A method, device, equipment and computer readable storage medium for mapping

Abstract

The present disclosure relates to a mapping method, device, equipment and computer readable storage medium, the present disclosure receives a plurality of data units sent by a vehicle to receive data in segments, each data unit includes a two-dimensional image of current point cloud data and feature point cloud data in the current point cloud data, which reduces the transmission amount of data; the two-dimensional image of the current point cloud data and the historical image corresponding to the two-dimensional image of the current point cloud data are fused to obtain a fused image, so that the accuracy of the image is improved; the feature point cloud data in the current point cloud data is optimized in pose to obtain an optimized feature point cloud position, the position of the fused image is adjusted according to the optimized feature point cloud position to obtain a target image, so that the target image obtained is more accurate, and the mapping method can update the target image locally, saves time, reduces labor cost and improves mapping efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of mapping technology, and in particular to a mapping method, apparatus, device and computer-readable storage medium. Background Technology

[0002] A point cloud is a map represented by a set of discrete points. A point cloud itself consists of hundreds or thousands of points that are not logically independent of each other, exhibiting sparsity and disorder. When people see a cluster of point clouds, they can identify the objects they represent based on years of experience and observation.

[0003] Normally, cloud-based mapping is based on the full amount of point cloud data. However, due to bandwidth and traffic limitations, vehicles cannot transmit the full amount of point cloud data back. Summary of the Invention

[0004] To address the aforementioned technical problems, this disclosure provides a method, apparatus, device, and computer-readable storage medium for mapping, thereby reducing the transmission of mapping data and improving the accuracy of mapping.

[0005] In a first aspect, embodiments of this disclosure provide a mapping method, including:

[0006] The system receives multiple data units sent by the vehicle. Each data unit includes a two-dimensional image of the current point cloud data and feature point cloud data in the current point cloud data. The current point cloud data is the point cloud data collected by the vehicle while it is traveling on a route of a preset length.

[0007] For each of the plurality of data units, a historical image corresponding to the two-dimensional image of the current point cloud data is obtained. The historical image is a two-dimensional image of the historical point cloud data. The current point cloud data and the historical point cloud data correspond to the same route of a preset length.

[0008] The two-dimensional image of the current point cloud data and the corresponding historical image of the current point cloud data are fused to obtain the fused image;

[0009] The pose of the feature point cloud data in the current point cloud data is optimized to obtain the optimized feature point cloud position.

[0010] The position of the fused image is adjusted based on the optimized feature point cloud position to obtain the target image.

[0011] In some embodiments, the two-dimensional image of the current point cloud data is a two-dimensional image obtained by flattening the current point cloud data, and the two-dimensional image is used to characterize the intensity and height information of the target object corresponding to the current point cloud data.

[0012] In some embodiments, after receiving multiple data units transmitted by the vehicle, the method further includes:

[0013] The feature point cloud data is sorted according to the first location information of the feature point cloud data to obtain the feature point cloud data in the point cloud data collected during the vehicle's travel on the preset trajectory, wherein the preset trajectory includes multiple routes of the preset length.

[0014] In some embodiments, the method further includes:

[0015] The feature point cloud data collected during the vehicle's journey along a preset trajectory is optimized to obtain the second location information of the feature point cloud data.

[0016] In some embodiments, the feature point cloud data in the point cloud data collected during the vehicle's travel on a preset trajectory is optimized, including:

[0017] Based on the information output by the vehicle's inertial measurement unit during the vehicle's journey along the preset trajectory, the feature point cloud data in the point cloud data collected during the vehicle's journey along the preset trajectory is pre-integrated.

[0018] In some embodiments, the two-dimensional image of the current point cloud data and the historical image corresponding to the two-dimensional image of the current point cloud data are fused to obtain a fused image, including:

[0019] Based on the second location information of the feature point cloud data, the two-dimensional image of the current point cloud data is superimposed onto the historical image corresponding to the two-dimensional image of the current point cloud data to obtain the fused image.

[0020] In some embodiments, the method further includes:

[0021] The target image is segmented, and the segmented target image is output to a third-party platform, which is used to annotate the segmented target image.

[0022] Secondly, embodiments of this disclosure provide a mapping apparatus, comprising:

[0023] The receiving module is used to receive multiple data units sent by the vehicle. Each data unit includes a two-dimensional image of the current point cloud data and feature point cloud data in the current point cloud data. The current point cloud data is the point cloud data collected by the vehicle while traveling on a route of a preset length.

