WO2022017133A1 - 一种点云数据处理方法及装置 - Google Patents

一种点云数据处理方法及装置 Download PDF

Info

Publication number
WO2022017133A1
WO2022017133A1 PCT/CN2021/102856 CN2021102856W WO2022017133A1 WO 2022017133 A1 WO2022017133 A1 WO 2022017133A1 CN 2021102856 W CN2021102856 W CN 2021102856W WO 2022017133 A1 WO2022017133 A1 WO 2022017133A1
Authority
WO
WIPO (PCT)
Prior art keywords
matrix
grid
target
cloud data
point cloud
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2021/102856
Other languages
English (en)
French (fr)
Inventor
王哲
石建萍
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sensetime Group Ltd
Original Assignee
Sensetime Group Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sensetime Group Ltd filed Critical Sensetime Group Ltd
Priority to JP2022514581A priority Critical patent/JP2022547873A/ja
Priority to KR1020227007394A priority patent/KR20220044777A/ko
Publication of WO2022017133A1 publication Critical patent/WO2022017133A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • G01S17/08—Systems determining position data of a target for measuring distance only
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30248—Vehicle exterior or interior
    • G06T2207/30252—Vehicle exterior; Vicinity of vehicle
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30248—Vehicle exterior or interior
    • G06T2207/30252—Vehicle exterior; Vicinity of vehicle
    • G06T2207/30261—Obstacle

