A data processing method, device and equipment

Abstract

The present invention provides a data processing method, device and equipment, which relate to the field of communication technology. The method comprises: dividing the point cloud collected by the roadside equipment into a plurality of first point cloud blocks; determining a second point cloud block among the plurality of first point cloud blocks, wherein the second point cloud block is a point cloud block including a part of the road point cloud; and determining the road boundary according to the second point cloud block. The solution of the present invention solves the problem that the existing method of processing the point cloud obtained by the roadside is complicated and consumes a lot of resources.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a data processing method, device and equipment. Background Art

[0002] With the development of intelligent automobiles, driverless cars can use on-board sensors to sense the environment around the vehicle, and control the steering and speed of the vehicle based on the road, vehicle position and obstacle information obtained through perception, so as to achieve driving on the road. However, driverless cars will always encounter some difficult-to-solve blind spot problems when they perceive the environment independently, and the concept of vehicle-road collaboration came into being. Among them, the perception capability of roadside equipment is an important part of vehicle-road collaboration. The computing unit on the roadside is used to complete the detection and identification of road traffic elements, and cooperate with the perception capability of the vehicle to realize the implementation of vehicle-road collaboration.

[0003] However, the laser point cloud detection method currently used by roadside equipment will crop the point cloud, usually by detecting the boundaries of some areas of the point cloud to obtain the segmented area. This requires full-domain calculation of the point cloud, which makes the processing complex and consumes a lot of resources. Summary of the invention

[0004] The purpose of the present invention is to provide a data processing method, device and equipment to solve the problem that the existing method of processing the point cloud obtained from the roadside is complicated and consumes a lot of resources.

[0005] To achieve the above object, an embodiment of the present invention provides a data processing method, comprising:

[0006] Dividing the point cloud collected by the roadside equipment into a plurality of first point cloud blocks;

[0007] Determine a second point cloud block among the plurality of first point cloud blocks, wherein the second point cloud block is a point cloud block including a portion of a road point cloud;

[0008] A road boundary is determined based on the second point cloud block.

[0009] Optionally, dividing the point cloud collected by the roadside equipment into a plurality of first point cloud blocks includes:

[0010] Based on a preset coordinate system, converting the point cloud collected by the roadside equipment into a plane point cloud;

[0011] The planar point cloud is divided into a plurality of first point cloud blocks.

[0012] Optionally, determining a second point cloud block among the plurality of first point cloud blocks comprises:

[0013] According to the intensity information of the road point cloud, starting from the edge point cloud block among the multiple first point cloud blocks, each first point cloud block is analyzed in turn along the first preset direction to determine whether the analyzed first point cloud block is the second point cloud block. If so, stop analyzing the remaining first point cloud blocks; if not, continue analyzing the next first point cloud block.

[0014] Optionally, determining a road boundary according to the second point cloud block includes:

[0015] Based on the second point cloud block, divide it according to a preset rule to obtain a plurality of candidate point cloud blocks;

[0016] Determine a target point cloud block among the multiple candidate point cloud blocks;

[0017] According to the boundary position of the target point cloud block or the road point cloud position, a road boundary is obtained; wherein,

[0018] The intensity information of the point cloud on the first boundary of the target point cloud block is consistent with the intensity information of the road point cloud, and the intensity information of the point cloud on the second boundary is inconsistent with the intensity information of the road point cloud, and the first boundary is opposite to the second boundary; or, the intensity information of the point cloud on at least one boundary of the target point cloud block partially conforms to the intensity information of the road point cloud, and partially does not conform to the intensity information of the road point cloud.

[0019] Optionally, the preset rules include:

[0020] When the width of the determined target point cloud block is greater than a preset threshold, the determined target point cloud block is divided.

[0021] Optionally, after determining the road boundary according to the second point cloud block, the method further includes:

[0022] Get the centerline position of the road boundary;

[0023] Determining whether the distance between the centerline position and the road boundary conforms to the road width setting;

[0024] If yes, obtaining a point cloud of the road area according to the road boundary;

[0025] If not, the point cloud collected by the roadside equipment is divided again until the point cloud of the road area is obtained.

[0026] To achieve the above object, an embodiment of the present invention provides a data processing device, including:

[0027] A first processing module, used for dividing the point cloud collected by the roadside equipment into a plurality of first point cloud blocks;

[0028] A second processing module, configured to determine a second point cloud block among the plurality of first point cloud blocks, wherein the second point cloud block is a point cloud block including a portion of a road point cloud;

[0029] The third processing module is used to determine the road boundary according to the second point cloud block.

