WO2022166323A1 - 一种道路线确定的方法，相关装置以及设备 - Google Patents

一种道路线确定的方法，相关装置以及设备 Download PDF

Info

Publication number
WO2022166323A1
WO2022166323A1 PCT/CN2021/132672 CN2021132672W WO2022166323A1 WO 2022166323 A1 WO2022166323 A1 WO 2022166323A1 CN 2021132672 W CN2021132672 W CN 2021132672W WO 2022166323 A1 WO2022166323 A1 WO 2022166323A1
Authority
WO
WIPO (PCT)
Prior art keywords
sliding frame
target
point
road
initial
Prior art date
Application number
PCT/CN2021/132672
Other languages
English (en)
French (fr)
Inventor
周旺
魏宁
刘大伟
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2022166323A1 publication Critical patent/WO2022166323A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/05—Geographic models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06T2207/30256—Lane; Road marking

Definitions

  • the embodiments of the present application relate to the field of unmanned driving, and in particular, to a method for determining a road line, related devices, and equipment.
  • the point cloud that is within a preset distance from the ground in the spatial point cloud can be intercepted as the point cloud to be processed, and the point cloud to be processed can be divided into multiple grids according to the preset grid range, and the driving distance of the vehicle
  • the trajectory is the benchmark, and the grid on the left or right side of the vehicle's driving trajectory is detected according to the detection direction from the right inside to the outside. All the first detected grids are stored in the grid set, and the grid set is The grids with continuous positional relationship are divided into the same grid group, and then the grid group with the largest number of grids is selected as the road edge grid set.
  • the embodiments of the present application provide a method, related devices and equipment for determining a road line.
  • the target sliding frame is determined by the height of the laser point and the number of the laser points, and then the target road point is determined from the target sliding frame. This improves the accuracy of the determined target road point, since the target road point is used to generate the target road line, thereby improving the accuracy of the road line determination.
  • the present application provides a method for road route determination.
  • the method may be executed by a terminal device or a server, or may also be executed by a chip configured in the terminal device or server, which is not limited in this application.
  • the initial sliding frame set needs to be generated from the inside to the outside based on the target vehicle trajectory point.
  • Each initial sliding frame in the initial sliding frame set is continuous, and the height of the laser point of each initial sliding frame is based on The height of the laser points of the laser point cloud included in the initial sliding frame is determined.
  • the first initial sliding frame is determined as The sliding frame to be processed, the first initial sliding frame and the second initial sliding frame are adjacent initial sliding frames, and the distance between the second initial sliding frame and the target vehicle trajectory point is smaller than the distance between the first initial sliding frame and the target vehicle trajectory point , and then determine the target sliding frame from the sliding frame to be processed.
  • the target sliding frame is the candidate sliding frame with the highest density.
  • the candidate sliding frame is obtained by dividing the sliding frame to be processed on average.
  • the density indicates the laser beam included in the candidate sliding frame.
  • the number of points, and finally the target road point is determined from the target sliding box, and the target road point is used to generate the target road line.
  • the target sliding frame is further determined by the feature of the number of laser points in the sliding frame to be processed, and then the target road point is determined from the target sliding frame.
  • the accuracy of the determined target road point because the target road point is used to generate the target road line, thereby improving the accuracy of the road line determination.
  • the position information of the target vehicle trajectory point is obtained, and then the position information of the center point of the sliding frame to be processed is determined according to the position information of the target vehicle trajectory point.
  • the position information of the target vehicle trajectory point is the coordinate information of the target vehicle trajectory point in the coordinate system, including the abscissa and the ordinate, and the specific position information is not limited herein.
  • the extracted road points to be processed are denoised, and the multi-segment spline curve is applied to re-discrete the parameter equation to obtain the target road points.
  • the denoising process can use random sample consensus (RANSAC), mean shift (Mean Shift) clustering algorithm, and iterative closest point algorithm (iterative closest point, ICP), etc., which are not limited here.
