to the second position information in response to receiving an operation of selecting automatic adjustment.

[0076] According to an embodiment of the present disclosure, the third determining module includes a display unit and a second determining unit.

[0077] The display unit is configured to highlight the area occupied by the bounding box feature data corresponding to the second position information.

[0078] The second determining unit is configured to determine the position corresponding to the target point data as the position of the target homologous point data in response to receiving an operation of selecting the target point data in the highlighted area.

[0079] According to an embodiment of the present disclosure, the second determining unit includes a generating subunit and a third determining unit.

[0080] The generating subunit is configured to generate a prompt message for selecting and determining the position of the adjusted target homologous point data in response to receiving an operation of selecting the target point data in the highlighted area.

[0081] The third determining unit is configured to determine the position corresponding to the target point data as the position of the target homologous point data in response to receiving an operation of selecting and determining the position of the adjusted target homologous point data.

[0082] According to an embodiment of the present disclosure, the point cloud data processing device further includes a first display module and a second display module.

[0083] The first display module is configured to display first identification information at the position corresponding to the first position information in response to detecting that the position represented by the second position information is within the target area range.

[0084] The second display module is configured to display second identification information at the position corresponding to the first position information in response to detecting that the position represented by the second position information is outside the target area range.

[0085] According to an embodiment of the present disclosure, the point cloud data processing device further includes a fourth determining module.

[0086] The fourth determining module is configured to determine the position of the target homologous point data according to the first position information in response to detecting that the position represented by the second position information is within the target area range.

[0087] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0088] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the point cloud data processing method of the present disclosure.

[0089] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the point cloud data processing method of the present disclosure.

[0090] According to an embodiment of the present disclosure, a computer program product includes a computer program, and the computer program implements the point cloud data processing method of the present disclosure when executed by a processor.

[0091] Figure 5 FIG. shows a schematic block diagram of an exemplary electronic device 500 that can be used to implement embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, for example, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, for example, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely exemplary and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0092] As Figure 5 shown, the device 500 includes a computing unit 501, which can execute various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0093] Multiple components in device 500 are connected to I / O interface 505, including: input unit 506, such as a keyboard, mouse, etc.; output unit 507, such as various types of displays, speakers, etc.; storage unit 508, such as a disk, optical disc, etc.; and communication unit 509, such as a network card, modem, wireless communication transceiver, etc. Communication unit 509 allows device 500 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0094] Computing unit 501 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of computing unit 501 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Computing unit 501 executes the various methods and processes described above, such as the point cloud data processing method. For example, in some embodiments, the point cloud data processing method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed onto device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by computing unit 501, one or more steps of the point cloud data processing method described above can be executed. Alternatively, in other embodiments, computing unit 501 can be configured to execute the point cloud data processing method in any other suitable way (e.g., by means of firmware).

[0095] Various embodiments of the systems and techniques described above in this document 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), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: implemented in one or more computer programs, the one or more computer programs can be executed and / or interpreted on a programmable system including at least one programmable processor, the programmable processor can be a special or general-purpose programmable processor, can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0096] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing devices, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowchart and / or block diagram are implemented. The program codes can be executed entirely on the machine, partially on the machine, executed partially on the machine as an independent software package and partially on a remote machine, or executed entirely on a remote machine or server.

[0097] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0098] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and the input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0099] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.

[0100] A computer system can include a client and a server. The client and the server are generally far from each other and typically interact through a communication network. 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, a server of a distributed system, or a server incorporating a blockchain.

[0101] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and no limitation is imposed herein.

[0102] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. 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 disclosure shall be included within the protection scope of this disclosure.