[0030] Optionally, the first processing module includes:

[0031] A conversion submodule, used to convert the point cloud collected by the roadside equipment into a plane point cloud based on a preset coordinate system;

[0032] The first processing submodule is used to divide the plane point cloud into a plurality of first point cloud blocks.

[0033] Optionally, the second processing module is further used for:

[0034] According to the intensity information of the road point cloud, starting from the edge point cloud block among the multiple first point cloud blocks, each first point cloud block is analyzed in turn along the first preset direction to determine whether the analyzed first point cloud block is the second point cloud block. If so, stop analyzing the remaining first point cloud blocks; if not, continue analyzing the next first point cloud block.

[0035] Optionally, the third processing module includes:

[0036] A second processing submodule, configured to divide the second point cloud block into a plurality of candidate point cloud blocks according to a preset rule;

[0037] A third processing submodule, configured to determine a target point cloud block among the plurality of candidate point cloud blocks;

[0038] The fourth processing submodule is used to obtain the road boundary according to the boundary position of the target point cloud block or the road point cloud position; wherein,

[0039] The intensity information of the point cloud on the first boundary of the target point cloud block is consistent with the intensity information of the road point cloud, and the intensity information of the point cloud on the second boundary is inconsistent with the intensity information of the road point cloud, and the first boundary is opposite to the second boundary; or, the intensity information of the point cloud on at least one boundary of the target point cloud block partially conforms to the intensity information of the road point cloud, and partially does not conform to the intensity information of the road point cloud.

[0040] Optionally, the preset rules include:

[0041] When the width of the determined target point cloud block is greater than a preset threshold, the determined target point cloud block is divided.

[0042] Optionally, the device further comprises:

[0043] An acquisition module, used for acquiring the centerline position of the road boundary;

[0044] A judgment module, used to judge whether the distance between the center line position and the road boundary meets the road width setting;

[0045] A fourth processing module, configured to obtain a point cloud of the road area according to the road boundary;

[0046] The fifth processing module is used to, if not, re-divide the point cloud collected by the roadside equipment until the point cloud of the road area is obtained.

[0047] To achieve the above object, an embodiment of the present invention provides a data processing device, including a processor; the processor is used to:

[0048] Dividing the point cloud collected by the roadside equipment into a plurality of first point cloud blocks;

[0049] Determine a second point cloud block among the plurality of first point cloud blocks, wherein the second point cloud block is a point cloud block including a portion of a road point cloud;

[0050] A road boundary is determined based on the second point cloud block.

[0051] Optionally, the processor is further configured to:

[0052] Based on a preset coordinate system, converting the point cloud collected by the roadside equipment into a plane point cloud;

[0053] The planar point cloud is divided into a plurality of first point cloud blocks.

[0054] Optionally, the processor is further configured to:

[0055] According to the intensity information of the road point cloud, starting from the edge point cloud block among the multiple first point cloud blocks, each first point cloud block is analyzed in turn along the first preset direction to determine whether the analyzed first point cloud block is the second point cloud block. If so, stop analyzing the remaining first point cloud blocks; if not, continue analyzing the next first point cloud block.

[0056] Optionally, the processor is further configured to:

[0057] Based on the second point cloud block, divide it according to a preset rule to obtain a plurality of candidate point cloud blocks;

[0058] Determine a target point cloud block among the multiple candidate point cloud blocks;

[0059] According to the boundary position of the target point cloud block or the road point cloud position, a road boundary is obtained; wherein,

[0060] The intensity information of the point cloud on the first boundary of the target point cloud block is consistent with the intensity information of the road point cloud, and the intensity information of the point cloud on the second boundary is inconsistent with the intensity information of the road point cloud, and the first boundary is opposite to the second boundary; or, the intensity information of the point cloud on at least one boundary of the target point cloud block partially conforms to the intensity information of the road point cloud, and partially does not conform to the intensity information of the road point cloud.

[0061] Optionally, the preset rules include:

[0062] When the width of the determined target point cloud block is greater than a preset threshold, the determined target point cloud block is divided.

[0063] Optionally, the processor is further configured to:

[0064] Get the centerline position of the road boundary;

[0065] Determining whether the distance between the centerline position and the road boundary conforms to the road width setting;

[0066] If yes, obtaining a point cloud of the road area according to the road boundary;

[0067] If not, the point cloud collected by the roadside equipment is divided again until the point cloud of the road area is obtained.

[0068] To achieve the above-mentioned purpose, an embodiment of the present invention provides a data processing device, comprising: a transceiver, a processor, a memory, and a program or instruction stored in the memory and executable on the processor; when the processor executes the program or instruction, the data processing method as described above is implemented.