[0024] The acquisition module is used to acquire a historical image corresponding to the two-dimensional image of the current point cloud data for each of the plurality of data units. The historical image is a two-dimensional image of the historical point cloud data, and the current point cloud data and the historical point cloud data correspond to the same route of a preset length.

[0025] The fusion module is used to fuse the two-dimensional image of the current point cloud data and the historical image corresponding to the two-dimensional image of the current point cloud data to obtain the fused image;

[0026] The optimization module is used to optimize the pose of the feature point cloud data in the current point cloud data to obtain the optimized feature point cloud position.

[0027] The adjustment module is used to adjust the position of the fused image according to the optimized feature point cloud position to obtain the target image.

[0028] Thirdly, embodiments of this disclosure provide an electronic device, including:

[0029] Memory;

[0030] Processor; and

[0031] Computer programs;

[0032] The computer program is stored in the memory and configured to be executed by the processor to implement the method as described in the first aspect.

[0033] Fourthly, embodiments of this disclosure provide a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the method described in the first aspect.

[0034] Fifthly, embodiments of this disclosure also provide a computer program product comprising a computer program or instructions which are executed by a processor to implement the method described in the first aspect.

[0035] The mapping method, apparatus, device, and computer-readable storage medium provided in this disclosure receive data in segments by receiving multiple data units sent by a vehicle. Each data unit includes a two-dimensional image of the current point cloud data and feature point cloud data from the current point cloud data. The current point cloud data is point cloud data collected by the vehicle while traveling along a route of a preset length, thus reducing the amount of data transmission. For each of the multiple data units, a historical image corresponding to the two-dimensional image of the current point cloud data is obtained. The historical image is a two-dimensional image of historical point cloud data. The current point cloud data and the historical point cloud data correspond to the same route of a preset length, thus clarifying the current point cloud data. The method involves: 1) determining the position of a 2D image of the current point cloud data within a historical image; 2) fusing the 2D image of the current point cloud data with the corresponding historical image to obtain a fused image, thus improving image accuracy; 3) optimizing the pose of the feature point cloud data in the current point cloud data to obtain optimized feature point cloud positions; 4) adjusting the position of the fused image based on the optimized feature point cloud positions to obtain the target image; 5) determining the position of the fused image and making further adjustments to make the target image more accurate. This mapping method allows for local updates of the target image, saving time, reducing labor costs, improving mapping efficiency, and enhancing user experience. Attached Figure Description

[0036] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0037] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 A flowchart of a mapping method provided in this embodiment of the disclosure;

[0039] Figure 2 This is a schematic diagram of data unit segmentation provided in an embodiment of the present disclosure;

[0040] Figure 3 This is a schematic diagram of data unit segmentation provided in an embodiment of the present disclosure;

[0041] Figure 4 This is a schematic diagram of a two-dimensional image of the current point cloud data and a corresponding two-dimensional image of the historical point cloud data provided in an embodiment of this disclosure;

[0042] Figure 5This is a schematic diagram of data unit fusion provided in an embodiment of the present disclosure;

[0043] Figure 6 A schematic diagram of the structure of the drawing apparatus provided in the embodiments of this disclosure;

[0044] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0045] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0046] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0047] This disclosure provides a method for mapping, which will be described below with reference to specific embodiments.

[0048] Figure 1 This is a flowchart illustrating a mapping method provided in this embodiment. This method can be applied to cloud-based mapping scenarios; it is understood that the mapping method provided in this embodiment can also be applied to other scenarios. The following describes... Figure 1 The method for creating the map shown is described below, and the specific steps involved are as follows:

[0049] S101. Receive multiple data units sent by the vehicle. Each data unit includes a two-dimensional image of the current point cloud data and feature point cloud data in the current point cloud data. The current point cloud data is point cloud data collected by the vehicle while traveling on a route of a preset length.

[0050] Radar (radio detection and ranging), also known as radio positioning, is an electronic device that uses radio waves to detect targets and determine their spatial location. It emits electromagnetic waves to illuminate a target and receives its echo, thereby obtaining information such as the distance from the target to the electromagnetic wave emission point, the rate of change of distance (radial velocity), azimuth, and altitude.

