Point cloud data processing method, apparatus, device, storage medium, and program product

Abstract

This disclosure relates to point cloud data processing methods, apparatus, devices, storage media, and program products. The method includes: acquiring raw point cloud data of a target survey area and road width information during the acquisition of the raw point cloud data; wherein the road width information is width-related information of a one-way road or width-related information of a two-way road; determining a measurement width threshold for the target survey area based on the road width information; and filtering the raw point cloud data based on the measurement width threshold to generate target point cloud data. Thus, obtaining the measurement width threshold simplifies the filtering logic of the raw point cloud data, reducing the time consumption of point cloud data filtering, improving the efficiency and accuracy of filtering processing, and reducing the content of redundant information in the point cloud data, thereby reducing its interference with road information identification and improving the production efficiency and accuracy of subsequent high-precision maps.

Description

Technical Field

[0001] This disclosure relates to the field of map data technology, and in particular to a point cloud data processing method, apparatus, device, storage medium, and program product. Background Technology

[0002] Currently, the basic data for producing high-precision maps is mainly obtained by collecting point cloud data of roads using data collection vehicles equipped with high-precision LiDAR. During the collection process, due to the large scanning range of LiDAR, the collected road point cloud data often includes point cloud data of trees, buildings, and other objects outside the road area that are unrelated to road information. The presence of such data has two main drawbacks: firstly, it makes the processing of the collected point cloud data time-consuming and storage costs high, reducing the production efficiency of high-precision maps; secondly, because the shape of tree trunks is similar to that of traffic sign poles, it can easily affect the identification of traffic sign poles, reducing the accuracy of high-precision maps. Summary of the Invention

[0003] To address the technical problem that the production efficiency and accuracy of high-precision maps are low due to the inclusion of road-irrelevant information in the collected point cloud data, this disclosure provides a point cloud data processing method, apparatus, device, storage medium, and program product.

[0004] Firstly, this disclosure provides a point cloud data processing method, including:

[0005] Acquire the raw point cloud data of the target survey area and the road width information when collecting the raw point cloud data; wherein, the road width information is width-related information of a one-way road or width-related information of a two-way road;

[0006] Determine the measurement width threshold of the target measurement area based on the road width information;

[0007] The original point cloud data is filtered based on the measured width threshold to generate target point cloud data.

[0008] Secondly, this disclosure also provides a point cloud data processing apparatus, comprising:

[0009] The information acquisition module is used to acquire the original point cloud data of the target survey area and the road width information when acquiring the original point cloud data; wherein, the road width information is the width-related information of a one-way road or the width-related information of a two-way road;

[0010] A measurement width threshold determination module is used to determine the measurement width threshold of the target measurement area based on the road width information;

[0011] The point cloud data filtering module is used to filter the original point cloud data based on the measured width threshold to generate target point cloud data.

[0012] Thirdly, this disclosure also provides an electronic device, including:

[0013] A memory and a processor, wherein the memory is used to store executable instructions of the processor;

[0014] The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the point cloud data processing method provided in any embodiment of this disclosure.

[0015] Fourthly, this disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the point cloud data processing method provided in any embodiment of this disclosure.

[0016] Fifthly, this disclosure also provides a computer program product for executing the point cloud data processing method provided in any embodiment of this disclosure.

[0017] Compared with the prior art, the point cloud data processing technical solution provided in this disclosure has at least the following advantages: It can acquire road width information in real time when collecting raw point cloud data, determine the measurement width threshold corresponding to the road range based on this information, and then filter the raw point cloud data according to this measurement width threshold to obtain target point cloud data containing less road-irrelevant information. On the one hand, filtering point cloud data through the measurement width threshold simplifies the filtering logic, reduces the amount of point cloud data, and improves the efficiency of point cloud data preprocessing, thereby improving the production efficiency of subsequent high-precision maps. On the other hand, filtering irrelevant information such as trees can reduce their interference with the identification of road-related information, thereby improving the accuracy of subsequent high-precision maps. Attached Figure Description

[0018] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0019] Figure 1 A flowchart illustrating a point cloud data processing method provided in an embodiment of this disclosure;

[0020] Figure 2 A schematic diagram illustrating the principle of point cloud data filtering for bidirectional roads provided in this embodiment of the disclosure;

[0021] Figure 3 A schematic diagram illustrating the principle of point cloud data filtering for a one-way road, provided in an embodiment of this disclosure;

[0022] Figure 4 for Figure 1 A detailed flowchart of S130 in the point cloud data processing method is shown.