[0069] To achieve the above objective, an embodiment of the present invention provides a readable storage medium on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps in the data processing method described above are implemented.

[0070] The beneficial effects of the above technical solution of the present invention are as follows:

[0071] The method of the embodiment of the present invention can first perform a preliminary division on the point cloud collected by the roadside equipment to obtain multiple first point cloud blocks; then, determine a second point cloud block including a part of the road point cloud from the multiple first point cloud blocks; thereafter, it is possible to further determine the road boundary based on the second point cloud block to facilitate the subsequent acquisition of the road point cloud, thereby simplifying the point cloud processing process and avoiding a large consumption of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 is a flow chart of a data processing method according to an embodiment of the present invention;

[0073] Figure 2 Schematic diagram of point cloud segmentation;

[0074] Figure 3 is a structural diagram of a data processing device according to an embodiment of the present invention;

[0075] Figure 4 is a structural diagram of a data processing device according to an embodiment of the present invention;

[0076] Figure 5 A structural diagram of a data processing device according to another embodiment of the present invention. DETAILED DESCRIPTION

[0077] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0078] It should be understood that the references to "one embodiment" or "an embodiment" throughout the specification mean that the specific features, structures, or characteristics associated with the embodiment are included in at least one embodiment of the present invention. Therefore, the references to "in one embodiment" or "in an embodiment" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0079] In various embodiments of the present invention, it should be understood that the size of the serial numbers of the following processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0080] Additionally, the terms "system" and "network" are often used interchangeably herein.

[0081] In the embodiments provided in the present application, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0082] like Figure 1 As shown, a data processing method according to an embodiment of the present invention includes:

[0083] Step 101, dividing the point cloud collected by the roadside equipment into a plurality of first point cloud blocks;

[0084] Step 102, determining a second point cloud block among the plurality of first point cloud blocks, wherein the second point cloud block is a point cloud block including a portion of a road point cloud;

[0085] Step 103: determine the road boundary according to the second point cloud block.

[0086] The method of the embodiment of the present invention, such as steps 101-103, can first perform a preliminary division on the point cloud collected by the roadside equipment to obtain multiple first point cloud blocks; then, determine a second point cloud block including a portion of the road point cloud from the multiple first point cloud blocks; thereafter, the road boundary can be further determined based on the second point cloud block to facilitate the subsequent acquisition of the road point cloud, thereby simplifying the point cloud processing process and avoiding a large amount of resource consumption.

[0087] The roadside device may be a roadside sensor, and the point cloud collected by the roadside sensor is a roadside laser point cloud. In this way, the method of this embodiment is applied to a data processing device (such as a roadside device). In a scenario where the roadside device assists an unmanned vehicle in vehicle-road collaboration, the road boundary can be determined with fewer resources and faster processing, thereby obtaining a road point cloud, completing the detection and identification of road traffic elements, and cooperating with the perception capability of the vehicle to realize the implementation of vehicle-road collaboration.

[0088] It should be known that the point cloud collected by the roadside equipment is three-dimensional data. In this embodiment, to facilitate the determination of the road boundary, optionally, step 101 includes:

[0089] Based on a preset coordinate system, converting the point cloud collected by the roadside equipment into a plane point cloud;

[0090] The planar point cloud is divided into a plurality of first point cloud blocks.

[0091] In this way, the spatial point cloud is converted into a planar point cloud for subsequent processing, which further simplifies the complexity of the processing.

[0092] The preset coordinate system can be a Cartesian coordinate system based on the roadside equipment (such as a lidar) as the center, with the positive direction of the x-axis directly in front of the roadside equipment, the positive direction of the z-axis directly above, and the positive direction of the y-axis horizontally to the right. In the process of converting the plane point cloud, since the height information of the point cloud (the length on the z-axis) in the direction perpendicular to the ground is not the same in the actual point cloud, the reference point cloud will be used for plane conversion. Specifically, the height information of each point cloud is classified, and the point cloud with the smallest height is extracted and mapped to the top view, that is, a plane parallel to the ground plane, to obtain a plane point cloud, such as Figure 2 As shown, point O in the figure is the location of the roadside equipment.

[0093] For a plane point cloud, it can be equally divided according to a certain width (ie, the length on the y-axis) to obtain multiple first point cloud blocks. At this time, the width of each first point cloud block is equal to the width value used for the equal division.