[0051] The principle of radar velocity measurement is based on the Doppler effect, which occurs when there is relative motion between the radar and the target. The frequency of the target echo received by the radar differs from the radar's transmitted frequency; the difference between the two is called the Doppler frequency. The principle of radar distance measurement is based on measuring the time difference between the transmitted pulse and the echo pulse. Since electromagnetic waves travel at the speed of light, this time difference can be used to calculate the precise distance between the radar and the target.

[0052] Point cloud, in reverse engineering, is a collection of point data on the surface of a product obtained through measuring instruments. Usually, the number of points obtained by a 3D coordinate measuring machine is relatively small and the distance between points is relatively large, which is called sparse point cloud; while the point cloud obtained by a 3D laser scanner or photogrammetric scanner has a large number of points and is relatively dense, which is called dense point cloud.

[0053] Real-time kinematic (RTK) carrier phase differential technology is a method for processing the carrier phase observations of two measurement stations in real time. It transmits the carrier phase data collected by the base station to the user receiver, where the difference is calculated to determine the coordinates. This is a new and commonly used satellite positioning measurement method. Previous static, rapid static, and dynamic measurements all required post-processing to achieve centimeter-level accuracy. RTK, however, is a measurement method that can obtain centimeter-level positioning accuracy in real time in the field. It employs a dynamic real-time carrier phase differential method and represents a significant milestone in GPS applications. Its emergence has brought new measurement principles and methods to engineering layout, topographic mapping, and various control surveys, greatly improving operational efficiency.

[0054] The vehicle is equipped with RTK (Real-Time Kinematics) for more accurate positioning; it also has radar sensors to extract point cloud data collected as the vehicle travels along a preset route. For example, this could be point cloud data from 120 degrees forward of the vehicle's trajectory. When the vehicle travels a preset distance along the preset route, this preset distance can be divided into multiple data units, for example, in 50-meter increments. It's understood that if the preset length is less than or equal to 50 meters, then this preset length does not need to be divided. Figure 2 As shown, when the preset length is greater than 50 meters, and the preset length is an integer multiple of 50 meters, then the data is divided into units of 50 meters each, as follows: Figure 2 As shown, the preset length 20 is 200 meters, and it is divided into data units of 50 meters each, resulting in data unit 21, data unit 22, data unit 23, and data unit 24. When the preset length is greater than 50 meters and is not an integer multiple of 50 meters, it will first be divided into data units of 50 meters each, and so on, until the last data unit is less than 50 meters. Figure 3As shown, the preset length 30 is 180 meters, and it is divided into data units of 50 meters each, resulting in data unit 31, data unit 32, data unit 33, and data unit 34. It is understood that the preset length can be other lengths. This embodiment uses 50-meter units for division, but other embodiments may also use different lengths. This embodiment does not specifically limit this.

[0055] The two-dimensional image of the current point cloud data is a two-dimensional image obtained by flattening the current point cloud data. This two-dimensional image is used to characterize the intensity and height information of the target object corresponding to the current point cloud data. Intensity information refers to the information representing the brightness of the target object obtained after measurement by a measuring instrument. In this embodiment, the measuring instrument is a radar. Height information refers to the information representing the height of the target object obtained after measurement by a measuring instrument.

[0056] The feature point cloud data in the current point cloud data refers to the feature point cloud data extracted from the current point cloud data by the vehicle's in-vehicle system using the LOAM algorithm.

[0057] Optionally, the vehicle can also be other mobile carriers equipped with sensors; this embodiment does not impose any specific limitations.

[0058] Optionally, radar measurement can also be replaced by other measurement methods such as laser measurement or photogrammetry; this embodiment does not impose any specific limitations.

[0059] S102. For each of the plurality of data units, obtain a historical image corresponding to the two-dimensional image of the current point cloud data, wherein the historical image is a two-dimensional image of the historical point cloud data, and the current point cloud data and the historical point cloud data correspond to the same route of a preset length.

[0060] For each of the plurality of data units, a historical image corresponding to the two-dimensional image of the current point cloud data is obtained. The historical image is a two-dimensional image obtained by flattening the historical point cloud data. The current point cloud data and the historical point cloud data correspond to the same route of a preset length.

[0061] like Figure 4 As shown, the two-dimensional image 31 of the current point cloud data corresponds to the two-dimensional image 41 of the historical point cloud data, the two-dimensional image 32 of the current point cloud data corresponds to the two-dimensional image 42 of the historical point cloud data, the two-dimensional image 33 of the current point cloud data corresponds to the two-dimensional image 43 of the historical point cloud data, and the two-dimensional image 34 of the current point cloud data corresponds to the two-dimensional image 44 of the historical point cloud data.