  • the specific formula is used to determine the target road point from the target sliding box, which can improve the feasibility of this solution. Secondly, since the extracted road points to be processed are denoised, the influence of noise can be reduced, thereby improving the accuracy and reliability of the target road points.
  • the sliding frame to be processed needs to be equally divided into multiple candidate sliding frames, the density corresponding to the multiple candidate sliding frames is determined, and then the candidate sliding frame with the highest density is determined as the target sliding frame frame. Since the density indicates the number of laser points included in the candidate sliding frame, the candidate sliding frame with the highest density is the candidate sliding frame with the largest number of included laser points.
  • the target sliding frame is further determined by the feature of the number of laser spots included in the sliding frame to be processed, and the target sliding frame is determined by two features of the height of the laser spot and the number of laser spots, That is, the density feature can be used to determine the exact position of the more accurate sliding frame in the sliding frame to be processed, thereby improving the accuracy of the target sliding frame, thus improving the accuracy of the determined target road point, thereby further improving the road line Determined accuracy.
  • the initial vehicle trajectory point set before generating the initial sliding frame set from the inside to the outside based on the target vehicle trajectory point, it is also necessary to obtain the initial vehicle trajectory point set, and use the preset sampling density to analyze the initial vehicle trajectory point.
  • the set is subjected to down-sampling processing to obtain a target vehicle trajectory point set, where the target vehicle trajectory point set includes a plurality of target vehicle trajectory points.
  • the amount of data of the vehicle track points is reduced, thereby reducing the amount of calculation, thereby improving the efficiency of determining the target road point in the subsequent steps.
  • a target road line is generated by fitting the target road points obtained from multiple target vehicle track points.
  • the height of the laser spot is less than or equal to the second height threshold.
  • the amount of data of the laser points is reduced, the calculation efficiency of the subsequent steps is improved, and the interference of trees, railings and other interference objects can also be removed, thereby improving the accuracy of road line determination.
  • the target road line is a road edge line, or a road lane line.
  • the target road line is specifically defined as a road edge line or a road lane line, thereby improving the feasibility of this solution.
  • the target road line is used to create a high-resolution map.
  • a high-precision map is created through the target road line, and the driving area of the unmanned vehicle can be restricted by the target road line in the high-precision map when the unmanned vehicle is driving, thereby improving the unmanned vehicle. the accuracy of the driving route.
  • the present application provides a road line determination device, the road line determination device comprising:
  • the generation module is used to generate the initial sliding frame set from the inside to the outside based on the target vehicle trajectory point, wherein each initial sliding frame in the initial sliding frame set is continuous, and the height of each initial sliding frame is based on the initial sliding frame. Determined by the height of the laser points of the included laser point cloud;
  • a determination module configured to determine the first initial sliding frame as a pending sliding frame if the difference between the height of the first initial sliding frame and the height of the second initial sliding frame is greater than the first height threshold, wherein the first initial sliding frame
  • the second initial sliding frame is an adjacent initial sliding frame, and the distance between the second initial sliding frame and the target vehicle trajectory point is smaller than the distance between the first initial sliding frame and the target vehicle trajectory point;
  • the determination module is also used to determine the target sliding frame according to the sliding frame to be processed, wherein the target sliding frame is the candidate sliding frame with the largest density, and the candidate sliding frame is obtained by dividing the sliding frame to be processed equally, and the density indicates the candidate sliding frame. the number of laser spots included;
  • the determining module is further configured to determine a target road point from the target sliding frame, wherein the target road point is used to generate a target road line.
  • the road route determination device further includes an acquisition module
  • an acquisition module for acquiring the position information of the target vehicle trajectory point
  • the determining module is further configured to determine the position information of the center point of the sliding frame to be processed according to the position information of the target vehicle track point;
  • a determination module which is specifically configured to determine the road point to be processed from the target sliding frame according to the position information of the center point of the sliding frame to be processed;
  • the determining module is specifically configured to equally divide the sliding frame to be processed into multiple candidate sliding frames
  • the candidate sliding box with the highest density is determined as the target sliding box.