Definitions

  • the present disclosure relates to the technical field of information processing, and in particular, to a method and device for processing point cloud data.
  • LiDAR is widely used in the fields of automatic driving, UAV exploration, map mapping and other fields with its precise ranging ability.
  • autonomous driving in the application scenario of autonomous driving, the point cloud data collected by lidar is generally processed to realize the positioning of the vehicle and the identification of obstacles. It consumes a lot of computing resources.
  • the calculation method of this calculation method Low efficiency and low utilization of computing resources.
  • the embodiments of the present disclosure provide at least one point cloud data processing method and device.
  • an embodiment of the present disclosure provides a point cloud data processing method, including: acquiring point cloud data to be processed obtained by scanning a radar device in a target scene; The target point cloud data is screened out from the point cloud data to be processed; the target point cloud data is detected to obtain a detection result.
  • the point cloud data to be processed collected by the radar device in the target scene can be screened based on the effective perception range information corresponding to the target scene, and the screened target point cloud data is the target point cloud data corresponding to the target scene Therefore, based on the filtered point cloud data, the detection calculation is performed in the target scene, which can reduce the amount of calculation, improve the calculation efficiency, and the utilization rate of computing resources in the target scene.
  • the effective perception range information corresponding to the target scene is determined according to the following methods: obtaining computing resource information of a processing device; based on the computing resource information, determining the Effective sensing range information.
  • filtering out the target point cloud data from the to-be-processed point cloud data includes: determining an effective coordinate range based on the effective sensing range information. ; Based on the effective coordinate range, filter out the target point cloud data from the to-be-processed point cloud data.
  • the determining the effective coordinate range based on the effective sensing range information includes: based on the position information of the reference position point within the effective sensing range, and the reference position point within the target The coordinate information in the scene determines the valid coordinate range corresponding to the target scene.
  • the filtering out target point cloud data from the point cloud data to be processed based on the effective coordinate range includes: scanning a radar with the corresponding coordinate information located within the effective coordinate range. Points are used as radar scanning points in the target point cloud data.
  • the coordinate information of the reference position point in the target scene is determined according to the following methods: obtaining the position information of the intelligent driving device on which the radar device is set; based on the position information of the intelligent driving device Determine the road type of the road where the intelligent driving device is located; and obtain the coordinate information of the reference position point matching the road type as the coordinate information of the reference position point in the target scene.
  • the point cloud data that the intelligent driving device needs to process may be different when it is located on roads of different road types. Therefore, by obtaining the coordinate information of the reference position point matching the road type, the intelligent driving device can determine the current The valid coordinate range of the road type where it is located, so as to filter out the point cloud data under the corresponding road type, thereby improving the accuracy of the detection results of the intelligent driving device under different road types.
  • the detection result includes the position of the object to be identified in the target scene; the detecting the target point cloud data to obtain the detection result includes: performing the detection on the target point cloud data Perform rasterization processing to obtain a grid matrix; the value of each element in the grid matrix is used to represent whether there is a target point at the corresponding grid; according to the grid matrix and the to-be-identified in the target scene
  • the size information of the object is used to generate a sparse matrix corresponding to the object to be recognized; based on the generated sparse matrix, the position of the object to be recognized in the target scene is determined.
  • the generating a sparse matrix corresponding to the to-be-identified object according to the grid matrix and the size information of the to-be-identified object in the target scene includes: according to the grid matrix and the size information of the object to be identified in the target scene, perform at least one expansion processing operation or erosion processing operation on the target element in the grid matrix, and generate a sparse matrix corresponding to the object to be identified; wherein, the The value of the target element indicates that the target point exists at the corresponding grid.
  • the expansion processing operation or the erosion processing operation includes shift processing and logical operation processing, and the difference between the coordinate range of the sparse matrix and the size of the object to be identified is within a preset threshold. within the range.
  • At least one expansion processing operation is performed on the elements in the grid matrix to generate a
  • the sparse matrix corresponding to the object includes: performing a first inversion operation on the elements in the grid matrix before the current expansion processing operation to obtain the grid matrix after the first inversion operation;
  • the grid matrix after the first inversion operation is subjected to at least one convolution operation to obtain a grid matrix with a preset sparsity after at least one convolution operation; the preset sparsity is determined by the target scene.
  • the size information of the identification object is determined; the second inversion operation is performed on the elements in the grid matrix with the preset sparsity after the at least one convolution operation to obtain the sparse matrix.
  • performing the first inversion operation on the elements in the grid matrix before the current expansion processing operation to obtain the grid matrix after the first inversion operation includes: based on the second preset A convolution kernel, which performs a convolution operation on other elements except the target element in the grid matrix before the current expansion processing operation, to obtain the first inversion element, and based on the second preset convolution kernel, performs a convolution operation on the current time
  • the target element in the grid matrix before the expansion processing operation is subjected to a convolution operation to obtain a second inversion element; based on the first inversion element and the second inversion element, the grid after the first inversion operation is obtained. lattice matrix.
  • At least one convolution operation is performed on the grid matrix after the first inversion operation based on the first preset convolution check, to obtain at least one convolution operation with a preset sparsity.
  • the grid matrix includes: for the first convolution operation, performing a convolution operation on the grid matrix after the first inversion operation and the first preset convolution kernel to obtain the grid after the first convolution operation. matrix; repeat the steps of performing the convolution operation on the grid matrix after the previous convolution operation and the first preset convolution kernel to obtain the grid matrix after the current convolution operation, until obtaining the grid matrix with the pre-set convolution kernel. Set the raster matrix of sparsity.
  • the first preset convolution kernel has a weight matrix and an offset corresponding to the weight matrix; for the first convolution operation, the grid after the first inversion operation is Performing a convolution operation on the lattice matrix and the first preset convolution kernel to obtain a lattice matrix after the first convolution operation, including: for the first convolution operation, according to the size of the first preset convolution kernel and the preset steps length, select each grid sub-matrix from the grid matrix after the first inversion operation; for each selected grid sub-matrix, multiply the grid sub-matrix and the weight matrix operation to obtain a first operation result, and adding the first operation result and the offset to obtain a second operation result; based on the second operation result corresponding to each of the grid sub-matrixes, determine the first volume The grid matrix after the product operation.
  • At least one corrosion processing operation is performed on the elements in the grid matrix to generate a
  • the sparse matrix corresponding to the object includes: performing at least one convolution operation on the grid matrix to be processed based on the third preset convolution kernel to obtain a grid matrix with a preset sparsity after at least one convolution operation;
  • the sparsity is determined by the size information of the object to be identified in the target scene;
  • the grid matrix with the preset sparsity after the at least one convolution operation is determined as the sparseness corresponding to the object to be identified matrix.
  • performing grid processing on the target point cloud data to obtain a grid matrix includes: performing grid processing on the target point cloud data to obtain a grid matrix and the grid matrix.
  • the correspondence between each element and the coordinate range information of each target point; the determining the position range of the object to be identified in the target scene based on the generated sparse matrix includes: based on the grid matrix The corresponding relationship between each element in the sparse matrix and the coordinate range information of each target point, determine the coordinate information of the target point corresponding to each target element in the generated sparse matrix; The coordinate information of the target point is combined to determine the position of the object to be recognized in the target scene.
  • the determining the position of the object to be identified in the target scene based on the generated sparse matrix includes: pairing the generated sparse matrix based on a trained convolutional neural network. Perform at least one convolution process on each target element in to obtain a convolution result; based on the convolution result, determine the position of the object to be identified in the target scene.
  • the method further includes: controlling and setting an intelligent driving device of the radar device based on the detection result.
  • an embodiment of the present disclosure further provides a point cloud data processing device, including: an acquisition module for acquiring point cloud data to be processed obtained by scanning a radar device in a target scene; a screening module for according to the target The effective perception range information corresponding to the scene is used to filter out the target point cloud data from the to-be-processed point cloud data; the detection module is used to detect the target point cloud data to obtain a detection result.
  • embodiments of the present disclosure further provide a computer device, including a processor, a memory, and a bus, where the memory stores machine-readable instructions executable by the processor, and when the computer device runs, the processor It communicates with the memory through a bus, and when the machine-readable instructions are executed by the processor, the above-mentioned first aspect or the steps in any possible implementation manner of the first aspect are performed.
  • an embodiment of the present disclosure further provides a computer-readable storage medium, where a computer program stored on the computer program is executed by a processor to execute the steps in the first aspect or any possible implementation manner of the first aspect .
  • FIG. 1 shows a flowchart of a point cloud data processing method provided by an embodiment of the present disclosure
  • FIG. 2 shows a schematic diagram of coordinates of each position point of a cuboid provided by an embodiment of the present disclosure
  • FIG. 3 shows a flowchart of a method for determining coordinate information of the reference position point provided by an embodiment of the present disclosure
  • FIG. 4 shows a flowchart of a method for determining a detection result provided by an embodiment of the present disclosure
  • 5A shows a schematic diagram of a grid matrix before encoding provided by an embodiment of the present disclosure
  • FIG. 5B shows a schematic diagram of a sparse matrix provided by an embodiment of the present disclosure
  • 5C shows a schematic diagram of an encoded grid matrix provided by an embodiment of the present disclosure
  • FIG. 6A shows a schematic diagram of a left-shifted grid matrix provided by an embodiment of the present disclosure
  • FIG. 6B shows a schematic diagram of a logical OR operation provided by an embodiment of the present disclosure
  • FIG. 7A shows a schematic diagram of a grid matrix after a first inversion operation provided by an embodiment of the present disclosure
  • FIG. 7B shows a schematic diagram of a grid matrix after a convolution operation provided by an embodiment of the present disclosure
  • FIG. 8 shows a schematic diagram of the architecture of a point cloud data processing apparatus provided by an embodiment of the present disclosure
  • FIG. 9 shows a schematic structural diagram of a computer device provided by an embodiment of the present disclosure.
  • the present disclosure provides a point cloud data processing method and device, which can screen the point cloud data to be processed collected by the radar device in the target scene based on the effective perception range information corresponding to the target scene, and the screened target point Cloud data is the point cloud data that is valid in the target scene. Therefore, based on the filtered target point cloud data, the detection calculation is performed in the target scene, which can reduce the amount of calculation, improve the calculation efficiency, and the utilization of computing resources in the target scene. Rate.
  • the execution subject of the point cloud data processing method provided by the embodiment of the present disclosure is generally a computer with a certain computing capability.
  • equipment the computer equipment for example includes: terminal equipment or server or other processing equipment, the terminal equipment can be user equipment (User Equipment, UE), mobile equipment, user terminal, terminal, personal digital processing (Personal Digital Assistant, PDA), computing equipment, vehicle equipment, etc.
  • the point cloud data processing method may be implemented by a processor calling computer-readable instructions stored in a memory.
  • an embodiment of the present disclosure provides a point cloud data processing method, the method includes steps 101 to 103, wherein:
  • Step 101 Obtain point cloud data to be processed obtained by scanning the radar device in the target scene.
  • Step 102 Screen out target point cloud data from the to-be-processed point cloud data according to the effective perception range information corresponding to the target scene.
  • Step 103 Detect the target point cloud data to obtain a detection result.
  • the radar device can be deployed on an intelligent driving device, and during the driving process of the intelligent driving device, the radar device can scan to obtain point cloud data to be processed.
  • the effective sensing range information may include coordinate thresholds on each coordinate dimension in a reference coordinate system, where the reference coordinate system is a three-dimensional coordinate system.
  • the effective perception range information may be description information that constitutes a cuboid.
  • the description information may be the coordinate thresholds of the length, width, and height of the cuboid in each coordinate dimension in the reference coordinate system, including the x-axis direction.
  • FIG. 2 shows the structure based on the maximum value x_max and the minimum value x_min in the x-axis direction, the maximum value y_max and the minimum value y_min in the y-axis direction, and the maximum value z_max and the minimum value z_min in the z-axis direction.
  • the coordinates of each position point of the cuboid, the coordinate origin can be the lower left vertex of the cuboid, and its coordinate value is (x_min, y_min, z_min).
  • the effective sensing range information may also be description information of a sphere, a cube, etc. For example, only the radius of a sphere or the length, width, and height of a cube is given.
  • the specific effective sensing range information can be based on The actual application scenario is described, and the present disclosure is not limited.
  • the constraints on the effective sensing range can be preset.
  • the values of x_max, y_max, and z_max can be set to be less than or equal to 200 meters.
  • the calculation based on the point cloud data is based on the operation of the spatial voxels corresponding to the point cloud data, such as the layer-by-layer learning network (VoxelNet) based on the three-dimensional spatial information of the point cloud. Therefore, in this application scenario, in the case of limiting the coordinate thresholds of the reference radar scanning point in each coordinate dimension in the reference coordinate system, it is also possible to limit the number of spatial voxels of the reference radar scanning point in each coordinate dimension not to exceed the space volume pixel threshold.
  • the spatial voxels corresponding to the point cloud data such as the layer-by-layer learning network (VoxelNet) based on the three-dimensional spatial information of the point cloud. Therefore, in this application scenario, in the case of limiting the coordinate thresholds of the reference radar scanning point in each coordinate dimension in the reference coordinate system, it is also possible to limit the number of spatial voxels of the reference radar scanning point in each coordinate dimension not to exceed the space volume pixel threshold.
  • the number of spatial voxels in each coordinate dimension can be calculated by the following formula:
  • N_x (x_max–x_min)/x_gridsize
  • N_y (y_max–y_min)/y_gridsize
  • N_z (z_max ⁇ z_min)/z_gridsize.
  • x_gridsize, y_gridsize, z_gridsize respectively represent the preset resolutions corresponding to each dimension
  • N_x represents the number of spatial voxels in the x-axis direction
  • N_y represents the number of spatial voxels in the y-axis direction
  • N_z represents the z-axis direction. The number of spatial voxels on .
  • the calculation based on the point cloud data may also be an algorithm based on the point cloud data within the area of the top view, such as the point cloud-based fast target detection framework (PointPillars).
  • PointPillars point cloud-based fast target detection framework
  • Limit the top-view voxel area for example, you can limit the value of N_x*N_y.
  • the effective sensing range information obtained in advance based on experiments may be obtained, and the effective sensing range information may be used as a preset and A fixed value, and the limited perceptual range information also obeys the above constraints.
  • the computing resource information of the processing device may also be obtained first; The effective perception range information of .
  • the computing resource information includes at least one of the following information: the memory of the central processing unit (CPU), the video memory of the graphics processing unit (GPU), and the computing resources of the field programmable logic gate array (FPGA).
  • CPU central processing unit
  • GPU graphics processing unit
  • FPGA field programmable logic gate array
  • the corresponding relationship between the computing resource information at each level and the effective sensing range information can be preset, and then when the method provided by the present disclosure is applied For different electronic devices, the effective sensing range information that matches the computing resource information of the electronic device can be searched based on the comparison relationship, or, when it is detected that the computing resource information of the electronic device changes, the effective sensing range can be dynamically adjusted. range information.
  • the correspondence between the computing resource information of each level and the effective sensing range information may be obtained through an experimental test in advance.
  • the effective coordinate range when selecting the target point cloud data from the point cloud data to be processed according to the effective sensing range information corresponding to the target scene, the effective coordinate range may be determined based on the effective sensing range information first, and then based on the effective sensing range information. Valid coordinate range, filter out the target point cloud data from the point cloud data to be processed.
  • both the effective sensing range information and the effective coordinate range are fixed; the effective coordinate range can be changed according to the change of the effective sensing range information.
  • the effective sensing range information may be the description information of the cuboid, including the length, width and height of the cuboid, and the radar device is used as the intersection of the body diagonals of the cuboid. If the position does not change, the cuboid is fixed, and the coordinate range in the cuboid is the valid coordinate range, so the valid coordinate range is also fixed.
  • the position information of the reference position point within the effective sensing range and the coordinate information of the reference position point in the target scene may be used to determine the effective coordinate range. , and determine the effective coordinate range corresponding to the target scene.
  • the effective sensing range information may be the description information of the cuboid, and the reference position point may be the intersection of the body diagonals of the cuboid. With the change of the reference position point, the effective sensing range information will also be available in different target scenarios. changes, so the corresponding valid coordinate range also changes.
  • the coordinate information of the reference position point in the target scene may be the coordinate information of the reference position point in the radar coordinate system corresponding to the target scene, and the radar coordinate system may be used for collecting point cloud data in the target scene.
  • the reference position point may be the intersection of the body diagonals of the cuboid. If the effective sensing range information is the description information of a sphere, the reference position point may be the center of the sphere. , or, the reference position point can be any reference radar scanning point within the effective sensing range information.