[0062] It is understandable that when there is no historical image in the cloud corresponding to the two-dimensional image of the current point cloud data, the two-dimensional image of the current point cloud data can be used as a historical image. The vehicle collects point cloud data for the second time on a route of a preset length. The cloud receives multiple data units sent by the vehicle for the second time. Each data unit includes the two-dimensional image of the current point cloud data collected for the second time, as well as the feature point cloud data in the current point cloud data collected for the second time.

[0063] S103. The two-dimensional image of the current point cloud data and the historical image corresponding to the two-dimensional image of the current point cloud data are fused to obtain the fused image.

[0064] The two-dimensional image of the current point cloud data and the corresponding historical image are fused together to obtain the fused image.

[0065] like Figure 5 As shown, the two-dimensional image 31 of the current point cloud data is fused with the historical image 41 corresponding to the two-dimensional image of the current point cloud data to obtain the fused image 51; the two-dimensional image 32 of the current point cloud data is fused with the historical image 42 corresponding to the two-dimensional image of the current point cloud data to obtain the fused image 52; the two-dimensional image 33 of the current point cloud data is fused with the historical image 43 corresponding to the two-dimensional image of the current point cloud data to obtain the fused image 53; the two-dimensional image 34 of the current point cloud data is fused with the historical image 44 corresponding to the two-dimensional image of the current point cloud data to obtain the fused image 54.

[0066] Understandably, when there is no historical image in the cloud corresponding to the 2D image of the current point cloud data, the 2D image of the current point cloud data acquired the first time can be used as the historical image, and the 2D image of the current point cloud data acquired the second time can be used as the 2D image of the current point cloud data. The 2D images of the current point cloud data acquired the first time and the 2D images of the current point cloud data acquired the second time are then fused to obtain the fused image.

[0067] S104. Perform pose optimization on the feature point cloud data in the current point cloud data to obtain the optimized feature point cloud position.

[0068] Pose Graph optimization is a graph-building method based on least-squares nonlinear optimization. It uses a vertex-edge pose graph to model the Simultaneous Localization and Graphing (SLAM) problem for robots. By constructing this vertex-edge pose graph model, the least-squares nonlinear optimization problem is figuratively transformed into a graph optimization problem.

[0069] The pose optimization of the feature point cloud data in the current point cloud data is performed to obtain the optimized feature point cloud position. It can be understood that the feature point cloud data in the current point cloud data is consistent with the two-dimensional image position of the current point cloud data.

[0070] S105. Adjust the position of the fused image according to the optimized feature point cloud position to obtain the target image.

[0071] The position of the fused image is adjusted based on the optimized feature point cloud positions to obtain the target image. This achieves optimization of the target image on the horizontal plane.

[0072] This embodiment of the disclosure receives data in segments by receiving multiple data units sent by the vehicle. Each data unit includes a two-dimensional image of the current point cloud data and feature point cloud data from the current point cloud data. The current point cloud data is point cloud data collected by the vehicle while traveling along a route of a preset length, thus reducing the amount of data transmission. For each of the multiple data units, a historical image corresponding to the two-dimensional image of the current point cloud data is obtained. The historical image is a two-dimensional image of historical point cloud data. The current point cloud data and the historical point cloud data correspond to the same route of a preset length, thus clarifying the relationship between the two-dimensional image of the current point cloud data and the historical image. The method involves: 1) fusing the current two-dimensional image of the point cloud data with the corresponding historical image to obtain a fused image, thereby improving image accuracy; 2) optimizing the pose of the feature point cloud data in the current point cloud data to obtain optimized feature point cloud positions; 3) adjusting the position of the fused image based on the optimized feature point cloud positions to obtain the target image; 4) determining the position of the fused image and making further adjustments to make the target image more accurate. This mapping method can locally update the target image, saving time, reducing labor costs, improving mapping efficiency, and enhancing user experience.

[0073] Furthermore, since the embodiments of this disclosure can perform both partial and global updates during map creation, they offer greater flexibility compared to existing global update methods.

[0074] In some embodiments, after receiving multiple data units transmitted by the vehicle, the method further includes:

[0075] The feature point cloud data is sorted according to the first location information of the feature point cloud data to obtain the feature point cloud data in the point cloud data collected during the vehicle's travel on the preset trajectory, wherein the preset trajectory includes multiple routes of the preset length.