  • the acquisition module is further configured to acquire the initial vehicle trajectory point set before the generation module generates the initial sliding frame set from the inside to the outside based on the target vehicle trajectory point;
  • the acquisition module is further configured to perform down-sampling processing on the initial vehicle trajectory point set by using a preset sampling density to obtain a target vehicle trajectory point set, wherein the target vehicle trajectory point set includes a plurality of target vehicle trajectory points.
  • the generation module is further configured to fit the target road points obtained from multiple target vehicle track points after the determination module determines the target road points according to the target sliding frame to generate the target road points. road line.
  • the height of the laser spot is less than or equal to the second height threshold.
  • the target road line is a road edge line, or a road lane line.
  • the target road line is used for a high-precision map map.
  • an embodiment of the present application provides a terminal device, where the terminal device may be the device for determining a road line in the above method design, or a chip provided in the device for determining a road line.
  • the terminal device includes: a processor, coupled with the memory, and configured to execute the instructions in the memory, so as to implement the method performed by the apparatus for determining the road route in the first aspect and any possible implementation manner thereof.
  • the terminal device further includes a memory.
  • the terminal device further includes a communication interface, and the processor is coupled to the communication interface.
  • the communication interface may be a transceiver, or an input/output interface.
  • the communication interface may be an input/output interface.
  • the transceiver may be a transceiver circuit.
  • the input/output interface may be an input/output circuit.
  • an embodiment of the present application provides a server, where the server may be the road line determination device in the above method design, or a chip provided in the road line determination device.
  • the server includes: a processor, coupled with the memory, and configured to execute instructions in the memory, so as to implement the method performed by the apparatus for determining the road route in the first aspect and any possible implementation manner thereof.
  • the server further includes a memory.
  • the server further includes a communication interface to which the processor is coupled.
  • the communication interface may be a transceiver, or an input/output interface.
  • the communication interface may be an input/output interface.
  • the transceiver may be a transceiver circuit.
  • the input/output interface may be an input/output circuit.
  • a processor comprising: an input circuit, an output circuit and a processing circuit.
  • the processing circuit is configured to receive a signal through the input circuit and transmit a signal through the output circuit, so that the processor executes the method in any one of the possible implementation manners of the first aspect.
  • the above-mentioned processor may be a chip
  • the input circuit may be an input pin
  • the output circuit may be an output pin
  • the processing circuit may be a transistor, a gate circuit, a flip-flop, and various logic circuits.
  • the input signal received by the input circuit may be received and input by, for example, but not limited to, a receiver
  • the signal output by the output circuit may be, for example, but not limited to, output to and transmitted by a transmitter
  • the circuit can be the same circuit that acts as an input circuit and an output circuit at different times.
  • the embodiments of the present application do not limit the specific implementation manners of the processor and various circuits.
  • a road route determination device including a processor and a memory.
  • the processor is configured to read instructions stored in the memory, and can receive signals through a receiver and transmit signals through a transmitter, so that the apparatus performs the method in any possible implementation manner of the first aspect.
  • processors there are one or more processors and one or more memories.
  • the memory may be integrated with the processor, or the memory may be provided separately from the processor.
  • the memory can be a non-transitory memory, such as a read only memory (ROM), which can be integrated with the processor on the same chip, or can be separately set in different On the chip, the embodiment of the present application does not limit the type of the memory and the setting manner of the memory and the processor.
  • ROM read only memory
  • the road route determination device in the sixth aspect may be a chip, and the processor may be implemented by hardware or software.
  • the processor may be a logic circuit, an integrated circuit, etc.; when implemented by software, the processor may be a logic circuit, an integrated circuit, etc.
  • the processor can be a general-purpose processor, which is realized by reading software codes stored in a memory, and the memory can be integrated in the processor or located outside the processor and exist independently.
  • a computer program product comprising: a computer program (also referred to as code, or instructions), which, when the computer program is executed, causes the computer to execute any one of the above-mentioned first aspects.
  • a computer program also referred to as code, or instructions
  • a computer-readable storage medium stores a computer program (which may also be referred to as code, or an instruction), when it is run on a computer, causing the computer to execute the above-mentioned first aspect method in any of the possible implementations.