  • the effective coordinate range corresponding to the target scene when determining the effective coordinate range corresponding to the target scene based on the position information of the reference position point within the effective perception range and the coordinate information of the reference position point in the target scene, the effective coordinate range corresponding to the target scene may be determined based on The coordinate information of the reference position point in the radar coordinate system, convert the coordinate thresholds in each coordinate dimension in the effective sensing range information in the reference coordinate system into the coordinates in each coordinate dimension in the radar coordinate system threshold.
  • the reference position point may have corresponding first coordinate information in the reference coordinate system, and may have corresponding second coordinate information in the radar coordinate system.
  • the coordinate thresholds of the reference radar scanning points in the effective sensing range information in each coordinate dimension under the reference coordinate system can be converted into the coordinate thresholds in the reference coordinate system. Coordinate thresholds in each coordinate dimension in the radar coordinate system.
  • the relative positional relationship between the threshold coordinate point corresponding to the coordinate threshold of each coordinate dimension of the reference radar scanning point in the effective sensing range information in the reference coordinate system and the reference position point may be determined first. , and then, based on the relative positional relationship, determine the coordinate thresholds of the reference radar scanning points in the effective sensing range information in each coordinate dimension in the reference coordinate system and the coordinate thresholds in each coordinate dimension in the radar coordinate system.
  • the coordinate thresholds of the reference radar scanning point in each coordinate dimension in the radar coordinate system in the effective sensing range information determined based on the coordinate information of the reference position point will also change accordingly. That is, the effective coordinate range corresponding to the target scene will also change, so it is possible to control the effective coordinate range in different target scenes by controlling the coordinate information of the reference position point.
  • the radar scanning with the corresponding coordinate information located within the effective coordinate range may be performed. Points are used as radar scanning points in the target point cloud data.
  • the three-dimensional coordinate information of the radar scan point can be stored, and then based on the three-dimensional coordinate information of the radar scan point, it can be determined whether the radar scan point is within the effective coordinate range.
  • the three-dimensional coordinate information of the radar scanning point is (x, y, z)
  • the three-dimensional coordinate information of the radar scanning point can be determined. Whether the coordinate information meets the following conditions:
  • the application of the above point cloud data processing method will be introduced in combination with specific application scenarios.
  • the above-mentioned point cloud data processing method can be applied to an automatic driving scene.
  • the intelligent driving device is provided with a radar device.
  • the coordinate information of the reference position point can be determined by the method as shown in FIG. 3 , and the method includes: The following steps 301 to 303.
  • Step 301 Acquire location information of the intelligent driving device on which the radar device is set.
  • the location information of the intelligent driving device for example, it can be acquired based on a Global Positioning System (Global Positioning System, GPS), and the present disclosure does not limit other ways in which the location information of the intelligent driving device can be acquired.
  • GPS Global Positioning System
  • Step 302 Determine the road type of the road where the smart driving device is located based on the location information of the smart driving device.
  • the road type of each road within the drivable range of the intelligent driving device may be preset, and the road type may include, for example, an intersection, a T-junction, a highway, a parking lot, etc., based on the location information of the intelligent driving device
  • the road on which the intelligent driving device is located may be determined, and then the road type of the road where the intelligent driving device is located may be determined according to the preset road type of each road within the drivable range of the intelligent driving device.
  • Step 303 Acquire coordinate information of a reference position point matching the road type.
  • the location of the point cloud data that needs to be focused on processing may be different for different road types. For example, if the intelligent driving device is located on a highway, the point cloud data that the intelligent driving device needs to process may be the point cloud data in front of the intelligent driving device. When the device is located at an intersection, the point cloud data that the intelligent driving device needs to process may be the point cloud data around the intelligent driving device. Screening of point cloud data under road type.
  • the point cloud data that the intelligent driving device needs to process may be different when it is located on roads of different road types. Therefore, by obtaining the coordinate information of the reference position point matching the road type, the intelligent driving device can determine the current The valid coordinate range of the road type where it is located, so as to filter out the point cloud data under the corresponding road type, thereby improving the accuracy of screening point cloud data.
  • the target point cloud data after the target point cloud data is screened out from the point cloud data to be processed, the target point cloud data can also be detected, and after the detection result is obtained, based on the detection result, the control settings Intelligent driving equipment for radar installations.
  • the detection of the object to be recognized (for example, an obstacle) during the driving process of the intelligent driving device can be realized based on the filtered target point cloud data.
  • Controlling the driving of the intelligent driving device may be controlling the acceleration, deceleration, steering, braking, and the like of the intelligent driving device.
  • the detection result includes the position of the object to be identified in the target scene.
  • the process of detecting the target point cloud data will be described in detail below with reference to specific embodiments, as shown in FIG. 4 .
  • An embodiment of the present disclosure provides a method for determining a detection result, which includes the following steps:
  • Step 401 Perform grid processing on the target point cloud data to obtain a grid matrix; the value of each element in the grid matrix is used to represent whether there is a target point at the corresponding grid.
  • the point corresponding to the target point cloud data is called a target point.
  • Step 402 Generate a sparse matrix corresponding to the to-be-identified object according to the grid matrix and the size information of the to-be-identified object in the target scene.
  • Step 403 Determine the position of the object to be identified in the target scene based on the generated sparse matrix.
  • rasterization may be performed first, and then the raster matrix obtained by the rasterization may be sparsely processed to generate a sparse matrix.
  • the rasterization process here can be to map the spatially distributed target point cloud data including each target point into a set grid, and perform grid coding based on the target points corresponding to the grid (corresponding to a zero-one matrix ) process, the sparse processing process may be based on the size information of the object to be identified in the target scene to perform expansion processing operation on the above zero-one matrix (corresponding to the processing result of increasing the elements indicated as 1 in the zero-one matrix) or erosion processing The process of the operation (corresponding to the processing result of reducing the elements indicated as 1 in the zero-one matrix).
  • the above-mentioned rasterization process and thinning process will be further described.
  • the target points distributed in the Cartesian continuous real number coordinate system may be converted into the rasterized discrete coordinate system.
  • the embodiment of the present disclosure has target points such as point A (0.32m, 0.48m), point B (0.6m, 0.4801m), and point C (2.1m, 3.2m), and rasterization is performed with 1m as the grid width,
  • the range from (0m,0m) to (1m,1m) corresponds to the first grid
  • the range from (0m,1m) to (1m,2m) corresponds to the second grid, and so on.
  • the gridded A'(0,0) and B'(0,0) are in the grid of the first row and the first column, and C'(2,3) can be in the grid of the second row and the third column. Gerry, thus realizing the conversion from the Cartesian continuous real coordinate system to the discrete coordinate system.
  • the coordinate information about the target point may be determined by the reference reference point (for example, the location of the radar device that collects the point cloud data), which will not be repeated here.
  • two-dimensional rasterization can be performed, and three-dimensional rasterization can also be performed.
  • the three-dimensional rasterization adds height information on the basis of the two-dimensional rasterization.
  • the limited space can be divided into N*M grids, which are generally divided at equal intervals, and the interval size can be configured.
  • a zero-one matrix ie, the above grid matrix
  • Each grid can be represented by coordinates consisting of a unique row number and column number. and the above target point, the grid is encoded as 1, otherwise it is 0, so that the encoded zero-one matrix can be obtained.
  • a sparse processing operation may be performed on the elements in the grid matrix according to the size information of the object to be identified in the target scene to generate a corresponding sparse matrix.
  • the size information about the object to be recognized may be acquired in advance.
  • the size information of the object to be recognized may be determined in combination with the image data synchronously collected from the target point cloud data, and the size information of the object to be recognized may also be roughly estimated based on specific application scenarios. Identify the size information of the object.
  • the object in front of the vehicle can be a vehicle, and its general size information can be determined to be 4m ⁇ 4m.
  • the embodiment of the present disclosure may also determine the size information of the object to be recognized based on other manners, which is not specifically limited in the embodiment of the present disclosure.
  • the related sparse processing operation may be performing at least one expansion processing operation on the target element in the grid matrix (that is, the element representing the existence of the target point at the corresponding grid), and the expansion processing operation here may be performed on the grid matrix. It is performed when the coordinate range of the grid matrix is smaller than the size of the object to be recognized in the target scene, that is, through one or more expansion processing operations, the range of elements representing the existence of the target point at the corresponding grid can be performed step by step.
  • the sparse processing operation in the embodiment of the present disclosure may also be performed on the target element in the grid matrix at least A corrosion processing operation, where the corrosion processing operation can be performed when the coordinate range of the grid matrix is larger than the size of the object to be identified in the target scene, that is, through one or more corrosion processing operations, the representation can be The range of elements in which the target point exists at the corresponding grid is gradually reduced, so that the reduced range of elements can be matched with the object to be identified, thereby realizing the determination of the position.
  • one expansion processing operation which of the following operations is performed: one expansion processing operation, multiple expansion processing operations, one erosion processing operation, and multiple erosion processing operations, depending on the sparse matrix obtained by performing at least one shift processing and logic operation processing Whether the difference between the coordinate range of the target scene and the size of the object to be recognized in the target scene belongs to the preset threshold range, that is, the expansion or erosion processing operation adopted in the present disclosure is based on the constraint of the size information of the object to be recognized to make the information represented by the determined sparse matrix more consistent with the relevant information of the object to be identified.
  • the purpose of the sparse processing whether based on the dilation processing operation or the erosion processing operation is to enable the generated sparse matrix to represent more accurate relevant information of the object to be identified.
  • the above-mentioned dilation processing operation may be implemented based on a shift operation and a logical OR operation, or may be implemented based on convolution followed by negation, and negation after convolution.
  • the two operations use different methods, but the final result of the resulting sparse matrix can be consistent.
  • the above-mentioned erosion processing operation may be implemented based on a shift operation and a logical AND operation, or may be implemented directly based on a convolution operation.
  • the two operations use different methods, the final result of the generated sparse matrix can be the same.
  • 5A is a schematic diagram of a grid matrix obtained after grid processing (corresponding to before uncoding), by performing an eight-neighborhood analysis on each target element (corresponding to a grid with a filling effect) in the grid matrix once Dilation operation, that is, the corresponding sparse matrix 5B can be obtained. It can be seen that, for the target element with the target point at the corresponding grid in 5A, the embodiment of the present disclosure performs an eight-neighbor expansion operation, so that each target element becomes an element set after expansion, and the element The grid width corresponding to the set may match the size of the object to be identified.
  • the expansion operation of the above-mentioned eight neighborhoods may be a process of determining an element whose absolute value of the difference between the abscissa or ordinate of the above-mentioned target element does not exceed 1. Except for the elements at the edge of the grid, generally all elements in the neighborhood of an element are There are eight elements (corresponding to the above element set), the input of the expansion processing result can be the coordinate information of the six target elements, and the output can be the coordinate information of the element set in the eight neighborhoods of the target element, as shown in FIG. 5B .
  • a four-neighbor expansion operation can also be performed, and the latter and other expansion operations are not specifically limited herein.
  • the embodiment of the present disclosure can also perform multiple dilation operations. For example, based on the dilation result shown in FIG. 5B , the dilation operation is performed again to obtain a sparse matrix with a larger range of element sets. No longer.
  • the position of the object to be identified in the target scene can be determined.
  • the embodiments of the present disclosure can be specifically implemented through the following two aspects.
  • the position range of the object to be identified can be determined based on the correspondence between each element in the grid matrix and the coordinate range information of each target point. Specifically, the following steps can be used to achieve:
  • Step 1 Based on the correspondence between each element in the grid matrix and the coordinate range information of each target point, determine the coordinate information of the target point corresponding to each target element in the generated sparse matrix;
  • Step 2 Combine the coordinate information of the target points corresponding to each target element in the sparse matrix to determine the position of the object to be identified in the target scene.
  • each target element in the grid matrix may correspond to multiple target points.
  • the coordinate range information of the target points corresponding to the relevant elements and the multiple target points may be preset. definite.
  • the coordinate information of the target point corresponding to each target element in the sparse matrix can be determined based on the predetermined correspondence between the above-mentioned elements and the coordinate range information of each target point. That is, the processing operation of de-rasterization is performed.
  • the sparse matrix is obtained based on the sparse processing of the elements in the grid matrix that represent the target points at the corresponding grids
  • the values of the target elements in the sparse matrix here can also represent the corresponding A target point exists at the grid.
  • point A'(0,0) and point B'(0,0) indicated by the sparse matrix are in the first row and first column of the grid; point C'(2,3) is in the second row and third column
  • point A'(0,0) and point B'(0,0) indicated by the sparse matrix are in the first row and first column of the grid; point C'(2,3) is in the second row and third column
  • the grid as an example, in the process of de-rasterization, after the first grid (0,0) uses its center to map back to the Cartesian coordinate system, we can get (0.5m, 0.5m), the second row
  • the grid (2,3) in the third column, using its center to map back to the Cartesian coordinate system can get (2.5m, 3.5m), that is, (0.5m, 0.5m) and (2.5m, 3.5m) It is determined as the mapped coordinate information, so that the position of the object to be identified in the target scene can be determined by combining the mapped coordinate information.
  • the embodiments of the present disclosure can not only determine the location range of the object to be recognized based on the approximate relationship between the sparse matrix and the target detection result, but also determine the location range of the object to be recognized based on the trained convolutional neural network.
  • the embodiments of the present disclosure may first perform at least one convolution process on the generated sparse matrix based on the trained convolutional neural network, and then determine the position range of the object to be recognized based on the convolution result obtained by the convolution process.
  • the embodiments of the present disclosure can be implemented by combining shift processing and logical operations, and can also be implemented based on inversion followed by convolution, and convolution followed by inversion.
  • one or more expansion processing operations may be performed based on at least one shift processing and logical OR operation.
  • the size information of the object is determined.
  • the target element representing the existence of the target point at the corresponding grid can be shifted in multiple preset directions to obtain a plurality of corresponding shifted grid matrices.
  • the grid matrix and the plurality of shifted grid matrices corresponding to the first expansion processing operation are logically ORed, so that the sparse matrix after the first expansion processing operation can be obtained.
  • it can be judged whether the coordinate range of the obtained sparse matrix is less than The size of the object to be identified, and whether the corresponding difference is large enough (for example, greater than a preset threshold), if so, the target element in the sparse matrix after the first expansion processing operation can be shifted in multiple preset directions according to the above method.
  • Bit processing and logical OR operation to obtain the sparse matrix after the second expansion processing operation, and so on, until it is determined that the difference between the coordinate range of the newly obtained sparse matrix and the size of the object to be identified in the target scene belongs to the preset value.
  • the threshold range is set, the sparse matrix is determined.
  • the sparse matrix is essentially a zero-one matrix.
  • the number of target elements in the obtained sparse matrix representing the existence of target points at the corresponding grid also increases, and since the grid mapped by the zero-one matrix has width information,
  • the coordinate range corresponding to each target element in the sparse matrix can be used to verify whether the size of the object to be recognized in the target scene is reached, thereby improving the accuracy of subsequent target detection applications.
  • Step 1 Select a shifted grid matrix from a plurality of shifted grid matrices
  • Step 2 Perform a logical OR operation on the grid matrix before the current expansion processing operation and the selected shifted grid matrix to obtain an operation result;
  • Step 3 Repeat the steps of selecting grid matrices that are not involved in the operation from the shifted grid matrices, and performing a logical OR operation on the selected grid matrix and the result of the latest operation, until all the grid matrices are selected.
  • Grid matrix to get the sparse matrix after the current dilation operation.
  • a shifted grid matrix can be selected from the shifted grid matrices.
  • the grid matrix before the current expansion processing operation can be compared with the selected shifted grid matrix.
  • the sparse matrix after the current expansion processing operation can be obtained.
  • the expansion processing operation in this embodiment of the present disclosure may be a four-neighbor expansion operation centered on the target element, an eight-neighbor expansion operation centered on the target element, or other neighborhood processing operation methods.
  • a corresponding neighborhood processing operation mode may be selected based on the size information of the object to be recognized, which is not specifically limited here.
  • the corresponding preset directions of the shift processing are not the same.
  • the grid matrix can be shifted according to the four preset directions.
  • Bit processing which are left shift, right shift, up shift and down shift.
  • the grid matrix can be shifted according to eight preset directions, respectively left shift, right shift. Move, move up, move down, move up and down under the premise of moving left, and move up and down under the premise of moving right.
  • first perform a logical OR operation after determining the shifted grid matrix based on multiple shift directions, first perform a logical OR operation, and then perform multiple logical OR operations on the result. The shift operation in the shift direction is performed, and then the next logical OR operation is performed, and so on, until the dilated sparse matrix is obtained.