[0076] Based on the first location information of the feature point cloud data, the feature point cloud data on multiple routes of preset length are sorted. For example, when the network is poor, the received feature point cloud data is not obtained in chronological order. The third segment of feature point cloud data may be received faster than the second segment. Therefore, we need to sort the feature point cloud data on multiple routes of preset length according to the first location information of the feature point cloud data, and place the third segment of feature point cloud data after the second segment of feature point cloud data. This yields the feature point cloud data collected during the vehicle's journey on the preset trajectory, which is more transparent and facilitates position correction of the entire trajectory.

[0077] In some embodiments, the method further includes: optimizing the feature point cloud data in the point cloud data collected during the vehicle's travel on a preset trajectory to obtain the second location information of the feature point cloud data.

[0078] Among them, optimizing the feature point cloud data in the point cloud data collected during the vehicle's travel on the preset trajectory includes: pre-integrating the feature point cloud data in the point cloud data collected during the vehicle's travel on the preset trajectory based on the information output by the vehicle's inertial measurement unit during the vehicle's travel on the preset trajectory.

[0079] An Inertial Measurement Unit (IMU) is a device that measures the three-axis attitude angles (or angular rates) and acceleration of an object. Typically, an IMU contains three single-axis accelerometers and three single-axis gyroscopes. The accelerometers detect the acceleration signals of the object along the three independent axes of the carrier coordinate system, while the gyroscopes detect the angular velocity signals of the carrier relative to the navigation coordinate system. By measuring the object's angular velocity and acceleration in three-dimensional space, the object's attitude can be calculated. IMUs are generally used for local integration in mapping processes to obtain relatively accurate local displacements and attitude changes.

[0080] IMU pre-integration, part of the front-end, involves computation immediately after IMU data acquisition. Because IMUs have high sampling frequencies, typically 100Hz-1000Hz, resulting in massive amounts of data, optimization often involves extracting data at regular intervals, such as every second. However, during back-end optimization, when iteratively calculating and adjusting displacement, velocity, quaternion, and PVQ values, any subsequent trajectories requiring re-integration after a change in the PVQ value (e.g., in the first second) must be recalculated. Pre-integration aims to reduce this multiple integration processes to a single integration, significantly reducing computational costs.

[0081] Based on the information output by the vehicle's inertial measurement unit during the vehicle's journey along the preset trajectory, the feature point cloud data collected during the journey is pre-integrated. Through pre-integration, the true distance between two adjacent feature point cloud data can be determined, and timely corrections can be made to obtain the second position information of the feature point cloud data.

[0082] Because PTK failure over a long period of time can cause breaks and jumps in the feature point cloud data on the preset trajectory, this embodiment of the present disclosure corrects and optimizes the feature point cloud data of the vehicle on the preset trajectory by treating the feature point cloud data as a rigid node as a whole, thereby further improving the accuracy of mapping.

[0083] In some embodiments, the two-dimensional image of the current point cloud data and the historical image corresponding to the two-dimensional image of the current point cloud data are fused to obtain a fused image, including:

[0084] Based on the second location information of the feature point cloud data, the two-dimensional image of the current point cloud data is superimposed onto the historical image corresponding to the two-dimensional image of the current point cloud data. Using the two-dimensional image of the current point cloud data as the primary reference and the historical image corresponding to the two-dimensional image of the current point cloud data as a secondary reference, a fused image is obtained. The position information of the boundary nodes on the two-dimensional image of the current point cloud data and the historical image corresponding to the two-dimensional image of the current point cloud data is saved, and adjustments are made with adjacent nodes in the global image. The global image refers to the unique image on the preset trajectory. For example, when a target image on the preset trajectory is obtained in this embodiment, the target image can be updated to the global image.

[0085] This embodiment of the disclosure further improves the accuracy of mapping by overlaying the two-dimensional image of the current point cloud data onto the corresponding historical image for fusion, enabling the mapping method to have the ability to update locally, and realizing large-scale urban mapping by combining vehicle-side data with cloud-based mapping throughout the entire process.

[0086] In some embodiments, the method further includes: segmenting the target image and outputting the segmented target image to a third-party platform, wherein the third-party platform is used to annotate the segmented target image.