[0023] Figure 5 A flowchart illustrating another point cloud data processing method provided in this embodiment of the disclosure;

[0024] Figure 6 A flowchart illustrating yet another point cloud data processing method provided in this embodiment of the disclosure;

[0025] Figure 7 A flowchart illustrating yet another point cloud data processing method provided in this embodiment of the disclosure;

[0026] Figure 8 This is a schematic diagram of the structure of a point cloud data processing device provided in an embodiment of the present disclosure;

[0027] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. Detailed Implementation

[0028] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0029] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0030] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0031] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0032] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0033] In the high-precision map production process, a LiDAR on a data collection vehicle is used to scan the road survey area to obtain high-precision basic data. Because the LiDAR has a large scanning range, the raw point cloud data collected includes point cloud data of trees, buildings, and other objects outside the road area that are unrelated to road information.

[0034] To improve data processing efficiency and the accuracy of subsequent high-definition maps, the raw point cloud data can be filtered. In related technologies, after the high-definition map production end (such as the server corresponding to the map producer) obtains the raw point cloud data from the collection end (such as a data collection vehicle), it performs filtering preprocessing using machine learning algorithms based on computer vision or deep learning to identify and remove redundant point clouds such as trees and buildings. The preprocessed point cloud data is then used for high-definition map production. However, this filtering method consumes excessive computing resources and time due to the large amount of redundant point cloud data and the complexity of the algorithm, resulting in low filtering efficiency. Furthermore, the limited training accuracy of the machine learning algorithm leads to low filtering accuracy, resulting in a long, inefficient, and inaccurate map production process overall.

[0035] Based on the above, this disclosure provides a point cloud data processing method to obtain road width information when collecting raw point cloud data, and then determine the measurement width threshold when collecting the corresponding point cloud data based on the road width information, and remove redundant point cloud data that exceeds the measurement width threshold from the corresponding raw point cloud data. This greatly simplifies the processing logic of filtering raw point cloud data, reduces the time consumption of point cloud data filtering, and improves the efficiency and accuracy of filtering processing, thereby reducing the impact of redundant point cloud data on the identification of road-related information and improving the efficiency and accuracy of subsequent high-precision map production processes.

[0036] Figure 1This is a flowchart illustrating a point cloud data processing method provided in an embodiment of this disclosure. The point cloud data processing method provided in this embodiment is applicable to scenarios involving the acquisition of point cloud data for high-precision maps. This point cloud data processing method can be executed by a point cloud data processing device, which can be implemented using software and / or hardware and integrated into an electronic device with computing capabilities. This electronic device can be a device corresponding to the high-precision map production end, such as a laptop, desktop computer, or server; the electronic device can also be a device on a data acquisition vehicle, such as a point cloud data acquisition sensor like a LiDAR, or an onboard processor.

[0037] like Figure 1 As shown, the point cloud data processing method provided in this embodiment may include:

[0038] S110. Obtain the original point cloud data of the target survey area and the road width information when collecting the original point cloud data.

[0039] The target measurement area is the region where point cloud data needs to be collected, such as a one-way or two-way road within a certain area. Both one-way and two-way roads can be single-lane or multi-lane. The raw point cloud data is point cloud data directly acquired by sensors such as LiDAR. Road width information is related to the width of the road associated with point cloud data filtering; for example, it can be a road width value, or the lane width and the total number of lanes contained in the road. In this embodiment, based on whether the target measurement area contains one-way or two-way roads, the road width information can correspondingly be width-related information for one-way roads or width-related information for two-way roads. Specifically, the electronic device can acquire the raw point cloud data of the target measurement area from sensors such as LiDAR installed on the data acquisition vehicle. Furthermore, it can obtain the original road width information of the road segment at the time of acquiring the raw point cloud data from a navigation map or the cloud.

[0040] In one example, when the electronic device is located in a data acquisition vehicle, it can simultaneously read road width information at the corresponding location on the navigation map while the sensor acquires raw point cloud data.