  • the grid matrix before encoding shown in FIG. 5A can be converted into the grid matrix after encoding as shown in FIG. 5C , and then the first expansion processing operation is performed in conjunction with FIG. 6A to FIG. 6B .
  • the grid matrix shown in FIG. 5C is taken as a zero-one matrix, the positions of all "1"s in the matrix can represent the grid where the target element is located, and all the "0"s in the matrix can represent the background.
  • the matrix shift may be used to determine the neighborhood of all elements in the zero-one matrix whose element value is 1.
  • the left shift means that the column coordinates corresponding to the elements with the element value of 1 in the zero-one matrix are subtracted by one, as shown in Figure 6A;
  • the right-shift means that the column coordinates corresponding to all the elements in the zero-one matrix with the element value of 1 are added by one;
  • Moving up means adding one to the row coordinates corresponding to all elements whose value is 1 in the zero-one matrix; moving down means adding one to the row coordinates corresponding to all elements in the zero-one matrix having a value of 1.
  • embodiments of the present disclosure may combine the results of all neighborhoods using a matrix logical OR operation.
  • Matrix logical OR operation that is, in the case of receiving two sets of zero-one matrix inputs with the same size, perform logical OR operation on the zero-one in the same position of the two sets of matrices in turn, and the obtained result forms a new zero-one matrix as the output,
  • FIG. 6B A specific example of a logical OR operation is shown in FIG. 6B .
  • the left-shifted grid matrix, the right-shifted grid matrix, the up-shifted grid matrix, and the down-shifted grid matrix can be sequentially selected to participate in the logical OR operation middle. For example, you can first perform a logical OR operation on the grid matrix with the grid matrix after shifting to the left, and the obtained operation result can perform a logical OR operation with the grid matrix after shifting right. The subsequent grid matrix is subjected to a logical OR operation, and the obtained operation result can be subjected to a logical OR operation with the grid matrix after the downshift, so as to obtain the sparse matrix after the first expansion processing operation.
  • the above-mentioned selection order of the grid matrix after translation is only a specific example. In practical applications, it can also be selected in combination with other methods.
  • the logical OR operation is performed after the paired down shift, and the logical OR operation is performed after the left shift and the right shift are paired.
  • the two logical OR operations can be performed synchronously, which can save computing time.
  • the expansion processing operation can be implemented by combining convolution and two inversion processing. Specifically, the following steps can be implemented:
  • Step 1 Perform a first inversion operation on the elements in the grid matrix before the current expansion processing operation to obtain the grid matrix after the first inversion operation;
  • Step 2 Perform at least one convolution operation on the grid matrix after the first inversion operation based on the first preset convolution check to obtain a grid matrix with a preset sparsity after at least one convolution operation; the preset sparsity Determined by the size information of the object to be recognized in the target scene;
  • Step 3 Perform a second inversion operation on the elements in the grid matrix with the preset sparsity after at least one convolution operation to obtain a sparse matrix.
  • the expansion processing operation can be realized by the operations of convolution followed by inversion and inversion after convolution, and the obtained sparse matrix can also represent the relevant information of the object to be recognized to a certain extent.
  • the above convolution operation can be automatically combined with the convolutional neural network used in subsequent applications such as target detection, so the detection efficiency can be improved to a certain extent.
  • the inversion operation may be implemented based on a convolution operation, or may be implemented based on other inversion operation modes.
  • a convolution operation can be used to implement the specific implementation.
  • the convolution operation can be performed on other elements except the target element in the grid matrix before the current expansion processing operation based on the second preset convolution check to obtain the first inversion element
  • the second preset convolution can also be based on kernel, perform the convolution operation on the target element in the grid matrix before the current expansion processing operation, and obtain the second inversion element.
  • the first inversion element can be determined.
  • At least one convolution operation may be performed on the grid matrix after the first inversion operation by using the first preset convolution check, so as to obtain a grid matrix with a preset sparsity.
  • the expansion processing operation can be used as a means of increasing the number of target elements in the grid matrix
  • the above convolution operation can be regarded as a process of reducing the number of target elements in the grid matrix (corresponding to the erosion processing operation)
  • the convolution operation in the embodiment of the present disclosure is performed on the grid matrix after the first inversion operation, using the inversion operation combined with the erosion processing operation, and then performing the inversion operation again is equivalent to the above expansion The equivalent operation of the processing operation.
  • the grid matrix after the first inversion operation is subjected to a convolution operation with the first preset convolution kernel to obtain the grid matrix after the first convolution operation.
  • the grid matrix after the first convolution operation and the first preset convolution kernel can be convolved again to obtain the grid matrix after the second convolution operation. lattice matrix, and so on, until a lattice matrix with a preset sparsity can be determined.
  • the above sparsity may be determined by the proportion distribution of target elements and non-target elements in the grid matrix.
  • the convolution operation in the embodiment of the present disclosure may be one time or multiple times.
  • the specific operation process of the first convolution operation can be described, including the following steps:
  • Step 1 For the first convolution operation, select each grid sub-matrix from the grid matrix after the first inversion operation according to the size of the first preset convolution kernel and the preset step size;
  • Step 2 For each selected grid sub-matrix, perform a product operation on the grid sub-matrix and the weight matrix to obtain a first operation result, and perform an addition operation on the first operation result and the offset to obtain a second operation result. operation result;
  • Step 3 Determine the grid matrix after the first convolution operation based on the second operation result corresponding to each grid sub-matrix.
  • the grid matrix after the first inversion operation can be traversed in a traversal manner, so that for each grid sub-matrix traversed, the grid sub-matrix and the weight matrix can be multiplied to obtain the first operation result, and add the first operation result and the offset to obtain the second operation result.
  • the second operation result corresponding to each grid sub-matrix is combined into the corresponding matrix elements, and the first operation result can be obtained.
  • the grid matrix after the convolution operation can be traversed in a traversal manner, so that for each grid sub-matrix traversed, the grid sub-matrix and the weight matrix can be multiplied to obtain the first operation result, and add the first operation result and the offset to obtain the second operation result.
  • the encoded grid matrix shown in FIG. 5C is still taken as an example here, and the expansion processing operation is illustrated in conjunction with FIGS. 7A to 7B .
  • a 1*1 convolution kernel (that is, a second preset convolution kernel) can be used to implement the first inversion operation.
  • the weight of the second preset convolution kernel is -1 and the offset is 1.
  • a 3*3 convolution kernel ie, the first preset convolution kernel
  • a linear rectification function Rectified Linear Unit, ReLU
  • Each weight value included in the above-mentioned first preset convolution kernel weight value matrix is 1, and the offset is 8.
  • the formula ⁇ output ReLU(input grid matrix after the first inversion operation* weight + bias) ⁇ to achieve the above-mentioned corrosion processing operation.
  • each nested layer of the convolutional network with the second preset convolution kernel can superimpose an erosion operation, so that a grid matrix with a fixed sparsity can be obtained, and the inversion operation again can be equivalent to an expansion processing operation. Thereby, the generation of sparse matrix can be realized.
  • the embodiments of the present disclosure may be implemented in combination with shift processing and logical operations, and may also be implemented based on convolution operations.
  • one or more corrosion processing operations can be performed based on at least one shift processing and logical AND operation.
  • the specific number of corrosion processing operations can be combined with the target scene to be identified.
  • the size information of the object is determined.
  • the grid matrix shift processing can also be performed first.
  • the difference from the above expansion processing is that here
  • the logical operation of which can be a logical AND operation on the shifted grid matrix.
  • the corrosion processing operation in the embodiment of the present disclosure may be four-neighbor corrosion centered on the target element, eight-area corrosion centered on the target element, or other field processing operations.
  • the corresponding domain processing operation mode can be selected based on the size information of the object to be recognized, which is not specifically limited here.
  • the erosion processing operation can be implemented in combination with the convolution processing, which can be specifically implemented by the following steps:
  • Step 1 Perform at least one convolution operation on the grid matrix based on the third preset convolution check to obtain a grid matrix with a preset sparsity after at least one convolution operation; the preset sparsity is determined by the target scene to be identified. The size information of the object is determined;
  • Step 2 Determine the grid matrix with the preset sparsity after at least one convolution operation as the sparse matrix corresponding to the object to be recognized.
  • the above convolution operation can be regarded as a process of reducing the number of target elements in the grid matrix, that is, an erosion process.
  • the grid matrix and the first preset convolution kernel are subjected to convolution operation to obtain the grid matrix after the first convolution operation, and the sparsity of the grid matrix after the first convolution operation is judged.
  • the grid matrix after the first convolution operation and the third preset convolution kernel can be convolved again to obtain the grid matrix after the second convolution operation, and so on.
  • a grid matrix with a preset sparsity can be determined, that is, a sparse matrix corresponding to the object to be recognized is obtained.
  • the convolution operation in this embodiment of the present disclosure may be performed once or multiple times.
  • the specific process of the convolution operation please refer to the relevant description of implementing expansion processing based on convolution and inversion in the first aspect above, which will not be repeated here.
  • convolutional neural networks with different data processing bit widths can be used to generate sparse matrices.
  • 4 bits can be used to represent the input, output, and computational parameters of the network Parameters, such as the element value (0 or 1) of the grid matrix, weights, offsets, etc., in addition, can also be represented by 8bit to adapt to the network processing bit width and improve the operation efficiency.
  • the point cloud data to be processed collected by the radar device in the target scene can be screened based on the effective perception range information corresponding to the target scene, and the screened target point cloud data is the corresponding valid point cloud data in the target scene. Therefore, based on the filtered target point cloud data, the detection calculation is performed in the target scene, which can reduce the amount of calculation, improve the calculation efficiency, and the utilization rate of computing resources in the target scene.
  • the writing order of each step does not mean a strict execution order but constitutes any limitation on the implementation process, and the specific execution order of each step should be based on its function and possible Internal logic is determined.
  • the embodiment of the present disclosure also provides a point cloud data processing device corresponding to the point cloud data processing method. Similar, therefore, the implementation of the apparatus may refer to the implementation of the method, and repeated descriptions will not be repeated.
  • the device includes: an acquisition module 801 , a screening module 802 , and a detection module 803 ; wherein,
  • an acquisition module 801, configured to acquire point cloud data to be processed obtained by scanning the radar device in the target scene;
  • a screening module 802 configured to screen out target point cloud data from the to-be-processed point cloud data according to the effective perception range information corresponding to the target scene;
  • the detection module 803 is configured to detect the target point cloud data to obtain a detection result.
  • the screening module 802 is further configured to determine the effective perception range information corresponding to the target scene according to the following manner:
  • the effective sensing range information matched with the computing resource information is determined.
  • the screening module 802 when screening out target point cloud data from the to-be-processed point cloud data according to the effective perception range information corresponding to the target scene, is used for:
  • target point cloud data is filtered out from the point cloud data to be processed.
  • the screening module 802 when determining the effective coordinate range based on the effective sensing range information, is used to:
  • the effective coordinate range corresponding to the target scene is determined.
  • the screening module 802 when screening out target point cloud data from the to-be-processed point cloud data based on the valid coordinate range, is used to:
  • the radar scanning points whose corresponding coordinate information is located within the effective coordinate range are used as the radar scanning points in the target point cloud data.
  • the screening module 802 is further configured to determine the coordinate information of the reference position point in the target scene according to the following manner:
  • the coordinate information of the reference position point matching the road type is obtained.
  • the detection result includes the position of the object to be identified in the target scene
  • the detection module 803 when detecting the target point cloud data and obtaining a detection result, is used for:
  • the position of the object to be identified in the target scene is determined.
  • the detection module 803 is used for generating a sparse matrix corresponding to the object to be identified according to the grid matrix and the size information of the object to be identified in the target scene. :
  • At least one expansion processing operation or erosion processing operation is performed on the target element in the grid matrix to generate a corresponding object to be identified.
  • the value of the target element indicates that the target point exists at the corresponding grid.
  • the detection module 803 when performing the expansion processing operation or the erosion processing operation, is used for: shift processing and logical operation processing, and the coordinate range of the sparse matrix is the same as that of the object to be identified.
  • the difference between the sizes is within a preset threshold.
  • the detection module 803 performs at least one expansion processing operation on the elements in the grid matrix according to the grid matrix and the size information of the object to be identified in the target scene. , when generating a sparse matrix corresponding to the object to be identified, used for:
  • a second inversion operation is performed on the elements in the grid matrix with the preset sparsity after the at least one convolution operation to obtain the sparse matrix.
  • the detection module 803 performs the first inversion operation on the elements in the grid matrix before the current expansion processing operation to obtain the grid matrix after the first inversion operation, using At:
  • a convolution operation is performed on other elements except the target element in the grid matrix before the current expansion processing operation to obtain the first inversion element, and based on the second preset convolution kernel, perform the convolution operation on the target element in the grid matrix before the current expansion processing operation to obtain the second inversion element;
  • the detection module 803 performs at least one convolution operation on the grid matrix after the first inversion operation based on the first preset convolution check, to obtain at least one convolution operation.
  • a raster matrix with a preset sparsity is used:
  • For the first convolution operation performing a convolution operation on the grid matrix after the first inversion operation and the first preset convolution kernel to obtain the grid matrix after the first convolution operation;
  • the detection module 803 has a weight matrix and an offset corresponding to the weight matrix in the first preset convolution kernel; for the first convolution operation, the first The grid matrix after the reverse operation is subjected to a convolution operation with the first preset convolution kernel, and when the grid matrix after the first convolution operation is obtained, it is used for:
  • each grid sub-matrix is selected from the grid matrix after the first inversion operation
  • For each selected grid sub-matrix perform a product operation on the grid sub-matrix and the weight matrix to obtain a first operation result, and add the first operation result and the offset operation to obtain the second operation result;
  • the grid matrix after the first convolution operation is determined.
  • the detection module 803 performs at least one corrosion processing operation on the elements in the grid matrix according to the grid matrix and the size information of the object to be identified in the target scene. , when generating a sparse matrix corresponding to the object to be identified, used for:
  • the grid matrix with the preset sparsity after the at least one convolution operation is determined as the sparse matrix corresponding to the object to be identified.
  • the detection module 803 when performing grid processing on the target point cloud data to obtain a grid matrix, is used for:
  • the detection module 803 when determining the position range of the object to be identified in the target scene based on the generated sparse matrix, is used for:
  • the coordinate information of the target points corresponding to each of the target elements in the sparse matrix is combined to determine the position of the object to be identified in the target scene.
  • the detection module 803 when determining the position of the object to be identified in the target scene based on the generated sparse matrix, is configured to:
  • the position of the object to be identified in the target scene is determined.
  • the device further includes a control module 804, configured to: after detecting the target point cloud data and obtaining a detection result, control and set the intelligent driving of the radar device based on the detection result. equipment.
  • the point cloud data to be processed collected by the radar device in the target scene can be screened based on the effective perception range information corresponding to the target scene, and the screened target point cloud data is the target point cloud data corresponding to the target scene Therefore, based on the filtered point cloud data, the detection calculation is performed in the target scene, which can reduce the amount of calculation, improve the calculation efficiency, and the utilization rate of computing resources in the target scene.
  • an embodiment of the present disclosure further provides a computer device, including a processor 901 , a memory 902 and a bus 903 .
  • the memory 902 includes a memory 9021 and an external memory 9022 for storing execution instructions; the memory 9021 here is also called an internal memory, and is used for temporarily storing the operation data in the processor 901 and the data exchanged with the external memory 9022 such as a hard disk.
  • the processor 901 exchanges data with the external memory 9022 through the memory 9021, and when the computer device 900 is running, the processor 901 and the memory 902 communicate through the bus 903, so that the processor 901 executes the following instructions:
  • Embodiments of the present disclosure further provide a computer-readable storage medium, where a computer program stored on the computer program is executed by a processor to execute the point cloud data processing method described in the foregoing method embodiments.
  • the storage medium may be a volatile or non-volatile computer-readable storage medium.
  • the computer program product of the method for processing point cloud data provided by the embodiments of the present disclosure includes a computer-readable storage medium storing program codes, and the instructions included in the program codes can be used to execute the point cloud data described in the above method embodiments.
  • the processing method reference may be made to the foregoing method embodiments, and details are not described herein again.
  • Embodiments of the present disclosure also provide a computer program, which implements any one of the methods in the foregoing embodiments when the computer program is executed by a processor.
  • the computer program product can be specifically implemented by hardware, software or a combination thereof.
  • the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), etc. Wait.
  • the units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the functions, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a processor-executable non-volatile computer-readable storage medium.
  • the computer software products are stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present disclosure.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes .

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Electromagnetism (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

本公开提供了一种点云数据处理方法及装置，该方法包括：获取雷达装置在目标场景下扫描得到的待处理点云数据；根据所述目标场景对应的有效感知范围信息，从所述待处理点云数据中筛选出目标点云数据；对所述目标点云数据进行检测，得到检测结果。

Description

一种点云数据处理方法及装置
相关申请的交叉引用
本专利申请要求于2020年7月22日提交的、申请号为202010713989.6、发明名称为“一种点云数据处理方法及装置”的中国专利申请的优先权，该申请以引用的方式并入本文中。
技术领域
本公开涉及信息处理技术领域，具体而言，涉及一种点云数据处理方法及装置。
背景技术
随着科学技术的发展，激光雷达以其精确的测距能力，被广泛用于自动驾驶、无人机勘探、地图测绘等领域。以自动驾驶为例，在自动驾驶的应用场景中，一般是对激光雷达采集的点云数据进行处理，以实现对于车辆的定位和障碍物的识别，在对点云数据进行处理时，一般所耗费的计算资源较多，然而由于对点云数据进行处理的电子设备的计算资源有限，且并非所有的点云数据对于车辆的定位和障碍物的识别都有作用，因此这种计算方法的计算效率较低，且对于计算资源的利用率较低。
发明内容
本公开实施例至少提供一种点云数据处理方法及装置。
第一方面，本公开实施例提供了一种点云数据处理方法，包括：获取雷达装置在目标场景下扫描得到的待处理点云数据；根据所述目标场景对应的有效感知范围信息，从所述待处理点云数据中筛选出目标点云数据；对所述目标点云数据进行检测，得到检测结果。
基于上述方法，可以基于目标场景对应的有效感知范围信息，对目标场景下雷达装置采集的待处理点云数据进行筛选，所筛选出的目标点云数据为在目标场景中对应的目标点云数据，因此，基于筛选出的点云数据，再在目标场景下进行检测计算，可以降低计算量，提高计算效率，及目标场景下计算资源的利用率。
一种可能的实施方式中，根据以下方式确定所述目标场景对应的有效感知范围信息：获取处理设备的计算资源信息；基于所述计算资源信息，确定与所述计算资源信息所匹配的所述有效感知范围信息。
通过这种方式，可以为同一目标场景下的处理待处理点云数据的不同的电子设备确定不同的有效感知范围信息，从而可以适应于不同的电子设备。
一种可能的实施方式中，根据所述目标场景对应的有效感知范围信息，从所述待处理点云数据中筛选出目标点云数据，包括：基于所述有效感知范围信息，确定有效坐标范围；基于所述有效坐标范围，从所述待处理点云数据中筛选出目标点云数据。
一种可能的实施方式中，所述基于所述有效感知范围信息，确定有效坐标范围，包括：基于参考位置点在所述有效感知范围内的位置信息、以及所述参考位置点在所述目标场景中的坐标信息，确定所述目标场景对应的有效坐标范围。
一种可能的实施方式中，所述基于所述有效坐标范围，从所述待处理点云数据中筛选出目标点云数据，包括：将对应的坐标信息位于所述有效坐标范围内的雷达扫描点作为所述目标点云数据中的雷达扫描点。
一种可能的实施方式中，根据以下方式确定所述参考位置点在所述目标场景中的坐标信息：获取设置所述雷达装置的智能行驶设备的位置信息；基于所述智能行驶设备的 位置信息确定所述智能行驶设备所在道路的道路类型；获取与所述道路类型相匹配的参考位置点的坐标信息作为所述参考位置点在所述目标场景中的坐标信息。
这里，智能行驶设备位于不同道路类型的道路上时所需处理的点云数据可能不同，因此，通过获取与道路类型相匹配的参考位置点的坐标信息，可以为智能行驶设备确定适配其当前所在的道路类型的有效坐标范围，从而筛选出对应道路类型下的点云数据，从而提高智能行驶设备在不同道路类型下检测结果的准确率。
一种可能的实施方式中，所述检测结果包括在所述目标场景中待识别对象的位置；所述对所述目标点云数据进行检测，得到检测结果，包括：对所述目标点云数据进行栅格化处理，得到栅格矩阵；所述栅格矩阵中每个元素的值用于表征对应的栅格处是否存在目标点；根据所述栅格矩阵以及所述目标场景中的待识别对象的尺寸信息，生成与所述待识别对象对应的稀疏矩阵；基于生成的所述稀疏矩阵，确定所述待识别对象在所述目标场景中的位置。
一种可能的实施方式中，所述根据所述栅格矩阵以及所述目标场景中的待识别对象的尺寸信息，生成与所述待识别对象对应的稀疏矩阵，包括：根据所述栅格矩阵以及所述目标场景中的待识别对象的尺寸信息，对所述栅格矩阵中的目标元素进行至少一次膨胀处理操作或者腐蚀处理操作，生成与所述待识别对象对应的稀疏矩阵；其中，所述目标元素的值表征对应的栅格处存在所述目标点。
一种可能的实施方式中，所述膨胀处理操作或者腐蚀处理操作包括移位处理以及逻辑运算处理，所述稀疏矩阵的坐标范围与所述待识别对象的尺寸之间的差值在预设阈值范围内。
一种可能的实施方式中，根据所述栅格矩阵以及所述目标场景中的待识别对象的尺寸信息，对所述栅格矩阵中的元素进行至少一次膨胀处理操作，生成与所述待识别对象对应的稀疏矩阵，包括：对当前次膨胀处理操作前的栅格矩阵中的元素进行第一取反操作，得到第一取反操作后的栅格矩阵；基于第一预设卷积核对所述第一取反操作后的栅格矩阵进行至少一次卷积运算，得到至少一次卷积运算后的具有预设稀疏度的栅格矩阵；所述预设稀疏度由所述目标场景中的待识别对象的尺寸信息来确定；对所述至少一次卷积运算后的具有预设稀疏度的栅格矩阵中的元素进行第二取反操作，得到所述稀疏矩阵。
一种可能的实施方式中，所述对当前次膨胀处理操作前的栅格矩阵中的元素进行第一取反操作，得到第一取反操作后的栅格矩阵，包括：基于第二预设卷积核，对当前次膨胀处理操作前的栅格矩阵中除所述目标元素外的其它元素进行卷积运算，得到第一取反元素，以及基于第二预设卷积核，对当前次膨胀处理操作前的栅格矩阵中的目标元素进行卷积运算，得到第二取反元素；基于所述第一取反元素和所述第二取反元素，得到第一取反操作后的栅格矩阵。
一种可能的实施方式中，所述基于第一预设卷积核对所述第一取反操作后的栅格矩阵进行至少一次卷积运算，得到至少一次卷积运算后的具有预设稀疏度的栅格矩阵，包括：针对首次卷积运算，将所述第一取反操作后的栅格矩阵与所述第一预设卷积核进行卷积运算，得到首次卷积运算后的栅格矩阵；重复执行将上一次卷积运算后的栅格矩阵与所述第一预设卷积核进行卷积运算，得到当前次卷积运算后的栅格矩阵的步骤，直至得到具有所述预设稀疏度的栅格矩阵。
一种可能的实施方式中，所述第一预设卷积核具有权值矩阵以及与该权值矩阵对应的偏置量；针对首次卷积运算，将所述第一取反操作后的栅格矩阵与所述第一预设卷积核进行卷积运算，得到首次卷积运算后的栅格矩阵，包括：针对首次卷积运算，按照第一预设卷积核的尺寸以及预设步长，从所述第一取反操作后的栅格矩阵中选取每个栅格子矩阵；针对选取的每个所述栅格子矩阵，将该栅格子矩阵与所述权值矩阵进行乘积运算，得到第一运算结果，并将所述第一运算结果与所述偏置量进行加法运算，得到第二运算结果；基于各个所述栅格子矩阵对应的第二运算结果，确定首次卷积运算后的栅格 矩阵。
一种可能的实施方式中，根据所述栅格矩阵以及所述目标场景中的待识别对象的尺寸信息，对所述栅格矩阵中的元素进行至少一次腐蚀处理操作，生成与所述待识别对象对应的稀疏矩阵，包括：基于第三预设卷积核对待处理的栅格矩阵进行至少一次卷积运算，得到至少一次卷积运算后的具有预设稀疏度的栅格矩阵；所述预设稀疏度由所述目标场景中的待识别对象的尺寸信息来确定；将所述至少一次卷积运算后的具有预设稀疏度的栅格矩阵，确定为与所述待识别对象对应的稀疏矩阵。
一种可能的实施方式中，对所述目标点云数据进行栅格化处理，得到栅格矩阵，包括：对所述目标点云数据进行栅格化处理，得到栅格矩阵以及该栅格矩阵中各个元素与各个目标点坐标范围信息之间的对应关系；所述基于生成的所述稀疏矩阵，确定所述待识别对象在所述目标场景中的位置范围，包括：基于所述栅格矩阵中各个元素与各个目标点坐标范围信息之间的对应关系，确定生成的所述稀疏矩阵中每个目标元素所对应的目标点的坐标信息；将所述稀疏矩阵中各个所述目标元素所对应的目标点的坐标信息进行组合，确定所述待识别对象在所述目标场景中的位置。
一种可能的实施方式中，所述基于生成的所述稀疏矩阵，确定所述待识别对象在所述目标场景中的位置，包括：基于已训练的卷积神经网络对生成的所述稀疏矩阵中的每个目标元素进行至少一次卷积处理，得到卷积结果；基于所述卷积结果，确定所述待识别对象在所述目标场景中的位置。
一种可能的实施方式中，在对所述目标点云数据进行检测，得到检测结果之后，所述方法还包括：基于所述检测结果控制设置所述雷达装置的智能行驶设备。
第二方面，本公开实施例还提供一种点云数据处理装置，包括：获取模块，用于获取雷达装置在目标场景下扫描得到的待处理点云数据；筛选模块，用于根据所述目标场景对应的有效感知范围信息，从所述待处理点云数据中筛选出目标点云数据；检测模块，用于对所述目标点云数据进行检测，得到检测结果。
第三方面，本公开实施例还提供一种计算机设备，包括处理器、存储器和总线，所述存储器存储有所述处理器可执行的机器可读指令，当计算机设备运行时，所述处理器与所述存储器之间通过总线通信，所述机器可读指令被所述处理器执行时执行上述第一方面，或第一方面中任一种可能的实施方式中的步骤。
第四方面，本公开实施例还提供一种计算机可读存储介质，其上存储的计算机程序被处理器运行时执行上述第一方面，或第一方面中任一种可能的实施方式中的步骤。
关于上述点云数据处理装置、计算机设备、及计算机可读存储介质的效果描述参见上述点云数据处理方法的说明，这里不再赘述。
为使本公开的上述目的、特征和优点能更明显易懂，下文特举较佳实施例，并配合所附附图，作详细说明如下。
附图说明
图1示出了本公开实施例所提供的一种点云数据处理方法的流程图；
图2示出了本公开实施例所提供的一种长方体的各个位置点的坐标示意图；
图3示出了本公开实施例所提供的一种确定所述参考位置点的坐标信息的方法的流程图；
图4示出了本公开实施例所提供的一种检测结果确定方法的流程图；
图5A示出了本公开实施例所提供的一种编码前的栅格矩阵的示意图；
图5B示出了本公开实施例所提供的一种稀疏矩阵的示意图；
图5C示出了本公开实施例所提供的一种编码后的栅格矩阵的示意图；
图6A示出了本公开实施例所提供的一种左移后的栅格矩阵的示意图；
图6B示出了本公开实施例所提供的一种逻辑或运算的示意图；
图7A示出了本公开实施例所提供的一种第一取反操作后的栅格矩阵的示意图；
图7B示出了本公开实施例所提供的一种卷积运算后的栅格矩阵的示意图；
图8示出了本公开实施例所提供的一种点云数据处理装置的架构示意图；
图9示出了本公开实施例所提供的计算机设备的结构示意图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚，下面将结合本公开实施例中附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本公开一部分实施例，而不是全部的实施例。通常在此处附图中描述和示出的本公开实施例的组件可以以各种不同的配置来布置和设计。因此，以下对在附图中提供的本公开的实施例的详细描述并非旨在限制要求保护的本公开的范围，而是仅仅表示本公开的选定实施例。基于本公开的实施例，本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本公开保护的范围。
相关技术中，在对点云数据进行处理时，一般所耗费的计算资源比较多，但是并非采集的所有点云数据对于所需要的计算结果都有作用，一部分不必要的点云数据参与到计算过程中，导致计算资源的浪费。
基于此，本公开提供了一种点云数据处理方法及装置，可以基于目标场景对应的有效感知范围信息，对目标场景下雷达装置采集的待处理点云数据进行筛选，所筛选出的目标点云数据为在目标场景中有效的点云数据，因此，基于筛选出的目标点云数据，再在目标场景下进行检测计算，可以降低计算量，提高计算效率，及目标场景下计算资源的利用率。
针对以上方案所存在的缺陷，均是发明人在经过实践并仔细研究后得出的结果，因此，上述问题的发现过程以及下文中本公开针对上述问题所提出的解决方案，都应该是发明人在本公开过程中对本公开做出的贡献。
应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步定义和解释。
为便于对本实施例进行理解，首先对本公开实施例所公开的一种点云数据处理方法进行详细介绍，本公开实施例所提供的点云数据处理方法的执行主体一般为具有一定计算能力的计算机设备，该计算机设备例如包括：终端设备或服务器或其它处理设备，终端设备可以为用户设备(User Equipment，UE)、移动设备、用户终端、终端、个人数字处理(Personal Digital Assistant，PDA)、计算设备、车载设备等。在一些可能的实现方式中，该点云数据处理方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。
参见图1所示，本公开实施例提供一种点云数据处理方法，所述方法包括步骤101至步骤103，其中：
步骤101、获取雷达装置在目标场景下扫描得到的待处理点云数据。
步骤102、根据所述目标场景对应的有效感知范围信息，从所述待处理点云数据中筛选出目标点云数据。
步骤103、对所述目标点云数据进行检测，得到检测结果。
以下是对上述步骤101至步骤103的详细介绍。
所述雷达装置可以部署在智能行驶设备上，在智能行驶设备的行驶过程中，雷达装置可以进行扫描，获得待处理点云数据。
所述有效感知范围信息可以包括参考坐标系下各个坐标维度上的坐标阈值，所述参考坐标系为三维坐标系。
示例性的，有效感知范围信息可以是构成长方体的描述信息，例如，该描述信息可以为该长方体的长、宽、高在参考坐标系下各个坐标维度上的坐标阈值，包括x轴方向 上的最大值x_max和最小值x_min，y轴方向上的最大值y_max和最小值y_min，以及z轴方向上的最大值z_max和最小值z_min。
示例性的，图2示出了基于x轴方向上的最大值x_max和最小值x_min、y轴方向上的最大值y_max和最小值y_min、以及z轴方向上的最大值z_max和最小值z_min构成的长方体的各个位置点的坐标，坐标原点可以是长方体左下顶点，其坐标值为(x_min，y_min，z_min)。
在另外一种可能的实施方式中，有效感知范围信息还可以是球体、正方体等的描述信息，例如，只给出球体的半径或者正方体的长、宽、高，具体的有效感知范围信息可以根据实际的应用场景进行描述，对此本公开并不限制。
具体实施中，由于雷达装置的扫描范围是有限的，例如最远的扫描距离为200米，因此，为了保证有效感知范围对于待处理点云数据的约束，可以预先设置对于有效感知范围的约束条件，示例性的可以设置x_max、y_max、z_max的取值均小于或等于200米。
在一种可能的应用场景中，基于点云数据的计算是基于点云数据对应的空间体素进行的运算，例如基于点云的三维空间信息逐层次学习网络(VoxelNet)，因此，在这种应用场景下，在限制参考雷达扫描点在参考坐标系下各个坐标维度上的坐标阈值的情况下，还可以限制参考雷达扫描点在各个坐标维度上的空间体素的个数不超过空间体素阈值。
示例性的，各个坐标维度上的空间体素个数可以通过如下公式进行计算：
N_x＝(x_max–x_min)/x_gridsize；
N_y＝(y_max–y_min)/y_gridsize；
N_z＝(z_max–z_min)/z_gridsize。
其中，x_gridsize、y_gridsize、z_gridsize分别表示预先设置的各个维度对应的分辨率，N_x表示x轴方向上的空间体素个数，N_y表示y轴方向上的空间体素个数，N_z表示z轴方向上的空间体素个数。
在另外一种可能的应用场景中，基于点云数据的计算还可能是基于俯视图面积范围内的点云数据进行计算的算法，例如基于点云的快速目标检测框架(PointPillars)，因此，还可以限制俯视体素面积，例如可以限制N_x*N_y的值。
在一种可能的实施方式中，在确定所述目标场景对应的有效感知范围信息时，可以获取预先基于实验取得的有效感知范围信息，该有效感知范围信息在目标场景内可以作为预先设置的且固定不变的值，且该有限感知范围信息也遵循上述限制条件。
在另外一种可能的实施方式中，在确定目标场景对应的有效感知范围信息时，还可以先获取处理设备的计算资源信息；然后基于所述计算资源信息，确定与所述计算资源信息所匹配的所述有效感知范围信息。
其中，所述计算资源信息包括以下信息中的至少一种：中央处理器CPU的内存、图形处理器GPU的显存、现场可编程逻辑门阵列FPGA的计算资源。
具体的，在基于计算资源信息，确定与计算资源信息所匹配的有效感知范围信息时，可以预先设置各个等级的计算资源信息与有效感知范围信息的对应关系，然后当本公开所提供的方法应用于不同的电子设备时，可以基于该对照关系，查找与该电子设备的计算资源信息相匹配的有效感知范围信息，或者，当检测到电子设备的计算资源信息发生变化时，可以动态调整有效感知范围信息。
以计算资源信息包括中央处理器CPU的内存为例，各个等级的计算资源信息与有效感知范围信息的对应关系可以如下表1所示：
表1
Figure PCTCN2021102856-appb-000001
其中，上述各个等级的计算资源信息与有效感知范围信息的对应关系可以是预先通过实验测试所得。
通过这种方式，可以为同一目标场景下处理待处理点云数据的不同的电子设备确定不同的有效感知范围信息，从而可以适应于不同的电子设备。
在一种可能的实施方式中，在根据目标场景对应的有效感知范围信息，从待处理点云数据中筛选出目标点云数据时，可以先基于有效感知范围信息，确定有效坐标范围，然后基于有效坐标范围，从待处理点云数据中筛选出目标点云数据。
这里，可能包含两种情况：有效感知范围信息和有效坐标范围都固定不变；有效坐标范围可以根据有效感知范围信息的改变而改变。
针对第一种情况，示例性的，有效感知范围信息可以是长方体的描述信息，包括长方体的长宽高，以雷达装置作为长方体的体对角线的交点，由于长方体的体对角线交点的位置不变，则长方体固定不变，长方体内的坐标范围为有效坐标范围，因此有效坐标范围也固定不变。
针对第二种情况，在基于有效感知范围信息，确定有效坐标范围时，可以基于参考位置点在所述有效感知范围内的位置信息、以及所述参考位置点在所述目标场景中的坐标信息，确定所述目标场景对应的有效坐标范围。
示例性的，有效感知范围信息可以是长方体的描述信息，参考位置点可以是长方体的体对角线的交点，则随着参考位置点的改变，在不同的目标场景下有效感知范围信息也会发生改变，因此，对应的有效坐标范围也会发生改变。
其中，所述参考位置点在目标场景中的坐标信息可以是参考位置点在目标场景对应的雷达坐标系下的坐标信息，所述雷达坐标系可以是以用于在目标场景下采集点云数据的雷达装置为坐标原点建立的三维坐标系。