[0087] The target image is segmented, for example, into sections such as guardrails, poles, traffic lights, and traffic signs. The segmented target image is then output to a third-party platform via Bluetooth, network connection, or other communication methods. This third-party platform is used to annotate the segmented target image. This third-party platform can be an annotation platform or any other platform requiring annotation.

[0088] Optionally, a third-party platform can annotate the segmented target image, such as labeling barriers, guardrails, poles, traffic lights, traffic signs, etc.

[0089] The embodiments disclosed herein use a third-party platform to annotate the segmented target image, making the target image clearer and easier to use.

[0090] Figure 6 This is a schematic diagram of the structure of a mapping apparatus provided in an embodiment of this disclosure. The mapping apparatus may be an electronic device as described in the above embodiments, or it may be a component or assembly within that electronic device. The mapping apparatus provided in this disclosure can execute the processing flow provided in the mapping method embodiments, such as... Figure 6As shown, the mapping device 60 includes: a receiving module 61, an acquisition module 62, a fusion module 63, an optimization module 64, and an adjustment module 65. The receiving module 61 receives multiple data units sent by a vehicle. Each data unit includes a two-dimensional image of the current point cloud data and feature point cloud data from the current point cloud data. The current point cloud data is point cloud data collected by the vehicle while traveling along a route of a preset length. The acquisition module 62 acquires a historical image corresponding to the two-dimensional image of the current point cloud data for each of the multiple data units. The historical image is a two-dimensional image of historical point cloud data, and the current point cloud data and the historical point cloud data correspond to the same route of a preset length. The fusion module 63 fuses the two-dimensional image of the current point cloud data and the corresponding historical image to obtain a fused image. The optimization module 64 optimizes the pose of the feature point cloud data in the current point cloud data to obtain an optimized feature point cloud position. The adjustment module 65 adjusts the position of the fused image according to the optimized feature point cloud position to obtain a target image.

[0091] Optionally, the two-dimensional image of the current point cloud data is a two-dimensional image obtained by flattening the current point cloud data, and the two-dimensional image is used to characterize the intensity and height information of the target object corresponding to the current point cloud data.

[0092] Optionally, the mapping device 60 further includes: a sorting module 66, used to sort the feature point cloud data according to the first location information of the feature point cloud data, to obtain the feature point cloud data in the point cloud data collected during the vehicle's travel on a preset trajectory, wherein the preset trajectory includes multiple routes of the preset length.

[0093] Optionally, the optimization module 64 is also used to optimize the feature point cloud data in the point cloud data collected during the vehicle's travel on the preset trajectory, so as to obtain the second position information of the feature point cloud data.

[0094] Optionally, the optimization module 64 is further configured to pre-integrate the feature point cloud data in the point cloud data collected during the vehicle's travel on the preset trajectory based on the information output by the vehicle's inertial measurement unit during the vehicle's travel on the preset trajectory.

[0095] Optionally, the fusion module 63 is further configured to superimpose the two-dimensional image of the current point cloud data onto the historical image corresponding to the two-dimensional image of the current point cloud data based on the second location information of the feature point cloud data, so as to obtain the fused image.

[0096] Optionally, the mapping device 60 further includes an output module 67, used to segment the target image and output the segmented target image to a third-party platform, wherein the third-party platform is used to annotate the segmented target image.

[0097] Figure 6 The mapping apparatus of the illustrated embodiment can be used to execute the technical solutions of the above method embodiments, and its implementation principle and technical effect are similar, so they will not be described again here.

[0098] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. The electronic device provided in an embodiment of this disclosure can execute the processing flow provided in the method embodiment for drawing, such as... Figure 7 As shown, the electronic device 70 includes: a memory 71, a processor 72, a computer program, and a communication interface 73; wherein the computer program is stored in the memory 71 and configured to be executed by the processor 72 as described above in the mapping method.

[0099] In addition, this disclosure also provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the mapping method described in the above embodiments.

[0100] Furthermore, this disclosure also provides a computer program product, which includes a computer program or instructions that, when executed by a processor, implement the mapping method described above.

[0101] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—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 can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can 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.

[0102] In some implementations, clients and servers 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.

[0103] 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.

[0104] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to:

[0105] The system receives multiple data units sent by the vehicle. Each data unit includes a two-dimensional image of the current point cloud data and feature point cloud data in the current point cloud data. The current point cloud data is the point cloud data collected by the vehicle while it is traveling on a route of a preset length.