  • the present application provides a chip system, the chip system includes a processor and an interface, the interface is used to obtain a program or an instruction, and the processor is used to call the program or instruction to implement or support a terminal device/
  • the server implements the functions involved in the first aspect, for example, determining or processing at least one of the data and information involved in the above method.
  • the chip system further includes a memory for storing necessary program instructions and data of the terminal device/server.
  • the chip system may be composed of chips, or may include chips and other discrete devices.
  • the present application provides a vehicle on which the road line determination device in the above embodiment is deployed, or a chip provided in the road line determination device.
  • the vehicle includes: a processor coupled to the memory and operable to execute instructions in the memory, so as to implement the method performed by the apparatus for determining a road route in the first aspect and any of its possible implementations.
  • FIG. 1 is a schematic diagram of an electronic map data collection scene provided by an embodiment of the present application.
  • FIG. 2 is a schematic diagram of a scene of a method for determining a road route in an embodiment of the present application
  • FIG. 3 is a schematic diagram of another scenario of a method for determining a road route in an embodiment of the present application
  • FIG. 4 is a schematic diagram of an embodiment of a method for determining a road route in an embodiment of the present application
  • FIG. 5 is a schematic diagram of an embodiment of generating an initial sliding frame set in an embodiment of the present application
  • FIG. 6 is a schematic diagram of another embodiment of generating an initial sliding frame set in an embodiment of the present application.
  • FIG. 7 is a schematic diagram of an embodiment of the height of the initial sliding frame in the embodiment of the present application.
  • FIG. 8 is a schematic diagram of an embodiment of determining a sliding frame to be processed in an embodiment of the present application.
  • FIG. 9 is a schematic diagram of another embodiment of determining a sliding frame to be processed in an embodiment of the present application.
  • FIG. 10 is a schematic diagram of an embodiment of determining a target sliding frame in an embodiment of the present application.
  • FIG. 11 is a schematic diagram of an embodiment of determining a target road point in an embodiment of the present application.
  • FIG. 12 is a schematic diagram of an embodiment of generating a target road line in an embodiment of the present application.
  • FIG. 13 is a schematic diagram of an embodiment of a road route determination device in an embodiment of the present application.
  • FIG. 14 is a schematic diagram of a computer program product in an embodiment of the present application.
  • the laser beam is irradiated to the surface of the object through a sensor (such as lidar), and the laser reflected by the surface of the object is the laser point, and the laser point will carry the information such as the azimuth, distance, reflectivity and height of the object surface.
  • a sensor such as lidar
  • the laser beam is scanned according to a certain trajectory line, since the scanning is extremely fine, a large number of laser points can be obtained, thereby forming a laser point cloud.
  • FIG. 1 is a schematic diagram of an electronic map data collection scenario provided by an embodiment of the present application.
  • the data of the electronic map is mainly collected by the laser radar 120, and the laser radar 120 is arranged on the top of the mobile carrier.
  • the method for determining the road line provided by the embodiment of the present application is generated by an unmanned vehicle in real time, or generated by a cloud server, or generated by a collection vehicle after collection by a subsequent computing device.
  • the road line is taken as an example for the introduction.
  • FIG. 2 is a schematic diagram of a scenario of the method for determining the road line in the embodiment of the present application.
  • the road line determining device may be deployed in an unmanned The terminal device for driving the vehicle 200, as shown in (A) of FIG.
  • the terminal device when the unmanned vehicle 200 is driving on the road, the terminal device obtains the driving trajectory of the unmanned vehicle 200 in real time, and the driving trajectory is a plurality of consecutive As shown in (B) of Figure 2, the terminal device generates multiple continuous road points in real time based on multiple continuous track points. Finally, as shown in Figure 2 (C), the terminal device passes through multiple Consecutive road points generate road lines, that is, road edge lines.
  • the terminal device may be a device with high computing power such as a smart phone, a tablet computer, a notebook computer, a PDA, a personal computer, a smart TV, a smart watch, etc. limited to this.