[0041] For example, see Figure 2 For two-way roads, the electronic device can simultaneously acquire the raw point cloud data and obtain the width information of the left and right sides of the road segment it is traveling on from the navigation map. For one-way roads, the electronic device can obtain the road width information of the road on the side of the travel direction.

[0042] In another example, when the electronic device is the same as the device used for producing high-precision maps, the data collection vehicle can simultaneously collect raw point cloud data and read the road width information at the corresponding location on the navigation map, then associate and store this information with the raw point cloud data before uploading it. In this way, the electronic device can receive the raw point cloud data uploaded by the data collection vehicle along with the matching road width information.

[0043] In another example, when the electronic device corresponds to the high-precision map production terminal, the data collection vehicle can collect raw point cloud data and upload it to the electronic device. After receiving the raw point cloud data, the electronic device can extract the road width information of the corresponding location from a relatively low-precision standard-precision map (such as a navigation map) or a database based on the location information in the raw point cloud data.

[0044] In some embodiments, after S110 and before S120, the point cloud data processing method further includes: acquiring the driving lane of the data acquisition vehicle when the road width information includes at least the lane width; correcting the road width information based on the driving lane and the lane width in the road width information; and updating the road width information using the corrected road width information.

[0045] Specifically, considering that the driving direction of the data acquisition vehicle is roughly consistent with the road direction, the point cloud data filtering in this embodiment is based on the driving trajectory of the data acquisition vehicle. However, the data acquisition vehicle may not always be driving in the edge lane of the driving direction segmentation mark adjacent to its driving direction. Therefore, when filtering according to the original road width information initially obtained, the range of retained data will be too large, resulting in a relatively large amount of data in the filtered original point cloud data (i.e., target point cloud data) and a relatively large amount of redundant point cloud data.

[0046] For example, see Figure 3 When filtering based on the original road width information obtained initially, using the data collection vehicle center as a reference, the retention range of the corresponding point cloud data is likely to include some redundant point cloud data such as trees and buildings. Therefore, there is still a lot of redundant point cloud data in the target point cloud data.

[0047] Based on the above, when the navigation map has lane-level positioning and navigation capabilities, the electronic device can also acquire the lane the data collection vehicle is traveling in real time (i.e., the driving lane). Then, based on the driving lane and the lane width information contained in the road width information, the road width information participating in the point cloud filtering process is calculated more accurately, and the calculated result is used to replace the initially acquired road width information, completing the correction and update of the road width information. This can improve the accuracy of the road width information to a certain extent, thereby further reducing the number of irrelevant elements such as trees and buildings in the target point cloud data obtained by subsequent filtering, and further improving the accuracy of subsequent point cloud data filtering.

[0048] In one example, the above-mentioned correction of road width information based on driving lanes and lane widths includes: determining the number of lane targets covered by the target measurement area based on the total number of lanes contained in the driving lanes and road width information; and correcting the road width information by using the product of the number of lane targets and the lane width.

[0049] Specifically, see Figure 3 The data collection vehicle is traveling in the second lane of a one-way road, which contains a total of 3 lanes. Based on the vehicle's trajectory along the lane centerline, the number of lane targets covered by the target area is determined to be 1.5. Then, the product of the number of lane targets and the lane width is calculated, i.e., lane width * 1.5, which gives the corrected road width information.

[0050] In another example, the above-mentioned correction of road width information based on driving lanes and lane width includes: determining the number of lanes not covered by the target measurement area based on driving lanes; and correcting the road width information using the difference between the road width information and the product of the number of lanes to be discarded and the lane width.

[0051] Specifically, continue with Figure 3 For example, if the number of lanes not covered by the target area is determined to be 1.5, then the width to be discarded is the lane width * 1.5. Then, the difference between the original road width information and the discarded width can be calculated, i.e., the original road width information - lane width * 1.5, which is the corrected road width information.

[0052] See Figure 2 When the target survey area is a two-way road, the corrected road widths of both sides can be calculated using the method described in the example above, thus obtaining the corrected right road width information and the corrected left road width information shown in the figure.

[0053] S120. Determine the measurement width threshold of the target measurement area based on road width information.

[0054] The measurement width threshold refers to the critical value of the width range of valid point cloud data related to the road. Point cloud data within this critical value is retained, while point cloud data outside this critical value is discarded.