Claims

1. A method for processing point cloud data, comprising: responding to an operation of detecting the selection of homonymous point data in the point cloud data displayed at the front end of the client, and determining first position information corresponding to the selected target homonymous point data; determining second position information corresponding to the bounding box feature data, wherein the bounding box feature data corresponds to the target homonymous point data and is not displayed at the front end of the client; responding to detecting that the position represented by the second position information is within the target area range, and indicating the homonymous point data as valid homonymous point data with first identification information; responding to detecting that the position represented by the second position information is outside the target area range, and indicating the homonymous point data as invalid homonymous point data with second identification information; wherein the target area includes the area determined according to the first position information, and at least one of the color, shape, and style of the first identification information and the second identification information is different; the indicating the homonymous point data as invalid homonymous point data with the second identification information includes: displaying the second position information in the form of a dotted bounding box at the front end of the client; the method further includes: responding to detecting that the position represented by the second position information is outside the target area range, and highlighting the area occupied by the bounding box feature data corresponding to the second position information; responding to receiving an operation of selecting target point data in the highlighted area, and displaying first prompt information for selecting and determining the position of adjusting the target homonymous point data on the client; responding to receiving an operation of determining the position of adjusting the target homonymous point data, and determining the position corresponding to the target point data as the position of the target homonymous point data; the method further includes: responding to detecting that the position represented by the second position information is outside the target area range, and generating second prompt information for selecting automatic deviation adjustment; responding to receiving an operation of selecting automatic deviation adjustment, and incrementing the range of the target area to obtain a new area range; responding to the new area range including the bounding box feature data, and automatically adjusting the first position information of the target homonymous point data according to the second position information of the bounding box feature data.

2. The method according to claim 1, further comprising: responding to detecting that the position represented by the second position information is within the target area range, and displaying the first identification information at the position corresponding to the first position information; and responding to detecting that the position represented by the second position information is outside the target area range, and displaying the second identification information at the position corresponding to the first position information.

3. The method according to any one of claims 1-2, further comprising: responding to detecting that the position represented by the second position information is within the target area range, and determining the position of the target homonymous point data according to the first position information.

4. A point cloud data processing apparatus, comprising: A first determination module, configured to determine first position information corresponding to the selected target same-name point data in response to detecting an operation of selecting same-name point data in the point cloud data displayed on the front end of the client; A second determination module, configured to determine second position information corresponding to the bounding box feature data, where the bounding box feature data corresponds to the target same-name point data and is not displayed on the front end of the client; A first identification module, configured to indicate, in response to detecting that the position characterized by the second position information is within the target area range, that the same-name point data is valid same-name point data with first identification information; A second identification module, configured to indicate, in response to detecting that the position characterized by the second position information is outside the target area range, that the same-name point data is invalid same-name point data with second identification information; wherein the target area includes the area determined according to the first position information, and at least one of the color, shape, and style of the first identification information and the second identification information is different; The second identification module is further configured to display the second position information in the form of a dotted-line bounding box on the front end of the client; The apparatus further includes: A first deviation adjustment module, configured to, in response to detecting that the position characterized by the second position information is outside the target area range, highlight the area occupied by the bounding box feature data corresponding to the second position information; in response to receiving an operation of selecting target point data in the highlighted area, display first prompt information for selecting and determining the position of the adjusted target same-name point data on the client; in response to receiving an operation of determining the position of the adjusted target same-name point data, determine the position corresponding to the target point data as the position of the target same-name point data; A second deviation adjustment module, configured to, in response to detecting that the position characterized by the second position information is outside the target area range, generate second prompt information for selecting automatic deviation adjustment; in response to receiving an operation of selecting automatic deviation adjustment, increment the range of the target area to obtain a new area range; in response to the new area range including the bounding box feature data, automatically adjust the first position information of the target same-name point data according to the second position information of the bounding box feature data.

5. The apparatus according to claim 4, further includes: A first display module, configured to display the first identification information at the position corresponding to the first position information in response to detecting that the position characterized by the second position information is within the target area range; and A second display module, configured to display the second identification information at the position corresponding to the first position information in response to detecting that the position characterized by the second position information is outside the target area range.

6. The apparatus according to any one of claims 4-5, further includes: A third determination module, configured to determine the position of the target same-name point data according to the first position information in response to detecting that the position characterized by the second position information is within the target area range.

7. An electronic device, including: At least one processor; and A memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method according to any one of claims 1-3.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are for causing the computer to execute the method according to any one of claims 1-3.

9. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-3.

Images