  • FIG. 3 is a schematic diagram of another scenario of the method for determining the road line in the embodiment of the present application.
  • the driving track of the unmanned vehicle 300 may be stored, and the server may also acquire the vehicle driving track of the unmanned vehicle 300 in real time. Therefore, as shown in (A) of FIG. 3 , the server obtains the vehicle traveling trajectory of the unmanned vehicle 300 in real time, or obtains the vehicle traveling trajectory of the unmanned vehicle 300 from the memory, and as shown in FIG. 3 (B) As shown in Figure 3 (C), the server generates multiple continuous road points based on the multiple continuous track points.
  • the server generates multiple Road lines, that is, generate road edge lines. Based on this, the real-time generation of the road line can be completed by the server, or the generation can be performed when needed.
  • the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud service, cloud database, cloud Cloud servers for computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and basic cloud computing services such as big data and artificial intelligence platforms .
  • the unmanned vehicle and the server may be directly or indirectly connected through wired or wireless communication, which is not limited in this application.
  • FIG. 4 is one of the methods for determining road lines in the embodiments of the present application.
  • a schematic diagram of the embodiment, as shown in FIG. 4 the specific steps of the method for determining a road line are as follows.
  • the road line determination device first needs to acquire multiple laser points collected by the lidar , since each laser point can carry information such as the azimuth, distance, height and reflectivity of the surface of the object scanned by the lidar, the height of the laser point is less than or equal to the height threshold among the multiple laser points collected by the lidar.
  • the laser spot is identified as the laser spot required for this scheme. In this way, the amount of data of the laser points is reduced, the calculation efficiency of the subsequent steps is improved, and the interference of trees, railings and other interference objects can also be removed, and the accuracy of road line determination can be improved.
  • the height of the laser point is the height of the road line scanned by the lidar from the road surface.
  • the second height threshold is set to 50 centimeters (centimetre, cm), so the height of the laser spot required in this solution from the road surface is all less than or equal to 50 cm, and the initial laser spot greater than 50 cm should not be used in the subsequent steps. calculate. It should be understood that, in practical applications, the second height threshold can also be 60cm, 80cm or 90cm, etc.
  • the specific second height threshold needs to be flexibly determined by the specific environment of the road and the road layout and other aspects. Examples of height thresholds should not be construed as limitations of this application.
  • the vehicle driving trajectory of the vehicle when the unmanned vehicle is driving, the vehicle driving trajectory of the vehicle can be obtained, and the vehicle driving trajectory can be divided into a plurality of continuous vehicle trajectory points, and the road line determination device is based on the plurality of continuous vehicle trajectory points.
  • the initial vehicle trajectory point set can be obtained, so each initial vehicle trajectory point in the initial vehicle trajectory point set is continuous, and the number of initial vehicle trajectory points is large.
  • a downsampling process is performed to obtain a target vehicle trajectory point set including multiple target vehicle trajectory points, thereby reducing the amount of data of the vehicle trajectory points and improving the efficiency of determining the target road points in the subsequent steps.
  • the preset sampling density is set to 1 meter (meter, m), that is, after the vehicle obtains the set of initial vehicle trajectory points, a target vehicle is obtained every 1m from a plurality of consecutive initial vehicle trajectory points. track point.
  • the initial vehicle trajectory point set includes 100 initial vehicle trajectory points, and the interval between each initial vehicle trajectory point is 10cm.
  • the last initial vehicle trajectory point is determined as the desired target vehicle trajectory point, and then in the next 10 consecutive initial vehicle trajectory points, the target vehicle trajectory point is determined in a similar way, so it can be 10 target vehicle trajectory points are determined among 100 initial vehicle trajectory points, thereby generating a target vehicle trajectory point set including 10 target vehicle trajectory points.
  • the preset sampling density may also be 50cm, 80cm or 1.2m, etc.
  • the specific preset sampling density needs to be flexibly determined by the specific number of initial vehicle trajectory points. Examples should not be construed as limitations of this application.