[0055] Specifically, the electronic device can determine the measurement width threshold based on the road width information obtained above.

[0056] In some embodiments, the electronic device can directly determine the road width information as the measurement width threshold. For example, in target measurement areas where there are no traffic signs around the road, or in target measurement areas where traffic signs are very close to the road edge, the road width information can be determined as the measurement width threshold. This can improve the efficiency of point cloud filtering to some extent.

[0057] In other embodiments, considering that road width information may not cover traffic signs around the road, the electronic device can first widen the road width information to a certain extent, and determine the widened road width information as the measurement width threshold, so that the measurement width threshold can better cover traffic signs but not contain too much redundant information such as trees and buildings, thereby further improving the accuracy of point cloud data filtering.

[0058] S130. Filter the original point cloud data based on the measurement width threshold to generate target point cloud data.

[0059] Specifically, electronic devices can use a measurement width threshold to filter the raw point cloud data to remove redundant point cloud data beyond the measurement width threshold and obtain the target point cloud data.

[0060] See Figure 3 If the target measurement area is a one-way road, then redundant point cloud data that is outside the measurement width threshold in the original point cloud data can be removed to obtain the target point cloud data.

[0061] See Figure 2 If the target measurement area is a two-way road, the above steps will produce a right-side measurement threshold and a left-side measurement threshold. Then, the original point cloud data of the corresponding side will be filtered according to the right-side measurement threshold and the left-side measurement threshold to obtain the target point cloud data.

[0062] This disclosure provides a point cloud data processing method, which includes: acquiring raw point cloud data of a target survey area and road width information at the time of acquiring the raw point cloud data; determining a measurement width threshold for the target survey area based on the road width information; and filtering the raw point cloud data based on the measurement width threshold to generate target point cloud data. Thus, obtaining the measurement width threshold simplifies the filtering logic of the raw point cloud data, reducing the time consumption of point cloud data filtering, improving the efficiency and accuracy of filtering processing, and reducing the content of redundant information in the point cloud data, thereby reducing its interference with road information recognition and improving the production efficiency and accuracy of subsequent high-precision maps.

[0063] In some embodiments, it is possible to Figure 1 The S130 shown is further refined. Specifically, the electronic device can traverse the raw point cloud data and apply the same filtering process to each traversed point. This filtering process can be found in [reference needed]. Figure 4 .like Figure 4 As shown, S130's "filtering the original point cloud data based on the measurement width threshold to generate target point cloud data" includes:

[0064] S431. Project the points in the original point cloud data onto the ground and determine the vertical distance between the ground projection points and the trajectory of the data acquisition vehicle.

[0065] Among them, the vehicle trajectory is the trajectory of the vehicle during the point cloud data acquisition process, which can be obtained through relevant sensors on the vehicle.

[0066] Specifically, the electronic device projects the points it traverses onto the ground to obtain the corresponding ground projection points. Then, it calculates the perpendicular distance between the ground projection point and the trajectory of the data acquisition vehicle.

[0067] S432. Compare the perpendicular distance with the measurement width threshold.

[0068] Specifically, the electronic device compares the obtained perpendicular distance with the measurement width threshold. If the perpendicular distance is less than or equal to the measurement width threshold, then S433 is executed; otherwise, S434 is executed.

[0069] S433. If the perpendicular distance is less than or equal to the measurement width threshold, then retain the point in the original point cloud data that corresponds to the perpendicular distance.

[0070] Specifically, if the vertical distance is less than or equal to the measurement width threshold, it means that the above-mentioned ground projection point is within the effective measurement range, and the point traversed above corresponding to the vertical distance is retained.

[0071] S433. If the perpendicular distance is greater than the measurement width threshold, then remove the points corresponding to the perpendicular distance from the original point cloud data.

[0072] Specifically, if the electronic device determines that the vertical distance is greater than the measurement width threshold, it means that the above-mentioned ground projection point is outside the effective measurement range, and the points traversed above corresponding to the vertical distance are removed from the original point cloud data.

[0073] In some embodiments, when the electronic device is a device on a data collection vehicle, such as... Figure 5 As shown, based on the point cloud data processing method illustrated in any of the above embodiments, additional steps related to uploading the target point cloud data can be added. See also Figure 5 The point cloud data processing method includes:

[0074] S510. Obtain the original point cloud data of the target survey area and the road width information when collecting the original point cloud data.