[0094] In this embodiment, after the point cloud is divided into a plurality of first point cloud blocks, a point cloud block including a portion of the road point cloud is further determined based on the plurality of first point cloud blocks. Since the point cloud intensity information of the road area and the non-road area is significantly different, step 102 includes:

[0095] According to the intensity information of the road point cloud, starting from the edge point cloud block among the multiple first point cloud blocks, each first point cloud block is analyzed in turn along the first preset direction to determine whether the analyzed first point cloud block is the second point cloud block. If so, stop analyzing the remaining first point cloud blocks; if not, continue analyzing the next first point cloud block.

[0096] In this way, each first point cloud block will be analyzed in turn according to the first preset direction, and after the second point cloud block is found for the first time, the current analysis will be stopped to avoid analyzing all the first point cloud blocks and reduce resource consumption.

[0097] The first preset direction is set based on the arrangement of the plurality of first point cloud blocks, and considering the double-side boundaries of the road, the first preset direction includes the positive and negative directions of the direction. Figure 2 As shown, multiple first point cloud blocks are arranged in the y-axis direction, and the first preset direction is the direction indicated by the y-axis, including the positive direction of the y-axis and the negative direction of the y-axis. Therefore, the left and right second point cloud blocks can be determined.

[0098] Of course, for the analysis of the first point cloud block in the positive and negative directions, the analysis can be performed one by one from the edge point cloud blocks in both directions; or, first search for the second point cloud block inward from the edge point cloud block in one direction, and then search for the second point cloud block inward from the edge point cloud block in the other opposite direction.

[0099] After the second point cloud block is determined, the road boundary can be determined based on the second point cloud block. In this embodiment, optionally, step 103 includes:

[0100] Based on the second point cloud block, divide it according to a preset rule to obtain a plurality of candidate point cloud blocks;

[0101] Determine a target point cloud block among the multiple candidate point cloud blocks;

[0102] According to the boundary position of the target point cloud block or the road point cloud position, a road boundary is obtained; wherein,

[0103] The intensity information of the point cloud on the first boundary of the target point cloud block is consistent with the intensity information of the road point cloud, and the intensity information of the point cloud on the second boundary is inconsistent with the intensity information of the road point cloud, and the first boundary is opposite to the second boundary; or, the intensity information of the point cloud on at least one boundary of the target point cloud block partially conforms to the intensity information of the road point cloud, and partially does not conform to the intensity information of the road point cloud.

[0104] In this way, after using a larger width to divide and obtain multiple first point cloud blocks and determining the second point cloud block, the candidate point cloud blocks with smaller widths will be further divided until the target point cloud block is determined, and then the road boundary is obtained from the boundary position of the target point cloud block or the road point cloud position.

[0105] Here, for roads with straight boundaries (i.e., straight roads), the target point cloud block to be found is one in which the intensity information of the point cloud on the first boundary is consistent with the intensity information of the road point cloud, while the intensity information of the point cloud on the second boundary does not conform to the intensity information of the road point cloud; for roads with curved boundaries (i.e., bends), the target point cloud block to be found is one in which the intensity information of the point cloud on at least one boundary partially conforms to the intensity information of the road point cloud, and partially does not conform to the intensity information of the road point cloud.

[0106] Among them, the preset rule is for further subdividing the second point cloud block. Compared with the division of the first point cloud block, the second point cloud block will be divided according to a smaller width, such as half or one quarter of the original width.

[0107] In addition, optionally, the preset rules include:

[0108] When the width of the determined target point cloud block is greater than a preset threshold, the determined target point cloud block is divided.

[0109] That is, after the second point cloud block is initially divided and the target point cloud block is selected from the candidate point cloud blocks obtained by the current division, the target point cloud block will be further subdivided until the width of the determined target point cloud block is less than or equal to the preset threshold. The preset threshold is set based on the width of the road boundary, such as 20cm. In this way, the target point cloud block finally obtained is divided according to a better width granularity, thereby improving the accuracy of the road boundary obtained from the boundary position of the target point cloud block or the road point cloud position.

[0110] Of course, each subdivision of the target point cloud block may be half or a quarter of the width of the previous target point cloud block, etc., and may be consistent with or different from the width variation rule of the second point cloud block division.

[0111] Optionally, for a road with a straight line boundary, the road boundary can be obtained based on the boundary position of the target point cloud block (the target point cloud block whose width is less than or equal to the preset threshold) obtained in the end. Figure 2As shown, assuming that the boundary equations of the target point cloud block corresponding to the left road boundary are y=a1 and y=a2, the boundary equation of the left road boundary is y=(a1+a2) / 2; similarly, corresponding to the right road boundary, the boundary equations of the target point cloud block corresponding to the right road boundary are y=b1 and y=b2, the boundary equation of the right road boundary is y=(b1+b2) / 2. For the road boundary, z=-h, where h is the height of the roadside equipment relative to the ground plane.