若所述有效感知范围信息为以长方体的描述信息，则参考位置点可以是长方体的体对角线的交点，若有效感知范围信息为球体的描述信息，则参考位置点可以是球体的球心，或者，参考位置点可以是有效感知范围信息内的任意一个参考雷达扫描点。
具体实施中，在基于参考位置点在所述有效感知范围内的位置信息、以及所述参考位置点在所述目标场景中的坐标信息，确定所述目标场景对应的有效坐标范围时，可以基于所述参考位置点在雷达坐标系下的坐标信息，将所述有效感知范围信息中在参考坐标系下的各个坐标维度上的坐标阈值转换为在所述雷达坐标系下各个坐标维度上的坐标阈值。
具体的，参考位置点在参考坐标系下可以具有对应的第一坐标信息，在雷达坐标系下可以具有对应的第二坐标信息，基于参考位置点的第一坐标信息和第二坐标信息，可以确定参考坐标系与雷达坐标系之间的转换关系，基于该转换关系，可以将所述有效感知范围信息中的参考雷达扫描点在参考坐标系下各个坐标维度上的坐标阈值转换为在所述雷达坐标系下各个坐标维度上的坐标阈值。
在另外一种可能的实施方式中，可以先确定有效感知范围信息中的参考雷达扫描点在参考坐标系下各个坐标维度上的坐标阈值对应的阈值坐标点与参考位置点之间的相对位置关系，然后基于该相对位置关系，确定有效感知范围信息中的参考雷达扫描点在 参考坐标系下各个坐标维度上的坐标阈值在雷达坐标系下各个坐标维度上的坐标阈值。
这里，当参考位置点的坐标信息发生改变之后，基于参考位置点的坐标信息确定的有效感知范围信息中的参考雷达扫描点在雷达坐标系下各个坐标维度上的坐标阈值也会相应发生改变，即目标场景对应的有效坐标范围也会发生改变，因此可以通过控制参考位置点的坐标信息，实现对于不同目标场景中有效坐标范围的控制。
在一种可能的实施方式中，在基于所述有效坐标范围，从所述待处理点云数据中筛选出目标点云数据时，可以将对应的坐标信息位于所述有效坐标范围内的雷达扫描点作为所述目标点云数据中的雷达扫描点。
具体的，雷达扫描点在进行存储时，可以存储有雷达扫描点的三维坐标信息，然后基于雷达扫描点的三维坐标信息，可以判断该雷达扫描点是否位于有效坐标范围内。
示例性的，若雷达扫描点的三维坐标信息为(x，y，z)，则在判断该雷达扫描点是否为目标点云数据中的雷达扫描点时，可以判断所述雷达扫描点的三维坐标信息是否满足以下条件：
x_min<x<x_max且y_min<y<y_max且z_min<z<z_max。
下面，将结合具体的应用场景，对上述点云数据处理方法的应用展开介绍。在一种可能的实施方式中，上述点云数据处理方法可以应用于自动驾驶场景中。
在一种可能的应用场景中，智能行驶设备设置有雷达装置，在确定参考位置点的坐标信息时，可以通过如图3所述的方法来确定所述参考位置点的坐标信息，该方法包括以下步骤301至步骤303。
步骤301、获取设置所述雷达装置的智能行驶设备的位置信息。
在获取智能行驶设备的位置信息时，例如可以基于全球定位系统(Global Positioning System，GPS)进行获取，对于其他可以获取智能行驶设备位置信息的方式本公开也并不限制。
步骤302、基于所述智能行驶设备的位置信息确定所述智能行驶设备所在道路的道路类型。
具体实施中，可以预先设置智能行驶设备可行驶范围内每一段道路的道路类型，所述道路类型例如可以包括十字路口、丁字路口、高速路、停车场等，基于所述智能行驶设备的位置信息可以确定所述智能行驶设备所在的道路，然后可以根据预先设置的智能行驶设备可行驶范围内每一段道路的道路类型，确定智能行驶设备所在道路的道路类型。
步骤303、获取与所述道路类型相匹配的参考位置点的坐标信息。
不同道路类型所需重点处理的点云数据的位置可能不同，例如若智能行驶设备位于高速路上时，智能行驶设备所需处理的点云数据可能是智能行驶设备前方的点云数据，若智能行驶设备位于十字路口时，智能行驶设备所需处理的点云数据可能是智能行驶设备四周的点云数据，因此，可以通过预先设置不同道路类型相匹配的参考位置点的坐标信息，来实现对于不同道路类型下点云数据的筛选。
这里，智能行驶设备位于不同道路类型的道路上时所需处理的点云数据可能不同，因此，通过获取与道路类型相匹配的参考位置点的坐标信息，可以为智能行驶设备确定适配其当前所在的道路类型的有效坐标范围，从而筛选出对应道路类型下的点云数据，从而提高筛选点云数据的准确率。
在一种可能的实施方式中，在从所述待处理点云数据中筛选出目标点云数据之后，还可以对所述目标点云数据进行检测，得到检测结果之后，基于检测结果，控制设置雷达装置的智能行驶设备。
示例性的，在筛选出目标点云数据之后，可以基于筛选出的目标点云数据，实现对于智能行驶设备行驶过程中待识别对象(例如可以是障碍物)的检测，基于检测结果，可以控制设置雷达装置的智能行驶设备的行驶。
控制智能行驶设备的行驶可以是控制智能行驶设备加速、减速、转向、刹车等。
针对步骤103，在一种可能的实施方式中，检测结果包括目标场景中待识别对象的位置，下面将结合具体实施例对目标点云数据进行检测的过程展开详细描述，参见图4所示，本公开实施例提供一种检测结果确定方法，包括以下几个步骤：
步骤401、对所述目标点云数据进行栅格化处理，得到栅格矩阵；所述栅格矩阵中每个元素的值用于表征对应的栅格处是否存在目标点。在此，将目标点云数据所对应的点称为目标点。
步骤402、根据所述栅格矩阵以及所述目标场景中的待识别对象的尺寸信息，生成与所述待识别对象对应的稀疏矩阵。
步骤403、基于生成的所述稀疏矩阵，确定所述待识别对象在所述目标场景中的位置。
本公开实施例中，针对目标点云数据，首先可以进行栅格化处理，而后可以对栅格化处理得到的栅格矩阵进行稀疏处理，以生成稀疏矩阵。这里的栅格化处理的过程可以是将空间分布的包含各个目标点的目标点云数据映射到设定的栅格内，并基于栅格所对应的目标点进行栅格编码(对应零一矩阵)的过程，稀疏处理的过程则可以是基于目标场景中的待识别对象的尺寸信息对上述零一矩阵进行膨胀处理操作(对应增多零一矩阵中指示为1的元素的处理结果)或者腐蚀处理操作(对应减少零一矩阵中指示为1的元素的处理结果)的过程。接下来对上述栅格化处理的过程以及稀疏处理的过程进行更进一步的描述。
其中，上述栅格化处理的过程中，可以是将分布在笛卡尔连续实数坐标系的目标点转换到栅格化的离散坐标系。
为了便于理解上述栅格化的处理过程，接下来可以结合一个示例进行具体说明。本公开实施例具有点A(0.32m,0.48m)、点B(0.6m,0.4801m)和点C(2.1m,3.2m)等目标点，以1m为栅格宽度进行栅格化处理，(0m,0m)到(1m,1m)的范围对应第一个栅格，(0m,1m)到(1m,2m)的范围对应第二个栅格，以此类推。栅格化后的A'(0,0)，B'(0,0)均在第一行第一列的栅格里，C'(2,3)可以在第二行第三列的栅格里，从而实现了笛卡尔连续实数坐标系到离散坐标系的转换。其中，有关目标点的坐标信息可以由参照基准点(例如采集点云数据的雷达设备所在位置)确定，这里不做赘述。
本公开实施例中可以进行二维栅格化，也可以进行三维栅格化，相对于二维栅格化，三维栅格化在二维栅格化的基础上增加了高度信息。接下来可以以二维栅格化为例进行具体描述。
针对二维栅格化而言，可以将有限空间划分为N*M的栅格，一般是等间隔划分，间隔大小可配置。此时可以使用零一矩阵(即上述栅格矩阵)编码栅格化后的目标点云数据，每一个栅格可以使用唯一的行号和列号组成的坐标表示，如果该栅格中存在一个及以上目标点，则将该栅格编码为1，否则为0，从而可以得到编码后的零一矩阵。
在按照上述方法确定栅格矩阵之后，即可以根据目标场景的待识别对象的尺寸信息，对上述栅格矩阵中的元素进行稀疏处理操作，以生成对应的稀疏矩阵。
其中，有关待识别对象的尺寸信息可以是预先获取的，这里，可以结合目标点云数据所同步采集的图像数据来确定待识别对象的尺寸信息，还可以是基于具体应用场景来粗略估计上述待识别对象的尺寸信息。例如，针对自动驾驶领域，车辆前方的物体可以是车辆，可以确定其通用的尺寸信息为4m×4m。除此之外，本公开实施例还可以基于其它方式确定待识别对象的尺寸信息，本公开实施例对此不做具体的限制。
本公开实施例中，有关稀疏处理操作可以是对栅格矩阵中的目标元素(即表征对应的栅格处存在目标点的元素)进行至少一次膨胀处理操作，这里的膨胀处理操作可以是在栅格矩阵的坐标范围小于目标场景中的待识别对象的尺寸的情况下进行的，也即，通过一次或多次膨胀处理操作，可以对表征对应的栅格处存在目标点的元素范围进行逐级扩大，以使得扩大后的元素范围可以与待识别对象相匹配，进而实现位置的确定；除 此之外，本公开实施例中的稀疏处理操作还可以是对栅格矩阵中的目标元素进行至少一次腐蚀处理操作，这里的腐蚀处理操作可以是在栅格矩阵的坐标范围大于目标场景中的待识别对象的尺寸的情况下进行的，也即，通过一次或多次腐蚀处理操作，可以对表征对应的栅格处存在目标点的元素范围进行逐级缩小，以使得缩小后的元素范围可以与待识别对象相匹配，进而实现位置的确定。
在具体应用中，进行以下哪种操作：一次膨胀处理操作、多次膨胀处理操作、一次腐蚀处理操作、多次腐蚀处理操作，取决于进行至少一次移位处理以及逻辑运算处理所得到的稀疏矩阵的坐标范围与所述目标场景中的待识别对象的尺寸之间的差值是否属于预设阈值范围，也即，本公开所采用的膨胀或腐蚀处理操作是基于待识别对象的尺寸信息的约束来进行的，以使得所确定的稀疏矩阵所表征的信息更为符合待识别对象的相关信息。
可以理解的是，不管是基于膨胀处理操作还是腐蚀处理操作所实现的稀疏处理的目的在于使得生成的稀疏矩阵能够表征更为准确的待识别对象的相关信息。
本公开实施例中，上述膨胀处理操作可以是基于移位操作和逻辑或操作所实现的，还可以是基于取反之后卷积，卷积之后再取反所实现的。两种操作采用不同的方法，但最终所生成的稀疏矩阵的效果可以是一致的。
另外，上述腐蚀处理操作可以是基于移位操作和逻辑与操作所实现的，还可以是直接基于卷积操作所实现的。同理，尽管两种操作采用不同的方法，但最终所生成的稀疏矩阵的效果也可以是一致的。
接下来以膨胀处理操作为例，结合图5A至图5B所示的生成稀疏矩阵的具体示例图，进一步说明上述稀疏矩阵的生成过程。
图5A为栅格化处理后所得到的栅格矩阵(对应未编码前)的示意图，通过对该栅格矩阵中的每个目标元素(对应具有填充效果的栅格)进行一次八邻域的膨胀操作，即可以得到对应的稀疏矩阵5B。可知的是，本公开实施例针对5A中对应的栅格处存在目标点的目标元素而言，进行了八邻域的膨胀操作，从而使得每个目标元素在膨胀后成为一个元素集，该元素集所对应的栅格宽度可以是与待识别对象的尺寸相匹配的。
其中，上述八邻域的膨胀操作可以是确定与上述目标元素的横坐标或纵坐标之差的绝对值都不超过1的元素的过程，除了栅格边缘的元素，一般一个元素的邻域内都有八个元素(对应上述元素集)，膨胀处理结果输入可以是6个目标元素的坐标信息，输出则可以是该目标元素八邻域内的元素集的坐标信息，如图5B所示。
需要说明的是，在实际应用中，除了可以进行上述八邻域的膨胀操作，还可以进行四邻域的膨胀操作，后者及其它膨胀操作在此不做具体的限制。除此之外，本公开实施例还可以进行多次膨胀操作，例如，在图5B所示的膨胀结果的基础之上，再次进行膨胀操作，以得到更大元素集范围的稀疏矩阵，在此不再赘述。
本公开实施例中基于生成的稀疏矩阵，可以确定待识别对象在目标场景中的位置。本公开实施例中可以通过如下两个方面来具体实现。
第一方面：这里可以基于栅格矩阵中各个元素与各个目标点坐标范围信息之间的对应关系，来确定待识别对象的位置范围，具体可以通过如下步骤来实现：
步骤一、基于栅格矩阵中各个元素与各个目标点坐标范围信息之间的对应关系，确定与生成的稀疏矩阵中每个目标元素所对应的目标点的坐标信息；
步骤二、将稀疏矩阵中各个目标元素所对应的目标点的坐标信息进行组合，确定待识别对象在目标场景中的位置。
这里，基于上述有关栅格化处理的相关描述可知，栅格矩阵中的每个目标元素可以对应多个目标点，这样，有关元素与多个目标点所对应的目标点坐标范围信息可以是预先确定的。这里，仍以N*M维度的栅格矩阵为例，存在目标点的目标元素可以对应P个目标点，每个点的坐标为(Xi，Yi)，i属于0到P-1，Xi、Yi表示目标点在栅 格矩阵中的位置，0<＝Xi<N,0<＝Yi<M。
这样，在生成稀疏矩阵之后，可以采用基于预先确定的上述各个元素与各个目标点坐标范围信息之间的对应关系来确定与该稀疏矩阵中每个目标元素所对应的目标点的坐标信息，也即，进行了反栅格化的处理操作。
需要说明的是，由于稀疏矩阵是基于对栅格矩阵中表征对应的栅格处存在目标点的元素进行稀疏处理而得到的，因而，这里的稀疏矩阵中的目标元素的值也可以表征对应的栅格处存在目标点。
为了便于理解上述反栅格化的处理过程，接下来可以结合一个示例进行具体说明。这里以稀疏矩阵指示的点A'(0,0)和点B'(0,0)在第一行第一列栅格里；点C'(2,3)在第二行第三列的栅格为例，在进行反栅格化处理的过程中，第一个栅格(0,0)利用其中心映射回笛卡尔坐标系后，可以得到(0.5m,0.5m)，第二行第三列的栅格(2,3),利用其中心映射回笛卡尔坐标系，可以得到(2.5m,3.5m)，即可以将(0.5m,0.5m)和(2.5m,3.5m)确定为映射后的坐标信息，这样，将映射后的坐标信息进行组合，即可以确定待识别对象在目标场景中的位置。
本公开实施例不仅可以基于上述稀疏矩阵与目标检测结果的近似关系来实现待识别对象的位置范围的确定，还可以基于训练的卷积神经网络确定待识别对象的位置范围。
第二方面：本公开实施例首先可以基于已训练的卷积神经网络对生成的稀疏矩阵进行至少一次卷积处理，而后可以基于卷积处理得到的卷积结果确定待识别对象的位置范围。
在相关利用卷积神经网络来实现目标检测的技术中，需要遍历全部的输入数据，依次找到输入点的邻域点进行卷积运算，最后输出所有领域点的集合，而本公开实施例提供的方法仅需要通过快速遍历稀疏矩阵中的目标元素，来找到有效点所在位置(即零一矩阵中值为1的元素)进行卷积运算即可，从而大大加快卷积神经网络的计算过程，提升待识别对象的位置范围确定的效率。
考虑到稀疏处理操作对本公开实施例所提供的点云数据处理方法的关键作用，接下来可以通过如下两个方面分别进行说明。
第一方面：在稀疏处理操作为膨胀处理操作的情况下，本公开实施例可以结合移位处理和逻辑运算来实现，还可以基于取反之后卷积，卷积之后再取反来实现。
其一、本公开实施例中，可以基于至少一次移位处理和逻辑或运算进行一次或多次膨胀处理操作，在具体实现过程中，具体的膨胀处理操作的次数可以结合目标场景中的待识别对象的尺寸信息来确定。
这里，针对首次膨胀处理操作，可以对表征对应的栅格处存在目标点的目标元素进行多个预设方向的移位处理，得到对应的多个移位后的栅格矩阵，然后即可以对栅格矩阵和首次膨胀处理操作对应的多个移位后的栅格矩阵进行逻辑或运算，从而可以得到首次膨胀处理操作后的稀疏矩阵，这里，可以判断所得到的稀疏矩阵的坐标范围是否小于待识别对象的尺寸，且对应的差值是否足够大(如大于预设阈值)，若是，则可以按照上述方法对首次膨胀处理操作后的稀疏矩阵中的目标元素进行多个预设方向的移位处理和逻辑或运算，得到第二次膨胀处理操作后的稀疏矩阵，以此类推，直至确定最新得到的稀疏矩阵的坐标范围与目标场景中的待识别对象的尺寸之间的差值属于预设阈值范围的情况下，确定稀疏矩阵。
需要说明的是，不管是哪次膨胀处理操作后所得到的稀疏矩阵，其本质上也是一个零一矩阵。随着膨胀处理操作次数的增加，所得到的稀疏矩阵中表征对应的栅格处存在目标点的目标元素的个数也在增加，且由于零一矩阵所映射的栅格是具有宽度信息的，这里，即可以利用稀疏矩阵中各个目标元素所对应的坐标范围来验证是否达到目标场景中的待识别对象的尺寸，从而提升了后续目标检测应用的准确性。
其中，上述逻辑或运算可以按照如下步骤来实现：
步骤一、从多个移位后的栅格矩阵中选取一个移位后的栅格矩阵；
步骤二、将当前次膨胀处理操作前的栅格矩阵与选取出的移位后的栅格矩阵进行逻辑或运算，得到运算结果；
步骤三、重复执行从移位后的多个栅格矩阵中选取未参与运算的栅格矩阵，并对选取出的栅格矩阵与最近一次运算结果进行逻辑或运算的步骤，直至选取完所有的栅格矩阵，得到当前次膨胀处理操作后的稀疏矩阵。
这里，首先可以从移位后的多个栅格矩阵中选取一个移位后的栅格矩阵，这样，即可以将当前次膨胀处理操作前的栅格矩阵与选取出的移位后的栅格矩阵进行逻辑或运算，得到运算结果，这里，可以重复执行从移位后的多个栅格矩阵中选取未参与运算的栅格矩阵，并参与到逻辑或运算中的步骤，直至在选取完所有移位后的栅格矩阵，即可得到当前次膨胀处理操作后的稀疏矩阵。
本公开实施例中的膨胀处理操作可以是以目标元素为中心的四邻域的膨胀操作，还可以是以目标元素为中心的八邻域的膨胀操作，还可以是其它邻域处理操作方式，在具体应用中，可以基于待识别对象的尺寸信息来选择对应的邻域处理操作方式，这里不做具体的限制。
需要说明的是，针对不同的邻域处理操作方式，所对应移位处理的预设方向并不相同，以四邻域的膨胀操作为例，可以分别对栅格矩阵按照四个预设方向进行移位处理，分别是左移、右移、上移和下移，以八邻域的膨胀操作为例，可以分别对栅格矩阵按照八个预设方向进行移位处理，分别是左移、右移、上移、下移、在左移前提下的上移和下移、以及右移前提下的上移和下移。除此之外，为了适配后续的逻辑或运算，可以是在基于多个移位方向确定移位后的栅格矩阵之后，先进行一次逻辑或运算，而后将逻辑或运算结果再进行多个移位方向的移位操作，而后再进行下一次逻辑或运算，以此类推，直至得到膨胀处理后的稀疏矩阵。
为了便于理解上述膨胀处理操作，可以先将图5A所示的编码前的栅格矩阵转换为如图5C所示的编码后的栅格矩阵，而后结合图6A至图6B对首次膨胀处理操作进行示例说明。
图5C示出的栅格矩阵作为零一矩阵，矩阵中所有的“1”的位置可以表示目标元素所在的栅格，矩阵中所有“0”可以表示背景。
本公开实施例中，首先可以使用矩阵移位确定零一矩阵中所有元素值为1的元素的邻域。这里可以定义四个预设方向的移位处理，分别是左移、右移、上移和下移。其中，左移即零一矩阵中所有元素值为1的元素对应的列坐标减一，如图6A所示；右移即零一矩阵中所有元素值为1的元素对应的列坐标加一；上移即零一矩阵中所有元素值为1的元素对应的行坐标减一；下移即零一矩阵中所有元素值为1的元素对应的行坐标加一。
其次，本公开实施例可以使用矩阵逻辑或操作合并所有邻域的结果。矩阵逻辑或操作，即在接收到两组大小相同的零一矩阵输入的情况下，依次对两组矩阵相同位置的零一进行逻辑或操作，得到的结果组成一个新的零一矩阵作为输出，如图6B所示为一个逻辑或运算的具体示例。
在实现逻辑或操作的具体过程中，可以依次选取左移后的栅格矩阵、右移后的栅格矩阵、上移后的栅格矩阵、下移后的栅格矩阵参与到逻辑或的运算中。例如，可以先将栅格矩阵与左移以后的栅格矩阵进行逻辑或运算，得到的运算结果可以再和右移以后的栅格矩阵进行逻辑或运算，针对得到的运算结果可以再和上移以后的栅格矩阵进行逻辑或运算，针对得到的运算结果可以再和下移以后的栅格矩阵进行逻辑或运算，从而得到首次膨胀处理操作后的稀疏矩阵。
需要说明的是，上述有关平移后的栅格矩阵的选取顺序仅为一个具体的示例， 在实际应用中，还可以结合其它方式来选取，考虑到平移操作的对称性，这里可以选取上移和下移配对后进行逻辑或运算，左移和右移配对后进行逻辑或运算，两个逻辑或运算可以同步进行，可以节省计算时间。