[0075] S520. Determine the measurement width threshold of the target measurement area based on road width information.

[0076] S530: Filter the original point cloud data based on the measurement width threshold to generate target point cloud data.

[0077] S540: Upload the target point cloud data to the high-precision map production terminal.

[0078] Specifically, the electronic device uploads the target point cloud data to the high-precision map production terminal, so that the high-precision map production terminal can perform the post-processing required for high-precision map generation on the target point cloud data.

[0079] The point cloud data processing method provided in the above embodiments of this disclosure filters the raw point cloud data at the acquisition vehicle end using a readily obtainable measurement width threshold. This not only ensures the data processing performance of the acquisition vehicle end and guarantees data filtering efficiency, but also reduces the number of irrelevant elements such as trees and buildings during the point cloud data acquisition process. This reduces the amount of data transmitted during point cloud data upload and its storage cost at the high-precision map production end, thereby saving the relatively complex point cloud data filtering process at the high-precision map production end and further improving the efficiency of high-precision map production.

[0080] In some embodiments, such as Figure 6 As shown, based on the point cloud data processing method illustrated in any of the above embodiments, further improvements can be made to... Figure 1 The S120 shown is further refined. See [link / reference] Figure 6 The point cloud data processing method includes:

[0081] S610. Obtain the original point cloud data of the target survey area and the road width information when collecting the original point cloud data.

[0082] S620. The sum of the road width information and the initial buffer information is determined as the measurement width threshold.

[0083] The initial buffer information is a pre-set distance value used to correct the road width information.

[0084] In this embodiment of the disclosure, the initial buffer zone information can be determined based on the location of traffic signs. For example, the distances between traffic signs and road edges on multiple different types of roads can be statistically analyzed, and the resulting statistical values ​​can be used as the initial buffer zone information. Alternatively, the initial buffer zone information can be determined according to the values ​​specified in the standard document upon which the traffic signs are based.

[0085] Specifically, due to map data deviations in the high-precision map (such as insufficient map accuracy), outdated road width information, and positioning deviations of the data collection vehicle, filtering directly based on road width information may result in the incorrect removal of point cloud data for some road surfaces and traffic signs, leading to incomplete target point cloud data and the inability to build a high-precision map.

[0086] Therefore, this embodiment introduces initial buffer information based on the original road width information to increase the measurement width threshold. That is, the electronic device can superimpose the road width information and the initial buffer information, and use the sum as the measurement width threshold.

[0087] For example, when a navigation map has lane-level positioning and navigation capabilities, the updated road width information, updated with corrected road width information, can be overlaid with the initial buffer information to obtain a measurement width threshold, thereby further improving the accuracy of the measurement width threshold. When the navigation map does not have lane-level positioning capabilities, the original road width information can be directly added to the initial buffer information to obtain the measurement width threshold.

[0088] S630. Filter the raw point cloud data based on the measurement width threshold to generate target point cloud data.

[0089] The point cloud data processing method provided in the above embodiments of this disclosure expands the measurement width threshold by introducing initial buffer information, so that the measurement width threshold can cover a slightly larger area. This ensures that while reducing redundant point cloud data such as distant trees and buildings, it retains traffic signs located at the road edge to the greatest extent, reducing the probability of road elements being erroneously removed, thereby further improving the accuracy of point cloud data filtering and further improving the accuracy of high-precision maps.

[0090] In some embodiments, such as Figure 7 As shown, based on the point cloud data processing method illustrated in any of the above embodiments, further improvements can be made to... Figure 1The S120 shown is further refined. See [link / reference] Figure 7 The point cloud data processing method includes:

[0091] S710. Obtain the original point cloud data of the target survey area and the road width information when collecting the original point cloud data.

[0092] S720. Determine the confidence level of road width information.

[0093] Specifically, given that road width information may have low accuracy due to map data deviations in the precision map (such as insufficient map accuracy) or failure to update road width information in a timely manner, this embodiment introduces a confidence level to evaluate the reliability of road width information and adjust the initial buffer information based on the evaluation results.