  • an initial sliding frame set is generated from the inside to the outside.
  • the road line determination device After the road line determination device obtains a laser point set including multiple laser points and a target vehicle track point set including multiple target vehicle track points through steps S401 and S402, it needs to use the target vehicle track point set as the target vehicle track point set.
  • One of the target vehicle trajectory points is used as a reference, and an initial sliding frame set is generated from the inside to the outside.
  • Each initial sliding frame in the initial sliding frame set is continuous, and each initial sliding frame includes a laser point cloud, and the laser point cloud includes At least one laser spot can thus determine the height of the initial sliding frame by the height of the laser spot of the included laser spot cloud.
  • the length of each initial sliding frame is the same.
  • the length of the first initial sliding frame is 40 cm, then the length of all initial sliding frames in the initial sliding frame set is 40 cm. It should be understood that the length of each initial sliding frame is It is flexibly determined based on the actual situation of the distance between the target vehicle trajectory point and the road line.
  • the device for determining the road line will stop generating the initial sliding frame. Or, if the total length of multiple consecutive initial sliding frames exceeds the distance between the target vehicle trajectory point and the road line, the generation of the initial sliding frame is stopped. In this case, the road line of this section of road may be damaged or blocked. , so the sliding frame to be processed cannot be determined based on the target vehicle trajectory point, that is, the subsequent steps are not performed.
  • the device for determining the road line may generate a plurality of continuous initial sliding frames from the inside to the outside from the right side of the target vehicle trajectory point, or generate a plurality of continuous initial sliding frames from the inside to the outside from the left side of the target vehicle trajectory point. Whether it is the left side or the right side of the target vehicle trajectory point is not limited by the present application.
  • FIG. 5 is a schematic diagram of an embodiment of generating an initial sliding frame set in an embodiment of the present application.
  • the target vehicle trajectory point set 500 includes target vehicle trajectory points 501 , and the target vehicle trajectory point The vehicle trajectory point 501 is used as a reference, and an initial sliding frame set A3 is generated from the right side of the target vehicle trajectory point 501 from the inside to the outside.
  • FIG. 6 is a schematic diagram of another embodiment of generating an initial sliding frame set in this embodiment of the present application.
  • the target vehicle trajectory point set 600 includes target vehicle trajectory points 601 .
  • the trajectory point 601 is used as a reference, and an initial sliding frame set 602 is generated from the right side of the target vehicle trajectory point 601 from the inside to the outside, and when the total length 603 of the initial sliding frame set 602 is equal to the distance 604 between the target vehicle trajectory point 601 and the road line , stop continuing to generate the initial set of sliding boxes.
  • FIG. 5 and FIG. 6 are only used to understand this solution, and the specific initial sliding frame set needs to be flexibly determined according to the actual situation such as the target vehicle trajectory point set and the road width.
  • each laser point can carry information such as the azimuth, distance, height and reflectivity of the surface of the object scanned by the lidar, and each initial sliding frame includes at least one laser point. Based on this, each Each initial sliding frame determines the height of the initial sliding frame by including at least one laser point.
  • FIG. 7 is a schematic diagram of an embodiment of the height of the initial sliding frame in this embodiment of the application. As shown in FIG. 7 , the initial sliding frame 700 includes a laser spot 701 , a laser spot 702 and a laser spot 703 . The height is 40cm, the height of laser point B is 35cm, and the height of laser point C is 45cm.
  • the height of the initial sliding frame 700 is the average value of the heights of the laser spots included in the laser point cloud, it is necessary to calculate the height of the laser spot 701 , the height of the laser spot 702 and the average value of the height of the laser spot 703 .
  • the height of the initial sliding frame 700 is 40 cm.
  • the height of the initial sliding frame 700 is the maximum height of the laser points of the included laser point cloud, that is, the height of the laser spot C is 45 cm, which is the height of the initial sliding frame 700, the height of the initial sliding frame 700 can be determined as 45cm. It can be understood that the foregoing examples are only used to understand this solution, and the specific manner of determining the height of the initial sliding frame needs to be flexibly determined according to the actual situation, which is not limited here.