[0106] For each of the plurality of data units, a historical image corresponding to the two-dimensional image of the current point cloud data is obtained. The historical image is a two-dimensional image of the historical point cloud data. The current point cloud data and the historical point cloud data correspond to the same route of a preset length.

[0107] The two-dimensional image of the current point cloud data and the corresponding historical image of the current point cloud data are fused to obtain the fused image;

[0108] The pose of the feature point cloud data in the current point cloud data is optimized to obtain the optimized feature point cloud position.

[0109] The position of the fused image is adjusted based on the optimized feature point cloud position to obtain the target image.

[0110] In addition, the electronic device can also perform other steps in the mapping method described above.

[0111] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but 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 the user's computer, partially on the user's computer, as a standalone software package, partially on the user's 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 user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] In the context of this disclosure, a machine-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 machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-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 machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0116] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0117] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for mapping, characterized in that, The method includes: The system receives multiple data units sent by the vehicle. Each data unit includes a two-dimensional image of the current point cloud data and feature point cloud data in the current point cloud data. The current point cloud data is point cloud data collected by the vehicle while traveling on a route of a preset length. The two-dimensional image of the current point cloud data is a two-dimensional image obtained by flattening the current point cloud data. The two-dimensional image is used to characterize the intensity and height information of the target object corresponding to the current point cloud data. For each of the plurality of data units, a historical image corresponding to the two-dimensional image of the current point cloud data is obtained. The historical image is a two-dimensional image of the historical point cloud data. The current point cloud data and the historical point cloud data correspond to the same route of a preset length. The two-dimensional image of the current point cloud data and the corresponding historical image of the current point cloud data are fused to obtain the fused image; The pose of the feature point cloud data in the current point cloud data is optimized to obtain the optimized feature point cloud position. The position of the fused image is adjusted based on the optimized feature point cloud position to obtain the target image.

2. The method according to claim 1, characterized in that, After receiving multiple data units sent by the vehicle, the method further includes: The feature point cloud data is sorted according to the first location information of the feature point cloud data to obtain the feature point cloud data in the point cloud data collected during the vehicle's travel on the preset trajectory, wherein the preset trajectory includes multiple routes of the preset length.

3. The method according to claim 2, characterized in that, The method further includes: The feature point cloud data collected during the vehicle's journey along a preset trajectory is optimized to obtain the second location information of the feature point cloud data.

4. The method according to claim 3, characterized in that, Optimize the feature point cloud data in the point cloud data collected during the vehicle's journey along the preset trajectory, including: Based on the information output by the vehicle's inertial measurement unit during the vehicle's journey along the preset trajectory, the feature point cloud data in the point cloud data collected during the vehicle's journey along the preset trajectory is pre-integrated.

5. The method according to claim 3, characterized in that, The two-dimensional image of the current point cloud data and the corresponding historical image of the current point cloud data are fused to obtain a fused image, including: Based on the second location information of the feature point cloud data, the two-dimensional image of the current point cloud data is superimposed onto the historical image corresponding to the two-dimensional image of the current point cloud data to obtain the fused image.

6. The method according to claim 1, characterized in that, The method further includes: The target image is segmented, and the segmented target image is output to a third-party platform, which is used to annotate the segmented target image.

7. A mapping apparatus, characterized in that, The device includes: The receiving module is used to receive multiple data units sent by the vehicle. Each data unit includes a two-dimensional image of the current point cloud data and feature point cloud data in the current point cloud data. The current point cloud data is the point cloud data collected by the vehicle while traveling on a route of a preset length. The two-dimensional image of the current point cloud data is a two-dimensional image obtained by flattening the current point cloud data. The two-dimensional image is used to characterize the intensity and height information of the target object corresponding to the current point cloud data. The acquisition module is used to acquire a historical image corresponding to the two-dimensional image of the current point cloud data for each of the plurality of data units. The historical image is a two-dimensional image of the historical point cloud data, and the current point cloud data and the historical point cloud data correspond to the same route of a preset length. The fusion module is used to fuse the two-dimensional image of the current point cloud data and the historical image corresponding to the two-dimensional image of the current point cloud data to obtain the fused image; The optimization module is used to optimize the pose of the feature point cloud data in the current point cloud data to obtain the optimized feature point cloud position. The adjustment module is used to adjust the position of the fused image according to the optimized feature point cloud position to obtain the target image.

8. An electronic device, characterized in that, include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-6.

Images