[0094] If the data related to the refined map contains information on road confidence levels, then that confidence level can be directly obtained from the refined map. If the data related to the refined map does not contain such information, then the confidence level can be indirectly determined from the attribute information of the refined map.

[0095] In one example, S720 includes: obtaining source information and update time of road width information; determining confidence level based on the authority of the source information, source weight, freshness of update time, and freshness weight.

[0096] Specifically, in this example, the confidence level can be determined based on the source information and update time attributes of the road width information in the high-precision map. The source information refers to the provider of the road width information in the high-precision map, such as the government, the high-precision map producer corresponding to the data collection vehicle, other high-precision map producers, crowdsourcing users, etc. The update time is the time of the most recent update of the road width information in the high-precision map.

[0097] The electronic device retrieves the source information and update time of road width data from a high-precision map or its corresponding cloud platform. Then, based on a pre-defined authority level for the source information, it determines the authority of the road width data. For example, the authority levels decrease sequentially from government, the high-precision map producer corresponding to the data collection vehicle, other high-precision map producers, and crowdsourced users. Furthermore, the electronic device determines the freshness of the road width information based on the time difference between the update time and the current system time. Finally, using a pre-defined weighting of the source information's proportion in the confidence score (i.e., source weight) and the pre-defined weighting of the update time's proportion in the confidence score (i.e., freshness weight), a weighted sum is calculated to determine the confidence level of the road width information.

[0098] In one example, considering that the authority of the source information is more important than the freshness of the update time, the source weight can be set to be greater than the freshness weight.

[0099] S730. Determine buffer correction information based on confidence level, and correct the initial buffer information based on the buffer correction information.

[0100] Among them, the buffer correction information is used to correct the initial buffer information, which can be a distance value or a correction coefficient.

[0101] Specifically, the higher the confidence level of road width information, the higher the reliability and accuracy of that information, and the lower the likelihood of needing correction. Therefore, there is an inverse relationship between buffer correction information and confidence level. This inverse relationship can be implemented as a specific mathematical formula or as a numerical mapping table.

[0102] The electronic device can determine the buffer correction information corresponding to the road width information based on the confidence level and the aforementioned inverse relationship. Then, it uses this buffer correction information to correct the initial buffer information. For example, when the buffer correction information is a distance value, the buffer correction information and the initial buffer information can be added together to obtain the corrected initial buffer information; when the buffer correction information is a correction coefficient, the buffer correction information and the initial buffer information can be multiplied together to obtain the corrected initial buffer information.

[0103] For example, if road width information cannot be found during the above process, the confidence level is 0, and the buffer correction information can be infinite. Therefore, the corrected initial buffer information is also infinite, and point cloud data is not filtered subsequently. If the obtained road width information is highly authoritative (e.g., provided by the government) and has high freshness, the confidence level is 1, and the buffer correction information can be 0, meaning no correction is needed. In this case, the corrected initial buffer information becomes the set initial buffer information, and subsequent point cloud data filtering is performed directly based on the road width information and the initial buffer information.

[0104] S740. The sum of the road width information and the corrected initial buffer information is determined as the measurement width threshold.

[0105] Specifically, the electronic device can overlay road width information with the corrected initial buffer information and use the sum as the measurement width threshold.

[0106] For example, when a navigation map has lane-level positioning and navigation capabilities, the corrected road width information can be superimposed with the corrected initial buffer information to obtain the measurement width threshold, thereby further improving the accuracy of the measurement width threshold.

[0107] See Figure 3The electronic device can obtain the measurement width threshold shown in the example with the solid arrow line to filter the raw point cloud data more accurately. This not only retains more effective point cloud data of road-related elements, but also filters out point cloud data of road-irrelevant elements such as trees and buildings to a large extent, thereby further improving the accuracy of the target point cloud data.

[0108] See Figure 2 For two-way lanes, the electronic device can obtain the left and right measurement width thresholds (examples with solid arrows), and then the original point cloud data of the corresponding road side can be filtered using the left and right measurement width thresholds respectively.

[0109] For example, when the navigation map lacks lane-level positioning capabilities, the original road width information can be directly added to the corrected initial buffer zone information to obtain the measurement width threshold, thereby further improving the accuracy of the measurement width threshold to some extent. See also Figure 3 The electronic device can obtain the measured width threshold of the example with arrowed dashed lines and use it for subsequent filtering of the raw point cloud data.