  • the device for determining the road line needs to compare the heights of the laser spots corresponding to multiple consecutive initial sliding frames. The difference between the heights of the laser points corresponding to the sliding frame is greater than the first height threshold. At this time, the first initial sliding frame and the second initial sliding frame are adjacent initial sliding frames, and the distance between the second initial sliding frame and the target vehicle track point is greater. Recently, the first initial sliding frame is determined to be the sliding frame to be processed. It can be seen from the foregoing embodiments that the road line determination device will always generate continuous initial sliding frames from the inside to the outside before determining the sliding frame to be processed, and stop the step of generating the initial sliding frame set after determining the sliding frame to be processed.
  • the first height threshold is 5 cm as an example for description, please refer to FIG. 8 , which is a schematic diagram of an embodiment of determining a sliding frame to be processed in this embodiment of the present application.
  • the initial sliding frame is The set 800 includes an initial sliding frame 801, an initial sliding frame 802, an initial sliding frame 803, an initial sliding frame 804 and an initial sliding frame 805, and the distance from the initial sliding frame 801 to the initial sliding frame 802 to the target vehicle track point 806 is increasing.
  • the height of the initial sliding frame 801 is 40 cm and the height of the initial sliding frame 802 is 37 cm
  • the difference between the initial sliding frame 801 and the initial sliding frame 802 is 3 cm, which is less than 5 cm, and the sliding frame to be processed is not determined.
  • the difference between the initial sliding frame 802 and the initial sliding frame 803 is 2 cm, which is less than 5 cm, and the sliding frame to be processed is not determined at this time.
  • the height of the initial sliding frame 804 is 41 cm, the difference between the initial sliding frame 803 and the initial sliding frame 804 is 2 cm, which is less than 5 cm, and the sliding frame to be processed is not determined.
  • the height of the initial sliding frame 805 is 46 cm, the difference between the initial sliding frame 804 and the initial sliding frame 805 is 5 cm.
  • the initial sliding frame 804 Since the initial sliding frame 804 is closer to the target vehicle trajectory point 806, the initial sliding frame The distance between the frame 805 and the target vehicle trajectory point 806 is further, so the initial sliding frame 804 is the second initial sliding frame, and the initial sliding frame 805 is the first initial sliding frame, that is, the initial sliding frame 805 is determined as the pending sliding frame. It should be understood that the example in FIG. 8 is only used to understand this solution, and the specific determination method of the sliding frame to be processed needs to be determined flexibly according to the actual situation of the road.
  • FIG. 9 is a schematic diagram of another embodiment of determining a sliding frame to be processed in an embodiment of the application.
  • the road line determination device starts from the left side of the target vehicle trajectory point 900 from the inward.
  • the sliding frame to be processed is determined based on formula (1):
  • i is the sliding frame to be processed
  • L id is the height of the i-th initial sliding frame
  • L (i-1)d is the height of the i-1-th initial sliding frame
  • ⁇ is the first height threshold
  • L is the target The distance between the vehicle trajectory point and the road line
  • w is the length of the initial sliding frame.
  • i is the sliding frame to be processed
  • R id is the height of the laser spot of the ith initial sliding frame
  • R (i-1)d is the height of the laser spot of the ith initial sliding frame
  • ⁇ is the first height threshold
  • L is the distance between the target vehicle trajectory point and the road line
  • w is the length of the initial sliding frame.
  • the road line determination device divides the sliding frame to be processed into multiple candidate sliding frames on average, that is, the length and size of each candidate sliding frame are the same, and then determines the density corresponding to the multiple candidate sliding frames, and the density is the largest
  • the candidate sliding frame of is determined as the target sliding frame. Since the density indicates the number of laser points included in the candidate sliding frame, the candidate sliding frame with the highest density is the candidate sliding frame with the largest number of included laser points.
  • FIG. 10 is a schematic diagram of an embodiment of determining a target sliding frame in an embodiment of the present application.