其二、本公开实施例中，可以结合卷积和两次取反处理来实现膨胀处理操作，具体可以通过如下步骤来实现：
步骤一、对当前膨胀处理操作前的栅格矩阵中的元素进行第一取反操作，得到第一取反操作后的栅格矩阵；
步骤二、基于第一预设卷积核对第一取反操作后的栅格矩阵进行至少一次卷积运算，得到至少一次卷积运算后的具有预设稀疏度的栅格矩阵；预设稀疏度由目标场景中的待识别对象的尺寸信息来确定；
步骤三、对至少一次卷积运算后的具有预设稀疏度的栅格矩阵中的元素进行第二取反操作，得到稀疏矩阵。
本公开实施例可以通过取反之后卷积，卷积之后再取反的操作实现膨胀处理操作，所得到的稀疏矩阵一定程度上也可以表征待识别对象的相关信息，除此之外，考虑到上述卷积操作可以自动的与后续进行目标检测等应用所采用的卷积神经网络进行结合，因而一定程度上可以提升检测效率。
本公开实施例中，取反操作可以是基于卷积运算实现的，还可以是基于其它的取反操作方式实现的。为了便于配合后续的应用网络(如进行目标检测所采用的卷积神经网络)，这里，可以采用卷积运算来具体实现，接下来对上述第一取反操作进行具体说明。
这里，可以基于第二预设卷积核对当前次膨胀处理操作前的栅格矩阵中除目标元素外的其它元素进行卷积运算，得到第一取反元素，还可以基于第二预设卷积核，对当前次膨胀处理操作前的栅格矩阵中的目标元素进行卷积运算，得到第二取反元素，基于上述第一取反元素和第二取反元素，即可确定第一取反操作后的栅格矩阵。
有关第二取反操作的实现过程可以参照上述第一取反操作的实现过程，在此不再赘述。
本公开实施例中，可以利用第一预设卷积核对第一取反操作后的栅格矩阵进行至少一次卷积运算，从而得到具有预设稀疏度的栅格矩阵。如果膨胀处理操作可以作为一种扩增栅格矩阵中的目标元素个数的手段，则上述卷积运算可以视为一种减少栅格矩阵中的目标元素个数的过程(对应腐蚀处理操作)，由于本公开实施例中的卷积运算是针对第一取反操作后的栅格矩阵所进行的，因此，利用取反操作结合腐蚀处理操作，而后再次进行取反操作实现等价于上述膨胀处理操作的等价操作。
其中，针对首次卷积运算，将第一取反操作后的栅格矩阵与第一预设卷积核进行卷积运算，得到首次卷积运算后的栅格矩阵，在判断首次卷积运算后的栅格矩阵的稀疏度未达到预设稀疏度之后，可以将首次卷积运算后的栅格矩阵与第一预设卷积核再次进行卷积运算，得到第二次卷积运算后的栅格矩阵，以此类推，直至可以确定具有预设稀疏度的栅格矩阵。
其中，上述稀疏度可以是由栅格矩阵中目标元素与非目标元素的占比分布所确定的，目标元素占比越多，其所对应表征的待识别对象的尺寸信息越大，反之，目标元素占比越少，其所对应表征的待识别对象的尺寸信息越小，本公开实施例可以是在占比分布达到预设稀疏度时，停止卷积运算。
本公开实施例中的卷积运算可以是一次也可以是多次，这里可以以首次卷积运算的具体运算过程进行说明，包括如下步骤：
步骤一、针对首次卷积运算，按照第一预设卷积核的尺寸以及预设步长，从第一取反操作后的栅格矩阵中选取每个栅格子矩阵；
步骤二、针对选取的每个栅格子矩阵，将该栅格子矩阵与权值矩阵进行乘积运算， 得到第一运算结果，并将第一运算结果与偏置量进行加法运算，得到第二运算结果；
步骤三、基于各个栅格子矩阵对应的第二运算结果，确定首次卷积运算后的栅格矩阵。
这里，可以采用遍历方式对第一取反操作后的栅格矩阵进行遍历，这样针对遍历到的每个栅格子矩阵，即可以将栅格子矩阵与权值矩阵进行乘积运算，得到第一运算结果，并将第一运算结果与偏置量进行加法运算，得到第二运算结果，这样，将各个栅格子矩阵所对应的第二运算结果组合到对应的矩阵元素中，即可得到首次卷积运算后的栅格矩阵。
为了便于理解上述膨胀处理操作，这里仍以图5C所示的编码后的栅格矩阵为例，结合图7A至图7B对膨胀处理操作进行示例说明。
这里，可以利用一个1*1的卷积核(即第二预设卷积核)实现第一取反操作，该第二预设卷积核的权值为-1，偏置为1，此时将权值和偏置量代入{输出＝输入的栅格矩阵*权重+偏置量}这一卷积公式中，如果输入为栅格矩阵中的目标元素，其值对应为1，则输出＝1*-1+1＝0；如果输入为栅格矩阵中的非目标元素，其值对应为0，则输出＝0*-1+1＝1；这样，经过1*1卷积核作用于输入，可以使得零一矩阵取反，元素值0变为1、元素值1变为0，如图7A所示。
针对上述腐蚀处理操作，在具体应用中，可以利用一个3*3卷积核(即第一预设卷积核)和一个线性整流函数(Rectified Linear Unit,ReLU)来实现。上述第一预设卷积核权值矩阵所包括的各个权值均为1，偏置量为8，这样，可以利用公式{输出＝ReLU(输入的第一取反操作后的栅格矩阵*权重+偏置量)}来实现上述腐蚀处理操作。
这里，只有当输入的3*3的栅格子矩阵内所有元素都为1的情况下，输出＝ReLU(9-8)＝1；否则输出＝ReLU(输入的栅格子矩阵*1-8)＝0，其中，(输入的栅格子矩阵*1-8)<0，如图7B所示为卷积运算后的栅格矩阵。
这里，每嵌套一层具有第二预设卷积核的卷积网络可以叠加一次腐蚀操作，从而可以得到固定稀疏度的栅格矩阵，再次取反操作即可以等价于一次膨胀处理操作，从而可以实现稀疏矩阵的生成。
第二方面：在稀疏处理操作为腐蚀处理操作的情况下，本公开实施例可以结合移位处理和逻辑运算来实现，还可以基于卷积运算来实现。
其一、本公开实施例中，可以基于至少一次移位处理和逻辑与运算进行一次或多次腐蚀处理操作，在具体实现过程中，具体的腐蚀处理操作的次数可以结合目标场景中的待识别对象的尺寸信息来确定。
与第一方面中基于移位处理和逻辑或运算实现膨胀处理类似的是，在进行腐蚀处理操作的过程中，也可以先进行栅格矩阵的移位处理，与上述膨胀处理不同的是，这里的逻辑运算，可以是针对移位后的栅格矩阵进行逻辑与的运算。有关基于移位处理和逻辑与运算实现腐蚀处理操作的过程，具体参见上述描述内容，在此不再赘述。
同理，本公开实施例中的腐蚀处理操作可以是以目标元素为中心的四邻域腐蚀，还可以是以目标元素为中心的八领域腐蚀，还可以是其它领域处理操作方式，在具体应用中，可以基于待识别对象的尺寸信息来选择对应的领域处理操作方式，这里不做具体的限制。
其二、本公开实施例中，可以结合卷积处理来实现腐蚀处理操作，具体可以通过如下步骤来实现：
步骤一、基于第三预设卷积核对栅格矩阵进行至少一次卷积运算，得到至少一次卷积运算后的具有预设稀疏度的栅格矩阵；预设稀疏度由目标场景中的待识别对象的尺寸信息来确定；
步骤二、将至少一次卷积运算后的具有预设稀疏度的栅格矩阵，确定为与待识别对象对应的稀疏矩阵。
上述卷积运算可以视为一种减少栅格矩阵中的目标元素个数的过程，即腐蚀处理过程。其中，针对首次卷积运算，将栅格矩阵与第一预设卷积核进行卷积运算，得到首次卷积运算后的栅格矩阵，在判断首次卷积运算后的栅格矩阵的稀疏度未达到预设稀疏度之后，可以将首次卷积运算后的栅格矩阵与第三预设卷积核再次进行卷积运算，得到第二次卷积运算后的栅格矩阵，以此类推，直至可以确定具有预设稀疏度的栅格矩阵，即得到与待识别对象对应的稀疏矩阵。
本公开实施例中的卷积运算可以是一次也可以是多次，有关卷积运算的具体过程参见上述第一方面中基于卷积和取反实现膨胀处理的相关描述，在此不再赘述。
需要说明的是，在具体应用中，可以采用不同数据处理位宽的卷积神经网络来实现稀疏矩阵的生成，例如，可以采用4比特(bit)来表征网络的输入、输出以及计算用到的参数，例如栅格矩阵的元素值(0或1)，权值、偏置量等，除此之外，还可以采用8bit来进行表征以适应网络处理位宽，提升运算效率。
基于上述方法，可以基于目标场景对应的有效感知范围信息，对目标场景下雷达装置采集的待处理点云数据进行筛选，所筛选出的目标点云数据为在目标场景中对应的有效点云数据，因此，基于筛选出的目标点云数据，再在目标场景下进行检测计算，可以降低计算量，提高计算效率，及目标场景下计算资源的利用率。
本领域技术人员可以理解，在具体实施方式的上述方法中，各步骤的撰写顺序并不意味着严格的执行顺序而对实施过程构成任何限定，各步骤的具体执行顺序应当以其功能和可能的内在逻辑确定。
基于同一发明构思，本公开实施例中还提供了与点云数据处理方法对应的点云数据处理装置，由于本公开实施例中的装置解决问题的原理与本公开实施例上述点云数据处理方法相似，因此装置的实施可以参见方法的实施，重复之处不再赘述。
参照图8所示，为本公开实施例提供的一种点云数据处理装置的架构示意图，所述装置包括：获取模块801、筛选模块802、以及检测模块803；其中，
获取模块801，用于获取雷达装置在目标场景下扫描得到的待处理点云数据；
筛选模块802，用于根据所述目标场景对应的有效感知范围信息，从所述待处理点云数据中筛选出目标点云数据；
检测模块803，用于对所述目标点云数据进行检测，得到检测结果。
一种可能的实施方式中，所述筛选模块802，还用于根据以下方式确定所述目标场景对应的有效感知范围信息：
获取处理设备的计算资源信息；
基于所述计算资源信息，确定与所述计算资源信息所匹配的所述有效感知范围信息。
一种可能的实施方式中，所述筛选模块802，在根据所述目标场景对应的有效感知范围信息，从所述待处理点云数据中筛选出目标点云数据时，用于：
基于所述有效感知范围信息，确定有效坐标范围；
基于所述有效坐标范围，从所述待处理点云数据中筛选出目标点云数据。
一种可能的实施方式中，所述筛选模块802，在基于所述有效感知范围信息，确定有效坐标范围时，用于：
基于参考位置点在所述有效感知范围内的位置信息、以及所述参考位置点在所述目标场景中的坐标信息，确定所述目标场景对应的有效坐标范围。
一种可能的实施方式中，所述筛选模块802，在基于所述有效坐标范围，从所述待处理点云数据中筛选出目标点云数据时，用于：
将对应的坐标信息位于所述有效坐标范围内的雷达扫描点作为所述目标点云数据中的雷达扫描点。
一种可能的实施方式中，所述筛选模块802，还用于根据以下方式确定所述参考 位置点在目标场景中的坐标信息：
获取设置所述雷达装置的智能行驶设备的位置信息；
基于所述智能行驶设备的位置信息确定所述智能行驶设备所在道路的道路类型；
获取与所述道路类型相匹配的参考位置点的坐标信息。
一种可能的实施方式中，所述检测结果包括在所述目标场景中待识别对象的位置；
所述检测模块803，在对所述目标点云数据进行检测，得到检测结果时，用于：
对所述目标点云数据进行栅格化处理，得到栅格矩阵；所述栅格矩阵中每个元素的值用于表征对应的栅格处是否存在目标点；
根据所述栅格矩阵以及所述目标场景中的待识别对象的尺寸信息，生成与所述待识别对象对应的稀疏矩阵；
基于生成的所述稀疏矩阵，确定所述待识别对象在所述目标场景中的位置。
一种可能的实施方式中，所述检测模块803，在根据所述栅格矩阵以及所述目标场景中的待识别对象的尺寸信息，生成与所述待识别对象对应的稀疏矩阵时，用于：
根据所述栅格矩阵以及所述目标场景中的待识别对象的尺寸信息，对所述栅格矩阵中的目标元素进行至少一次膨胀处理操作或者腐蚀处理操作，生成与所述待识别对象对应的稀疏矩阵；
其中，所述目标元素的值表征对应的栅格处存在所述目标点。
一种可能的实施方式中，所述检测模块803，在进行膨胀处理操作或者腐蚀处理操作时，用于：移位处理以及逻辑运算处理，所述稀疏矩阵的坐标范围与所述待识别对象的尺寸之间的差值在预设阈值范围内。
一种可能的实施方式中，所述检测模块803，在根据所述栅格矩阵以及所述目标场景中的待识别对象的尺寸信息，对所述栅格矩阵中的元素进行至少一次膨胀处理操作，生成与所述待识别对象对应的稀疏矩阵时，用于：
对当前次膨胀处理操作前的栅格矩阵中的元素进行第一取反操作，得到第一取反操作后的栅格矩阵；
基于第一预设卷积核对所述第一取反操作后的栅格矩阵进行至少一次卷积运算，得到至少一次卷积运算后的具有预设稀疏度的栅格矩阵；所述预设稀疏度由所述目标场景中的待识别对象的尺寸信息来确定；
对所述至少一次卷积运算后的具有预设稀疏度的栅格矩阵中的元素进行第二取反操作，得到所述稀疏矩阵。
一种可能的实施方式中，所述检测模块803，在对当前次膨胀处理操作前的栅格矩阵中的元素进行第一取反操作，得到第一取反操作后的栅格矩阵时，用于：
基于第二预设卷积核，对当前次膨胀处理操作前的栅格矩阵中除所述目标元素外的其它元素进行卷积运算，得到第一取反元素，以及基于第二预设卷积核，对当前次膨胀处理操作前的栅格矩阵中的目标元素进行卷积运算，得到第二取反元素；
基于所述第一取反元素和所述第二取反元素，得到第一取反操作后的栅格矩阵。
一种可能的实施方式中，所述检测模块803，在基于第一预设卷积核对所述第一取反操作后的栅格矩阵进行至少一次卷积运算，得到至少一次卷积运算后的具有预设稀疏度的栅格矩阵时，用于：
针对首次卷积运算，将所述第一取反操作后的栅格矩阵与所述第一预设卷积核进行卷积运算，得到首次卷积运算后的栅格矩阵；
重复执行将上一次卷积运算后的栅格矩阵与所述第一预设卷积核进行卷积运算，得到当前次卷积运算后的栅格矩阵的步骤，直至得到具有预设稀疏度的栅格矩阵。
一种可能的实施方式中，所述检测模块803，在第一预设卷积核具有权值矩阵以及与该权值矩阵对应的偏置量；针对首次卷积运算，将所述第一取反操作后的栅格矩阵 与所述第一预设卷积核进行卷积运算，得到首次卷积运算后的栅格矩阵时，用于：
针对首次卷积运算，按照第一预设卷积核的尺寸以及预设步长，从所述第一取反操作后的栅格矩阵中选取每个栅格子矩阵；
针对选取的每个所述栅格子矩阵，将该栅格子矩阵与所述权值矩阵进行乘积运算，得到第一运算结果，并将所述第一运算结果与所述偏置量进行加法运算，得到第二运算结果；
基于各个所述栅格子矩阵对应的第二运算结果，确定首次卷积运算后的栅格矩阵。
一种可能的实施方式中，所述检测模块803，在根据所述栅格矩阵以及所述目标场景中的待识别对象的尺寸信息，对所述栅格矩阵中的元素进行至少一次腐蚀处理操作，生成与所述待识别对象对应的稀疏矩阵时，用于：
基于第三预设卷积核对待处理的栅格矩阵进行至少一次卷积运算，得到至少一次卷积运算后的具有预设稀疏度的栅格矩阵；所述预设稀疏度由所述目标场景中的待识别对象的尺寸信息来确定；
将所述至少一次卷积运算后的具有预设稀疏度的栅格矩阵，确定为与所述待识别对象对应的稀疏矩阵。
一种可能的实施方式中，所述检测模块803，在对所述目标点云数据进行栅格化处理，得到栅格矩阵时，用于：
对所述目标点云数据进行栅格化处理，得到栅格矩阵以及该栅格矩阵中各个元素与各个目标点坐标范围信息之间的对应关系。
所述检测模块803，在基于生成的所述稀疏矩阵，确定所述待识别对象在所述目标场景中的位置范围时，用于：
基于所述栅格矩阵中各个元素与各个目标点坐标范围信息之间的对应关系，确定生成的所述稀疏矩阵中每个目标元素所对应的目标点的坐标信息；
将所述稀疏矩阵中各个所述目标元素所对应的目标点的坐标信息进行组合，确定所述待识别对象在所述目标场景中的位置。
一种可能的实施方式中，所述检测模块803，在基于生成的所述稀疏矩阵，确定所述待识别对象在所述目标场景中的位置时，用于：
基于已训练的卷积神经网络对生成的所述稀疏矩阵中的每个目标元素进行至少一次卷积处理，得到卷积结果；
基于所述卷积结果，确定所述待识别对象在所述目标场景中的位置。
一种可能的实施方式中，所述装置还包括控制模块804，用于：在对所述目标点云数据进行检测，得到检测结果之后，基于所述检测结果控制设置所述雷达装置的智能行驶设备。
基于上述装置，可以基于目标场景对应的有效感知范围信息，对目标场景下雷达装置采集的待处理点云数据进行筛选，所筛选出的目标点云数据为在目标场景中对应的目标点云数据，因此，基于筛选出的点云数据，再在目标场景下进行检测计算，可以降低计算量，提高计算效率，及目标场景下计算资源的利用率。
关于装置中的各模块的处理流程、以及各模块之间的交互流程的描述可以参照上述方法实施例中的相关说明，这里不再详述。
基于同一技术构思，参照图9所示，本公开实施例还提供了一种计算机设备，包括处理器901、存储器902和总线903。其中，存储器902包括内存9021和外部存储器9022，以用于存储执行指令；这里的内存9021也称内存储器，用于暂时存放处理器901中的运算数据，以及与硬盘等外部存储器9022交换的数据，处理器901通过内存9021与外部存储器9022进行数据交换，当计算机设备900运行时，处理器901与存储器902之间通过总线903通信，使得处理器901在执行以下指令：
获取雷达装置在目标场景下扫描得到的待处理点云数据；
根据所述目标场景对应的有效感知范围信息，从所述待处理点云数据中筛选出目标点云数据；
对所述目标点云数据进行检测，得到检测结果。
本公开实施例还提供一种计算机可读存储介质，其上存储的计算机程序被处理器运行时执行上述方法实施例中所述的点云数据处理方法。其中，该存储介质可以是易失性或非易失的计算机可读取存储介质。
本公开实施例所提供的点云数据处理方法的计算机程序产品，包括存储了程序代码的计算机可读存储介质，所述程序代码包括的指令可用于执行上述方法实施例中所述的点云数据处理方法，具体可参见上述方法实施例，在此不再赘述。
本公开实施例还提供一种计算机程序，该计算机程序被处理器执行时实现前述实施例的任意一种方法。该计算机程序产品可以具体通过硬件、软件或其结合的方式实现。在一个可选实施例中，所述计算机程序产品具体体现为计算机存储介质，在另一个可选实施例中，计算机程序产品具体体现为软件产品，例如软件开发包(Software Development Kit，SDK)等等。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统和装置的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。在本公开所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，又例如，多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本公开各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个处理器可执行的非易失的计算机可读取存储介质中。基于这样的理解，本公开的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本公开各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是：以上所述实施例，仅为本公开的具体实施方式，用以说明本公开的技术方案，而非对其限制，本公开的保护范围并不局限于此，尽管参照前述实施例对本公开进行了详细的说明，本领域的普通技术人员应当理解：任何熟悉本技术领域的技术人员在本公开揭露的技术范围内，其依然可以对前述实施例所记载的技术方案进行修改或可轻易想到变化，或者对其中部分技术特征进行等同替换；而这些修改、变化或者替换，并不使相应技术方案的本质脱离本公开实施例技术方案的精神和范围，都应涵盖在本公开的保护范围之内。因此，本公开的保护范围应所述以权利要求的保护范围为准。