[0110] S750 filters the raw point cloud data based on the measurement width threshold to generate target point cloud data.

[0111] Figure 8 This is a schematic diagram of a point cloud data processing device provided in an embodiment of the present disclosure. The device can be implemented using software and / or hardware and can be integrated into any electronic device with a certain computing power.

[0112] like Figure 8 As shown, the point cloud data processing apparatus 800 provided in this embodiment may include:

[0113] The information acquisition module 810 is used to acquire the original point cloud data of the target survey area and the road width information when acquiring the original point cloud data; wherein, the road width information is the width-related information of a one-way road or the width-related information of a two-way road.

[0114] The measurement width threshold determination module 820 is used to determine the measurement width threshold of the target measurement area based on road width information.

[0115] The point cloud data filtering module 830 is used to filter the raw point cloud data based on the measurement width threshold to generate target point cloud data.

[0116] In some embodiments, the point cloud data processing device 800 further includes a data upload module, used for:

[0117] With the target point cloud data stored at the acquisition end, after filtering the original point cloud data based on the measurement width threshold to generate the target point cloud data, the target point cloud data is uploaded to the high-precision map production end.

[0118] In some embodiments, the width threshold determination module 820 is specifically used for:

[0119] The sum of the road width information and the initial buffer zone information is used to determine the measurement width threshold; where the initial buffer zone information is determined based on the location of traffic signs.

[0120] In some embodiments, the width threshold determination module 820 includes:

[0121] The confidence level determination submodule is used to determine the confidence level of road width information;

[0122] The initial buffer information correction submodule is used to determine buffer correction information based on confidence level, and to correct the initial buffer information based on the buffer correction information;

[0123] The measurement width threshold determination submodule is used to determine the measurement width threshold by summing the road width information with the corrected initial buffer information.

[0124] Furthermore, the confidence level determination submodule is specifically used for:

[0125] Source information and update time for obtaining road width information;

[0126] The confidence level is determined based on the authority of the source information, the source weight, the freshness of the update time, and the freshness weight.

[0127] In some embodiments, the point cloud data processing device 800 further includes a road width information updating module, used for:

[0128] If the road width information includes at least the lane width, the driving lane of the data acquisition vehicle is obtained before determining the measurement width threshold of the target measurement area based on the road width information;

[0129] Based on the driving lane and lane width, the road width information is corrected, and the corrected road width information is used to update the road width information.

[0130] Furthermore, the road width information update module is specifically used for:

[0131] Based on the total number of lanes contained in the driving lane and road width information, determine the number of lane targets covered by the target measurement area;

[0132] The road width information is corrected by multiplying the number of lane targets by the lane width.

[0133] Alternatively, the road width information update module is specifically used for:

[0134] Based on the driving lane, determine the number of lanes to be discarded that are not covered by the target measurement area;

[0135] The road width information is corrected by using the difference between the road width information and the product of the number of lanes discarded and the lane width.

[0136] In some embodiments, the point cloud data filtering module 830 is specifically used for:

[0137] Project the points in the original point cloud data onto the ground and determine the vertical distance between the ground projection points and the trajectory of the data acquisition vehicle.

[0138] If the perpendicular distance is less than or equal to the measurement width threshold, the point corresponding to the perpendicular distance in the original point cloud data is retained.

[0139] If the perpendicular distance is greater than the measurement width threshold, the point corresponding to the perpendicular distance is removed from the original point cloud data.

[0140] The point cloud data processing apparatus provided in this disclosure can execute any of the point cloud data processing methods provided in this disclosure, and has the corresponding functional modules and beneficial effects for executing the method. Content not described in detail in the apparatus embodiments of this disclosure can be referred to the description in any method embodiment of this disclosure.

[0141] This disclosure also provides an electronic device that may include a processor and a memory, the memory being used to store executable instructions. The processor may be used to read the executable instructions from the memory and execute the executable instructions to implement the point cloud data processing method in any of the above embodiments of this disclosure.

[0142] The electronic device in this embodiment can be a sensor on the data acquisition vehicle or a vehicle control device, or it can be a device such as a desktop computer or server corresponding to the high-precision map production end.