[0112] For roads with curved boundaries, the road boundary can be fitted based on the position of the road point cloud (i.e., the point cloud whose intensity information conforms to the intensity information of the road point cloud) in the final target point cloud block (the target point cloud block whose width is less than or equal to the preset threshold). Specifically, the road point cloud is fitted using the random sampling consistent RANSAC algorithm to obtain the road boundary equation y=a*x 2 +bx+c. Similarly, the boundary equations of the roads on both sides can be obtained, and z=-h, where h is the height of the roadside equipment relative to the ground plane.

[0113] In addition, in this embodiment, after step 103, the following steps are further included:

[0114] Get the centerline position of the road boundary;

[0115] Determining whether the distance between the centerline position and the road boundary conforms to the road width setting;

[0116] If yes, obtaining a point cloud of the road area according to the road boundary;

[0117] If not, the point cloud collected by the roadside equipment is divided again until the point cloud of the road area is obtained.

[0118] Here, the centerline position of the road boundary can be obtained by the road boundaries on both sides. Then, the distance between the centerline position and the road boundary is used to determine whether it meets the road width setting, such as 3.5m, to eliminate some point cloud noise interference similar to roads.

[0119] The centerline position can be obtained by calculating the road boundary equations. For example, for a road with a straight boundary, the centerline equation is y=(a1+a2+b1+b2) / 2. Similarly, for a road with a curved boundary, the centerline equation along the boundary can be derived based on the boundary equations of the roads on both sides.

[0120] In this way, when the road boundary is determined by the point cloud and the distance between the midline position and the road boundary meets the road width setting, the point cloud of the road area between the road boundaries on both sides can be clearly obtained based on the road boundary for subsequent processing; otherwise, it is necessary to re-divide the point cloud collected by the roadside equipment until the point cloud of the road area is obtained.

[0121] Next, combine Figure 2 The application of the method of the embodiment of the present invention is described as follows:

[0122] For a planar point cloud, Figure 2 After being equally divided into a plurality of first point cloud blocks as shown, point cloud blocks including part of the road point cloud, i.e., second point cloud blocks, will be searched from the positive and negative directions of the y-axis respectively. When the second point cloud block is found, such as the second point cloud block on the left, the second point cloud block will be subdivided into smaller point cloud blocks, and the intensity information of the boundaries of the smaller point cloud blocks will be analyzed. If the point clouds on both boundaries do not have the intensity information of the road, the smaller point cloud block will be abandoned; if the point cloud on one boundary has the intensity information of the road, and the point cloud on the other boundary does not have the intensity information of the road, the next step will be executed. In the next step, the smaller point cloud block will be further subdivided, and the analysis of the point cloud intensity information on the boundary of the point cloud block will be repeated until the subdivided point cloud block is less than or equal to the preset threshold. According to the smallest point cloud block finally found, the road boundary is obtained by the boundary positions on the left and right sides.

[0123] In the process of obtaining the boundary position of the smallest point cloud block finally found to determine the road boundary, the accuracy of the result can be verified by the center line of the obtained road boundary.

[0124] like Figure 3 As shown, an embodiment of the present invention provides a data processing device, including:

[0125] A first processing module 310, configured to divide the point cloud collected by the roadside equipment into a plurality of first point cloud blocks;

[0126] A second processing module 320 is used to determine a second point cloud block among the plurality of first point cloud blocks, wherein the second point cloud block is a point cloud block including a portion of a road point cloud;

[0127] The third processing module 330 is configured to determine a road boundary according to the second point cloud block.

[0128] Optionally, the first processing module includes:

[0129] A conversion submodule, used to convert the point cloud collected by the roadside equipment into a plane point cloud based on a preset coordinate system;

[0130] The first processing submodule is used to divide the plane point cloud into a plurality of first point cloud blocks.

[0131] Optionally, the second processing module is further used for:

[0132] According to the intensity information of the road point cloud, starting from the edge point cloud block among the multiple first point cloud blocks, each first point cloud block is analyzed in turn along the first preset direction to determine whether the analyzed first point cloud block is the second point cloud block. If so, stop analyzing the remaining first point cloud blocks; if not, continue analyzing the next first point cloud block.