Claims (20)

  1. 一种点云数据处理方法，包括：
    获取雷达装置在目标场景下扫描得到的待处理点云数据；
    根据所述目标场景对应的有效感知范围信息，从所述待处理点云数据中筛选出目标点云数据；
    对所述目标点云数据进行检测，得到检测结果。
  2. 根据权利要求1所述的方法，其特征在于，根据以下方式确定所述目标场景对应的所述有效感知范围信息：
    获取在所述目标场景下处理所述待处理点云数据的处理设备的计算资源信息；
    基于所述计算资源信息，确定与所述计算资源信息所匹配的所述有效感知范围信息。
  3. 根据权利要求1或2所述的方法，其特征在于，所述根据所述目标场景对应的有效感知范围信息，从所述待处理点云数据中筛选出目标点云数据，包括：
    基于所述有效感知范围信息，确定有效坐标范围；
    基于所述有效坐标范围，从所述待处理点云数据中筛选出目标点云数据。
  4. 根据权利要求3所述的方法，其特征在于，所述基于所述有效感知范围信息，确定有效坐标范围，包括：
    基于参考位置点在所述有效感知范围内的位置信息、以及所述参考位置点在所述目标场景中的坐标信息，确定所述目标场景对应的有效坐标范围。
  5. 根据权利要求3所述的方法，其特征在于，所述基于所述有效坐标范围，从所述待处理点云数据中筛选出目标点云数据，包括：
    将所述待处理点云数据中的坐标信息位于所述有效坐标范围内的每一个雷达扫描点作为所述目标点云数据中的雷达扫描点。
  6. 根据权利要求4所述的方法，其特征在于，根据以下方式确定所述参考位置点在所述目标场景中的坐标信息：
    获取设置所述雷达装置的智能行驶设备的位置信息；
    基于所述智能行驶设备的位置信息确定所述智能行驶设备所在道路的道路类型；
    获取与所述道路类型相匹配的参考位置点的坐标信息作为所述参考位置点在所述目标场景中的坐标信息。
  7. 根据权利要求1所述的方法，其特征在于，所述检测结果包括在所述目标场景中待识别对象的位置；所述对所述目标点云数据进行检测，得到检测结果，包括：
    对所述目标点云数据进行栅格化处理，得到栅格矩阵；所述栅格矩阵中每个元素的值用于表征对应的栅格处是否存在目标点；
    根据所述栅格矩阵以及所述目标场景中的待识别对象的尺寸信息，生成与所述待识别对象对应的稀疏矩阵；
    基于生成的所述稀疏矩阵，确定所述待识别对象在所述目标场景中的位置。
  8. 根据权利要求7所述的方法，其特征在于，所述根据所述栅格矩阵以及所述目标场景中的待识别对象的尺寸信息，生成与所述待识别对象对应的稀疏矩阵，包括：
    根据所述栅格矩阵以及所述目标场景中的待识别对象的尺寸信息，对所述栅格矩阵中的目标元素进行至少一次膨胀处理操作或者腐蚀处理操作，生成与所述待识别对象对应的稀疏矩阵；
    其中，所述目标元素的值表征对应的栅格处存在所述目标点。
  9. 根据权利要求8所述的方法，其特征在于，所述膨胀处理操作或者腐蚀处理操作包括：
    移位处理以及逻辑运算处理，
    所述稀疏矩阵的坐标范围与所述待识别对象的尺寸之间的差值在预设阈值范围内。
  10. 根据权利要求8所述的方法，其特征在于，根据所述栅格矩阵以及所述目标场 景中的待识别对象的尺寸信息，对所述栅格矩阵中的元素进行至少一次膨胀处理操作，生成与所述待识别对象对应的稀疏矩阵，包括：
    对当前次膨胀处理操作前的栅格矩阵中的元素进行第一取反操作，得到第一取反操作后的栅格矩阵；
    基于第一预设卷积核对所述第一取反操作后的栅格矩阵进行至少一次卷积运算，得到至少一次卷积运算后的具有预设稀疏度的栅格矩阵；
    对所述至少一次卷积运算后的具有预设稀疏度的栅格矩阵中的元素进行第二取反操作，得到所述稀疏矩阵。
  11. 根据权利要求10所述的方法，其特征在于，所述对当前次膨胀处理操作前的栅格矩阵中的元素进行第一取反操作，得到第一取反操作后的栅格矩阵，包括：
    基于第二预设卷积核，对当前次膨胀处理操作前的栅格矩阵中除所述目标元素外的其它元素进行卷积运算，得到第一取反元素；
    基于所述第二预设卷积核，对当前次膨胀处理操作前的栅格矩阵中的目标元素进行卷积运算，得到第二取反元素；
    基于所述第一取反元素和所述第二取反元素，得到第一取反操作后的栅格矩阵。
  12. 根据权利要求10或11所述的方法，其特征在于，所述基于第一预设卷积核对所述第一取反操作后的栅格矩阵进行至少一次卷积运算，得到至少一次卷积运算后的具有预设稀疏度的栅格矩阵，包括：
    针对首次卷积运算，将所述第一取反操作后的栅格矩阵与所述第一预设卷积核进行卷积运算，得到首次卷积运算后的栅格矩阵；
    重复执行将上一次卷积运算后的栅格矩阵与所述第一预设卷积核进行卷积运算，得到当前次卷积运算后的栅格矩阵的步骤，直至得到具有所述预设稀疏度的栅格矩阵。
  13. 根据权利要求12所述的方法，其特征在于，所述第一预设卷积核具有权值矩阵以及与该权值矩阵对应的偏置量；所述针对首次卷积运算，将所述第一取反操作后的栅格矩阵与所述第一预设卷积核进行卷积运算，得到首次卷积运算后的栅格矩阵，包括：
    针对首次卷积运算，按照第一预设卷积核的尺寸以及预设步长，从所述第一取反操作后的栅格矩阵中选取每个栅格子矩阵；
    针对选取的每个所述栅格子矩阵，将该栅格子矩阵与所述权值矩阵进行乘积运算，得到第一运算结果；
    将所述第一运算结果与所述偏置量进行加法运算，得到第二运算结果；
    基于各个所述栅格子矩阵对应的第二运算结果，确定首次卷积运算后的栅格矩阵。
  14. 根据权利要求8所述的方法，其特征在于，根据所述栅格矩阵以及所述目标场景中的待识别对象的尺寸信息，对所述栅格矩阵中的元素进行至少一次腐蚀处理操作，生成与所述待识别对象对应的稀疏矩阵，包括：
    基于第三预设卷积核对待处理的栅格矩阵进行至少一次卷积运算，得到至少一次卷积运算后的具有预设稀疏度的栅格矩阵；
    将所述至少一次卷积运算后的具有预设稀疏度的栅格矩阵，确定为与所述待识别对象对应的稀疏矩阵。
  15. 根据权利要求7至14任一所述的方法，其特征在于，
    所述对所述目标点云数据进行栅格化处理，得到栅格矩阵，包括：
    对所述目标点云数据进行栅格化处理，得到栅格矩阵以及该栅格矩阵中各个元素与各个目标点坐标范围信息之间的对应关系；
    所述基于生成的所述稀疏矩阵，确定所述待识别对象在所述目标场景中的位置范围，包括：
    基于所述栅格矩阵中各个元素与各个目标点坐标范围信息之间的对应关系，确定生成的所述稀疏矩阵中每个目标元素所对应的目标点的坐标信息；
    将所述稀疏矩阵中各个所述目标元素所对应的目标点的坐标信息进行组合，确定所述待识别对象在所述目标场景中的位置。
  16. 根据权利要求7至15任一所述的方法，其特征在于，所述基于生成的所述稀疏矩阵，确定所述待识别对象在所述目标场景中的位置，包括：
    基于已训练的卷积神经网络对生成的所述稀疏矩阵中的每个目标元素进行至少一次卷积处理，得到卷积结果；
    基于所述卷积结果，确定所述待识别对象在所述目标场景中的位置。
  17. 根据权利要求1至16任一所述的方法，其特征在于，在对所述目标点云数据进行检测，得到检测结果之后，所述方法还包括：
    基于所述检测结果控制设置有所述雷达装置的智能行驶设备。
  18. 一种点云数据处理装置，包括：
    获取模块，用于获取雷达装置在目标场景下扫描得到的待处理点云数据；
    筛选模块，用于根据所述目标场景对应的有效感知范围信息，从所述待处理点云数据中筛选出目标点云数据；
    检测模块，用于对所述目标点云数据进行检测，得到检测结果。
  19. 一种计算机设备，包括处理器、存储器和总线，所述存储器存储有所述处理器可执行的机器可读指令，当计算机设备运行时，所述处理器与所述存储器之间通过总线通信，所述机器可读指令被所述处理器执行时执行如权利要求1至17任一所述的点云数据处理方法。
  20. 一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器运行时执行如权利要求1至17任意一项所述的点云数据处理方法。
PCT/CN2021/102856 2020-07-22 2021-06-28 一种点云数据处理方法及装置 Ceased WO2022017133A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2022514581A JP2022547873A (ja) 2020-07-22 2021-06-28 点群データ処理方法及び装置
KR1020227007394A KR20220044777A (ko) 2020-07-22 2021-06-28 포인트 클라우드 데이터 처리 방법 및 장치

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010713989.6A CN113971694B (zh) 2020-07-22 2020-07-22 一种点云数据处理方法及装置
CN202010713989.6 2020-07-22

Publications (1)

Publication Number Publication Date
WO2022017133A1 true WO2022017133A1 (zh) 2022-01-27

Family

ID=79585066

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/102856 Ceased WO2022017133A1 (zh) 2020-07-22 2021-06-28 一种点云数据处理方法及装置

Country Status (4)

Country Link
JP (1) JP2022547873A (zh)
KR (1) KR20220044777A (zh)
CN (1) CN113971694B (zh)
WO (1) WO2022017133A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114664092A (zh) * 2022-05-18 2022-06-24 阿里巴巴达摩院(杭州)科技有限公司 交通事件检测系统、事件检测方法以及装置
CN115861626A (zh) * 2022-10-25 2023-03-28 武汉万集光电技术有限公司 目标检测方法、装置、终端设备及计算机可读存储介质
CN116299312A (zh) * 2022-12-29 2023-06-23 浙江大华技术股份有限公司 一种目标检测方法、装置、终端及计算机可读存储介质

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115629366A (zh) * 2022-09-30 2023-01-20 深圳优地科技有限公司 一种目标检测方法、装置、终端设备和可读存储介质
CN117218366A (zh) * 2022-12-05 2023-12-12 北京小米移动软件有限公司 识别目标对象的方法、装置及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120206438A1 (en) * 2011-02-14 2012-08-16 Fatih Porikli Method for Representing Objects with Concentric Ring Signature Descriptors for Detecting 3D Objects in Range Images
CN106570454A (zh) * 2016-10-10 2017-04-19 同济大学 基于移动激光扫描的行人交通参数提取方法
CN109649395A (zh) * 2018-12-29 2019-04-19 驭势科技（北京）有限公司 一种基于计算资源的自动驾驶调整方法及车载设备
CN109840448A (zh) * 2017-11-24 2019-06-04 百度在线网络技术（北京）有限公司 用于无人驾驶车辆的信息输出方法和装置

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110457407B (zh) * 2018-05-02 2022-08-12 北京京东尚科信息技术有限公司 用于处理点云数据的方法和装置
CN111353512B (zh) * 2018-12-20 2023-07-28 长沙智能驾驶研究院有限公司 障碍物分类方法、装置、存储介质和计算机设备
CN109901139B (zh) * 2018-12-28 2023-07-04 文远知行有限公司 激光雷达标定方法、装置、设备和存储介质
CN110674829B (zh) * 2019-09-26 2023-06-02 哈尔滨工程大学 一种基于图卷积注意网络的三维目标检测方法
CN110764108B (zh) * 2019-11-05 2023-05-02 畅加风行(苏州)智能科技有限公司 一种用于港口自动驾驶场景的障碍物检测方法及装置
CN110956137A (zh) * 2019-12-02 2020-04-03 深圳市镭神智能系统有限公司 点云数据的目标检测方法、系统及介质
CN111199206A (zh) * 2019-12-30 2020-05-26 上海眼控科技股份有限公司 三维目标检测方法、装置、计算机设备及存储介质
CN111192295B (zh) * 2020-04-14 2020-07-03 中智行科技有限公司 目标检测与跟踪方法、设备和计算机可读存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120206438A1 (en) * 2011-02-14 2012-08-16 Fatih Porikli Method for Representing Objects with Concentric Ring Signature Descriptors for Detecting 3D Objects in Range Images
CN106570454A (zh) * 2016-10-10 2017-04-19 同济大学 基于移动激光扫描的行人交通参数提取方法
CN109840448A (zh) * 2017-11-24 2019-06-04 百度在线网络技术（北京）有限公司 用于无人驾驶车辆的信息输出方法和装置
CN109649395A (zh) * 2018-12-29 2019-04-19 驭势科技（北京）有限公司 一种基于计算资源的自动驾驶调整方法及车载设备

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114664092A (zh) * 2022-05-18 2022-06-24 阿里巴巴达摩院(杭州)科技有限公司 交通事件检测系统、事件检测方法以及装置
CN115861626A (zh) * 2022-10-25 2023-03-28 武汉万集光电技术有限公司 目标检测方法、装置、终端设备及计算机可读存储介质
CN116299312A (zh) * 2022-12-29 2023-06-23 浙江大华技术股份有限公司 一种目标检测方法、装置、终端及计算机可读存储介质

Also Published As

Publication number Publication date
CN113971694A (zh) 2022-01-25
KR20220044777A (ko) 2022-04-11
JP2022547873A (ja) 2022-11-16
CN113971694B (zh) 2025-06-06

Similar Documents

Publication Publication Date Title
CN113971694A (zh) 一种点云数据处理方法及装置
CN111665842B (zh) 一种基于语义信息融合的室内slam建图方法及系统
WO2022017131A1 (zh) 点云数据的处理方法、智能行驶控制方法及装置
CN114648640A (zh) 一种目标物单体化方法、装置、设备及存储介质
CN115588187A (zh) 基于三维点云的行人检测方法、装置、设备以及存储介质
CN114140758A (zh) 一种目标检测方法、装置及计算机设备
WO2022016942A1 (zh) 一种目标检测方法、装置、电子设备及存储介质
CN115620263B (zh) 基于摄像机和激光雷达图像融合的智能车障碍物检测方法
CN114859938B (zh) 机器人、动态障碍物状态估计方法、装置和计算机设备
CN108399424B (zh) 一种点云分类方法、智能终端及存储介质
US11182942B2 (en) Map generation system and method for generating an accurate building shadow
CN108345007B (zh) 一种障碍物识别方法和装置
EP4310789A1 (en) Prediction method for target object, computer device, and storage medium
CN116935233B (zh) 用于激光雷达的目标检测方法和装置
CN109540023A (zh) 基于二值网格编码模板结构光的物体表面深度值测量方法
Zou et al. Efficient urban-scale point clouds segmentation with bev projection
Liu et al. These maps are made by propagation: Adapting deep stereo networks to road scenarios with decisive disparity diffusion
WO2022017129A1 (zh) 目标对象检测方法、装置、电子设备及存储介质
WO2025236913A1 (zh) 地图更新方法、装置、计算机设备和存储介质
CN116977312B (zh) 一种基于三维球面投影的回环检测方法及装置
CN118840517A (zh) 一种结构化场景并行多平面-直线并行提取方法及系统
WO2022017134A1 (zh) 一种点云数据的处理方法、装置、电子设备及存储介质
CN115239841A (zh) 车道线生成方法、装置、计算机设备和存储介质
CN112433193B (zh) 一种基于多传感器的模位置定位方法及系统
Cai et al. Deep representation and stereo vision based vehicle detection

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2022514581

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20227007394

Country of ref document: KR

Kind code of ref document: A

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21845387

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21845387

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 10.07.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21845387

Country of ref document: EP

Kind code of ref document: A1