[0143] Figure 9 This is a schematic diagram of an electronic device provided in an embodiment of this disclosure, used to exemplify an electronic device implementing the point cloud data processing method in any embodiment of this disclosure, and should not be construed as a specific limitation on the embodiments of this disclosure. That is, although Figure 9 An electronic device 900 with various devices / components is shown, but it should be understood that it is not required to implement or have all of the devices / components shown, and more or fewer devices / components may be implemented or have instead.

[0144] like Figure 9As shown, the electronic device 900 may include a processor (e.g., a central processing unit, graphics processor, etc.) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage device 908 into a random access memory (RAM) 903. The RAM 903 also stores various programs and data required for the operation of the electronic device 900. The processor 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0145] Optionally, the following devices may be connected to I / O interface 905: input devices 906 including, for example, touch screens, touchpads, keyboards, mice, cameras, LiDAR, microphones, accelerometers, gyroscopes, etc.; output devices 907 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 908 including, for example, magnetic tapes, hard disks, etc.; and communication devices 909. Communication device 909 allows electronic device 900 to communicate wirelessly or wiredly with other devices to exchange data.

[0146] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the point cloud data processing method provided in any of the embodiments of this disclosure. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 909, or installed from a storage device 908, or installed from a ROM 902. When the computer program is executed by the processor 901, it can perform the functions defined in the point cloud data processing method provided in any embodiment of this disclosure.

[0147] It should be noted that the computer-readable medium described in this disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0148] In some implementations, the client and server can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0149] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0150] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the point cloud data processing method provided in any embodiment of this disclosure.

[0151] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on a computer, partially on a computer, as a standalone software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0152] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0153] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0154] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0155] In the context of this disclosure, a computer-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium can be, 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 computer-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 fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0156] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0157] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0158] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A point cloud data processing method, characterized by, include: Acquire the raw point cloud data of the target survey area and the road width information when collecting the raw point cloud data; wherein, the road width information is width-related information of a one-way road or width-related information of a two-way road; Determining the measurement width threshold of the target measurement area based on the road width information includes: summing the road width information and initial buffer information to determine the measurement width threshold; wherein the initial buffer information is determined based on the position of traffic signs; The original point cloud data is filtered based on the measured width threshold to generate target point cloud data.

2. The method according to claim 1, wherein, When the target point cloud data is stored at the acquisition end, after filtering the original point cloud data based on the measurement width threshold to generate the target point cloud data, the method further includes: The target point cloud data is uploaded to the high-precision map production terminal.

3. The method according to claim 1, wherein, The step of determining the measurement width threshold of the target measurement area based on the road width information includes: Determine the confidence level of the road width information; Buffer correction information is determined based on the confidence level, and the initial buffer information is corrected based on the buffer correction information; The sum of the road width information and the corrected initial buffer information is determined as the measured width threshold.

4. The method according to claim 3, wherein, The confidence level for determining the road width information includes: Obtain the source information and update time of the road width information; The confidence level is determined based on the authority of the source information, the source weight, the freshness of the update time, and the freshness weight.

5. The method according to any one of claims 1 to 4, wherein, When the road width information includes at least the lane width, the method further includes, before determining the measurement width threshold of the target measurement area based on the road width information: Obtain the driving lane of the data collection vehicle; Based on the driving lane and the lane width, the road width information is corrected, and the corrected road width information is used to update the road width information.

6. A point cloud data processing device, characterized in that, include: The information acquisition module is used to acquire the original point cloud data of the target survey area and the road width information when acquiring the original point cloud data; wherein, the road width information is the width-related information of a one-way road or the width-related information of a two-way road; A measurement width threshold determination module is used to determine a measurement width threshold for the target measurement area based on the road width information; including: summing the road width information and initial buffer information to determine the measurement width threshold; wherein the initial buffer information is determined based on the position of traffic signs; The point cloud data filtering module is used to filter the original point cloud data based on the measured width threshold to generate target point cloud data.

7. An electronic device, characterized in that, include: A memory and a processor, wherein the memory is used to store executable instructions of the processor; The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the point cloud data processing method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program thereon, characterized in that, When the computer program is executed by the processor, it implements the point cloud data processing method as described in any one of claims 1 to 5.

9. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, performs the point cloud data processing method according to any one of claims 1 to 5.

Images