[0133] Optionally, the third processing module includes:

[0134] A second processing submodule, configured to divide the second point cloud block into a plurality of candidate point cloud blocks according to a preset rule;

[0135] A third processing submodule, configured to determine a target point cloud block among the plurality of candidate point cloud blocks;

[0136] The fourth processing submodule is used to obtain the road boundary according to the boundary position of the target point cloud block or the road point cloud position; wherein,

[0137] The intensity information of the point cloud on the first boundary of the target point cloud block is consistent with the intensity information of the road point cloud, and the intensity information of the point cloud on the second boundary is inconsistent with the intensity information of the road point cloud, and the first boundary is opposite to the second boundary; or, the intensity information of the point cloud on at least one boundary of the target point cloud block partially conforms to the intensity information of the road point cloud, and partially does not conform to the intensity information of the road point cloud.

[0138] Optionally, the preset rules include:

[0139] When the width of the determined target point cloud block is greater than a preset threshold, the determined target point cloud block is divided.

[0140] Optionally, the device further comprises:

[0141] An acquisition module, used for acquiring the centerline position of the road boundary;

[0142] A judgment module, used to judge whether the distance between the center line position and the road boundary meets the road width setting;

[0143] A fourth processing module, configured to obtain a point cloud of the road area according to the road boundary;

[0144] The fifth processing module is used to, if not, re-divide the point cloud collected by the roadside equipment until the point cloud of the road area is obtained.

[0145] The device can first perform preliminary division on the point cloud collected by the roadside equipment to obtain multiple first point cloud blocks; then, determine the second point cloud block including part of the road point cloud from the multiple first point cloud blocks; thereafter, it can further determine the road boundary based on the second point cloud block to facilitate the subsequent acquisition of the road point cloud, thereby simplifying the point cloud processing process and avoiding a large consumption of resources.

[0146] It should be noted that the device is a device that applies the above-mentioned data processing method, and the implementation method of the above-mentioned method embodiment is applicable to the device and can also achieve the same technical effect.

[0147] like Figure 4 As shown, a data processing device 400 according to an embodiment of the present invention includes a processor 410; the processor 410 is used to:

[0148] Dividing the point cloud collected by the roadside equipment into a plurality of first point cloud blocks;

[0149] Determine a second point cloud block among the plurality of first point cloud blocks, wherein the second point cloud block is a point cloud block including a portion of a road point cloud;

[0150] A road boundary is determined based on the second point cloud block.

[0151] Optionally, the processor is further configured to:

[0152] Based on a preset coordinate system, converting the point cloud collected by the roadside equipment into a plane point cloud;

[0153] The planar point cloud is divided into a plurality of first point cloud blocks.

[0154] Optionally, the processor is further configured to:

[0155] According to the intensity information of the road point cloud, starting from the edge point cloud block among the multiple first point cloud blocks, each first point cloud block is analyzed in turn along the first preset direction to determine whether the analyzed first point cloud block is the second point cloud block. If so, stop analyzing the remaining first point cloud blocks; if not, continue analyzing the next first point cloud block.

[0156] Optionally, the processor is further configured to:

[0157] Based on the second point cloud block, divide it according to a preset rule to obtain a plurality of candidate point cloud blocks;

[0158] Determine a target point cloud block among the multiple candidate point cloud blocks;

[0159] According to the boundary position of the target point cloud block or the road point cloud position, a road boundary is obtained; wherein,

[0160] The intensity information of the point cloud on the first boundary of the target point cloud block is consistent with the intensity information of the road point cloud, and the intensity information of the point cloud on the second boundary is inconsistent with the intensity information of the road point cloud, and the first boundary is opposite to the second boundary; or, the intensity information of the point cloud on at least one boundary of the target point cloud block partially conforms to the intensity information of the road point cloud, and partially does not conform to the intensity information of the road point cloud.

[0161] Optionally, the preset rules include:

[0162] When the width of the determined target point cloud block is greater than a preset threshold, the determined target point cloud block is divided.

[0163] Optionally, the processor is further configured to:

[0164] Get the centerline position of the road boundary;

[0165] Determining whether the distance between the centerline position and the road boundary conforms to the road width setting;

[0166] If yes, obtaining a point cloud of the road area according to the road boundary;

[0167] If not, the point cloud collected by the roadside equipment is divided again until the point cloud of the road area is obtained.

[0168] Optionally, the data processing device further includes a transceiver 420 for receiving and sending data under the control of the processor 410 .

[0169] The data processing equipment of this embodiment can first perform a preliminary division on the point cloud collected by the roadside equipment to obtain multiple first point cloud blocks; then, determine a second point cloud block including a part of the road point cloud from the multiple first point cloud blocks; thereafter, it can further determine the road boundary based on the second point cloud block to facilitate the subsequent acquisition of the road point cloud, thereby simplifying the point cloud processing process and avoiding a large consumption of resources.

[0170] A data processing device according to another embodiment of the present invention, Figure 5 As shown, it includes a transceiver 510, a processor 500, a memory 520, and a program or instruction stored in the memory 520 and executable on the processor 500; when the processor 500 executes the program or instruction, the above-mentioned data processing method is implemented.

[0171] The transceiver 510 is used to receive and send data under the control of the processor 500 .

[0172] Among them, Figure 5In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 500 and memory represented by memory 520. The bus architecture may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 510 may be a plurality of components, i.e., including a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. The processor 500 is responsible for managing the bus architecture and general processing, and the memory 520 may store data used by the processor 500 when performing operations.

[0173] A readable storage medium according to an embodiment of the present invention stores a program or instruction thereon. When the program or instruction is executed by a processor, the steps in the data processing method described above are implemented and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0174] The processor is a processor in the data processing device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0175] It should be further explained that many functional components described in this specification are referred to as modules in order to more particularly emphasize the independence of their implementation methods.

[0176] In the embodiment of the present invention, module can be implemented with software so that it can be executed by various types of processors. For example, an executable code module of an identification can include one or more physical or logical blocks of computer instructions, for example, it can be constructed as an object, process or function. Nevertheless, the executable code of the identified module does not need to be physically located together, but can include different instructions stored in different positions, and when these instructions are logically combined together, it constitutes a module and realizes the specified purpose of the module.

[0177] In fact, executable code module can be a single instruction or many instructions, and can even be distributed on a plurality of different code segments, distributed among different programs, and distributed across a plurality of memory devices. Similarly, operating data can be identified in the module, and can be implemented and organized in the data structure of any appropriate type according to any appropriate form. The operating data can be collected as a single data set, or can be distributed in different locations (including on different storage devices), and can only be present on a system or network as an electronic signal at least in part.

[0178] When a module can be implemented by software, considering the level of existing hardware technology, a person skilled in the art can build a corresponding hardware circuit to implement the corresponding function of the module that can be implemented by software without considering the cost. The hardware circuit includes a conventional very large scale integration (VLSI) circuit or gate array and existing semiconductors such as logic chips, transistors, or other discrete components. The module can also be implemented by a programmable hardware device, such as a field programmable gate array, a programmable array logic, a programmable logic device, etc.

[0179] The above exemplary embodiments are described with reference to the accompanying drawings, and many different forms and embodiments are feasible without departing from the spirit and teachings of the present invention. Therefore, the present invention should not be constructed as a limitation of the exemplary embodiments proposed herein. More specifically, these exemplary embodiments are provided so that the present invention will be perfect and complete, and the scope of the present invention will be conveyed to those who are familiar with the technology. In these figures, the component sizes and relative sizes may be exaggerated for clarity. The terms used here are only based on the purpose of describing specific exemplary embodiments and are not intended to be limiting. As used herein, unless the text clearly indicates otherwise, the singular forms "one", "an" and "the" are intended to include these multiple forms. It will be further understood that the terms "including" and / or "comprising" when used in this specification indicate the presence of the features, integers, steps, operations, components and / or components, but do not exclude the presence or increase of one or more other features, integers, steps, operations, components, components and / or their groups. Unless otherwise indicated, when stated, a range of values ​​includes the upper and lower limits of that range and any subranges therebetween.

[0180] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A data processing method, characterized in that: include: Dividing the point cloud collected by the roadside equipment into a plurality of first point cloud blocks; Determine a second point cloud block among the plurality of first point cloud blocks, wherein the second point cloud block is a point cloud block including a portion of a road point cloud; determining a road boundary according to the second point cloud block; Wherein, determining the road boundary according to the second point cloud block includes: Based on the second point cloud block, divide it according to a preset rule to obtain a plurality of candidate point cloud blocks; Determine a target point cloud block among the multiple candidate point cloud blocks; According to the boundary position of the target point cloud block or the road point cloud position, a road boundary is obtained; wherein, The intensity information of the point cloud on the first boundary of the target point cloud block conforms to the intensity information of the road point cloud, and the intensity information of the point cloud on the second boundary does not conform to the intensity information of the road point cloud, and the first boundary is opposite to the second boundary; or, the intensity information of the point cloud on at least one boundary of the target point cloud block partially conforms to the intensity information of the road point cloud, and partially does not conform to the intensity information of the road point cloud; The preset rules include: When the width of the determined target point cloud block is greater than a preset threshold, the determined target point cloud block is divided.

2. The method according to claim 1, characterized in that The step of dividing the point cloud collected by the roadside equipment into a plurality of first point cloud blocks includes: Based on a preset coordinate system, converting the point cloud collected by the roadside equipment into a plane point cloud; The planar point cloud is divided into a plurality of first point cloud blocks.

3. The method according to claim 1, characterized in that The determining a second point cloud block among the plurality of first point cloud blocks comprises: According to the intensity information of the road point cloud, starting from the edge point cloud block among the multiple first point cloud blocks, each first point cloud block is analyzed in turn along the first preset direction to determine whether the analyzed first point cloud block is the second point cloud block. If so, stop analyzing the remaining first point cloud blocks; if not, continue analyzing the next first point cloud block.

4. The method according to claim 1, characterized in that: After determining the road boundary according to the second point cloud block, the method further includes: Get the centerline position of the road boundary; Determining whether the distance between the centerline position and the road boundary conforms to the road width setting; If yes, obtaining a point cloud of the road area according to the road boundary; If not, the point cloud collected by the roadside equipment is divided again until the point cloud of the road area is obtained.

5. A data processing device, characterized in that: include: A first processing module, used for dividing the point cloud collected by the roadside equipment into a plurality of first point cloud blocks; A second processing module, configured to determine a second point cloud block among the plurality of first point cloud blocks, wherein the second point cloud block is a point cloud block including a portion of a road point cloud; A third processing module, configured to determine a road boundary according to the second point cloud block; Wherein, the third processing module includes: A second processing submodule, configured to divide the second point cloud block into a plurality of candidate point cloud blocks according to a preset rule; A third processing submodule, configured to determine a target point cloud block among the plurality of candidate point cloud blocks; The fourth processing submodule is used to obtain the road boundary according to the boundary position of the target point cloud block or the road point cloud position; wherein, The intensity information of the point cloud on the first boundary of the target point cloud block conforms to the intensity information of the road point cloud, and the intensity information of the point cloud on the second boundary does not conform to the intensity information of the road point cloud, and the first boundary is opposite to the second boundary; or, the intensity information of the point cloud on at least one boundary of the target point cloud block partially conforms to the intensity information of the road point cloud, and partially does not conform to the intensity information of the road point cloud; The preset rules include: When the width of the determined target point cloud block is greater than a preset threshold, the determined target point cloud block is divided.

6. The device according to claim 5, characterized in that The first processing module comprises: A conversion submodule, used to convert the point cloud collected by the roadside equipment into a plane point cloud based on a preset coordinate system; The first processing submodule is used to divide the plane point cloud into a plurality of first point cloud blocks.

7. The device according to claim 5, characterized in that The second processing module is also used for: According to the intensity information of the road point cloud, starting from the edge point cloud block among the multiple first point cloud blocks, each first point cloud block is analyzed in turn along the first preset direction to determine whether the analyzed first point cloud block is the second point cloud block. If so, stop analyzing the remaining first point cloud blocks; if not, continue analyzing the next first point cloud block.

8. A data processing device, characterized in that: A processor is included; the processor is used to: Dividing the point cloud collected by the roadside equipment into a plurality of first point cloud blocks; Determine a second point cloud block among the plurality of first point cloud blocks, wherein the second point cloud block is a point cloud block including a portion of a road point cloud; determining a road boundary according to the second point cloud block; The processor is further configured to: Based on the second point cloud block, divide it according to a preset rule to obtain a plurality of candidate point cloud blocks; Determine a target point cloud block among the multiple candidate point cloud blocks; According to the boundary position of the target point cloud block or the road point cloud position, a road boundary is obtained; wherein, The intensity information of the point cloud on the first boundary of the target point cloud block conforms to the intensity information of the road point cloud, and the intensity information of the point cloud on the second boundary does not conform to the intensity information of the road point cloud, and the first boundary is opposite to the second boundary; or, the intensity information of the point cloud on at least one boundary of the target point cloud block partially conforms to the intensity information of the road point cloud, and partially does not conform to the intensity information of the road point cloud; The preset rules include: When the width of the determined target point cloud block is greater than a preset threshold, the determined target point cloud block is divided.

9. A data processing device comprising: A transceiver, a processor, a memory, and a program or instruction stored in the memory and executable on the processor; wherein the processor implements the data processing method according to any one of claims 1 to 4 when executing the program or instruction.

10. A readable storage medium having a program or instruction stored thereon, characterized in that: When the program or instruction is executed by a processor, the steps in the data processing method according to any one of claims 1 to 4 are implemented.

Images