  • the sliding frame 1000 to be processed is evenly divided into multiple candidate sliding frames, which are respectively: The candidate sliding frame 1001 , the candidate sliding frame 1002 , the candidate sliding frame 1003 , the candidate sliding frame 1004 , and the candidate sliding frame 1005 , and each to-be-processed sliding frame contains laser points (black dots in FIG. 10 ).
  • the number of laser spots included in the candidate sliding frame 1001 is 2
  • the number of laser spots included in the candidate sliding frame 1002 is 4
  • the number of laser points is 3, and the number of laser points included in the candidate sliding frame 1005 is 1, that is, the number of laser points included in the candidate sliding frame 1003 is the largest, so the candidate sliding frame 1003 can be determined as the target sliding frame. It should be understood that the example in FIG. 10 is only used to understand this solution, and the specific determination method of the target sliding frame needs to be flexibly determined according to the actual situation of the candidate sliding frame.
  • the road line determination device needs to obtain the position information of the target vehicle track point first, and then determine the position information of the center point of the sliding frame to be processed according to the position information of the target vehicle track point.
  • the position information of the target vehicle trajectory point is the coordinate information of the target vehicle trajectory point in the coordinate system, including the abscissa and the ordinate, and the specific position information is not limited herein.
  • FIG. 11 is a schematic diagram of an embodiment of determining the target road point in the embodiment of the application.
  • the road line determination device generates from the inside to the outside from the left side of the target vehicle trajectory point 1100
  • the sliding frame to be processed is determined by the method described in the previous embodiment, and the center point 1101 of the sliding frame to be processed is determined based on formula (3), and then the center point 1101 of the sliding frame to be processed is obtained.
  • the coordinate information in the coordinate system which is the position information of the center point of the sliding frame to be processed:
  • L io is the position information of the center point 1101 of the sliding frame to be processed
  • P x is the abscissa information in the position information of the target vehicle trajectory point 1100
  • P y is the ordinate information in the position information of the target vehicle trajectory point 1100
  • i is the sliding frame to be processed
  • L is the distance between the target vehicle trajectory point 1100 and the road line.
  • the method described in the foregoing embodiment determines the to-be-received sliding frame.
  • R io is the position information of the center point 1101 of the sliding frame to be processed
  • P x is the abscissa information in the position information of the target vehicle trajectory point 1100
  • P y is the ordinate information in the position information of the target vehicle trajectory point 1100
  • i is the sliding frame to be processed
  • L is the distance between the target vehicle trajectory point 1100 and the road line.
  • the road point to be processed is determined from the target sliding frame, specifically based on formula (5) and formula (6) to determine Pending waypoints:
  • P j is the road point to be processed
  • P ix is the abscissa information in the position information of the center point 1101 of the sliding frame to be processed
  • P iy is the ordinate information in the position information of the center point 1101 of the sliding frame to be processed
  • j is the target sliding frame
  • L is the distance between the target vehicle trajectory point 1100 and the road line
  • n is the number of evenly dividing the sliding frame to be processed into multiple candidate sliding frames.
  • the extracted road points to be processed are denoised, and the multi-segment spline curve is applied to re-discrete the parameter equation to obtain the target road points.
  • the denoising process can use RANSAC, Mean Shift clustering algorithm and ICP, etc., which is not limited here.
  • the road line determination device performs steps S403 to S406 on all the target vehicle trajectory points in the target vehicle trajectory point set, so as to obtain the target road points obtained based on each target vehicle trajectory point, and then according to the distance threshold, the The candidate points are Euler clustering. For example, short distances converge into one class, such as vehicle occlusion, noise, etc., into one class, while long distances converge into another class, such as intersections, and thus into two types. After fitting the multi-segment curves, re-sampling is performed to finally generate the target road line.
  • the road line described in the embodiment of the present application may be a road lane line or a road edge line or the like.
  • the target road line is used to create a high-resolution map map. Therefore, when the unmanned vehicle is running, the driving area of the unmanned vehicle can be restricted by the road line of the high-precision map.
  • FIG. 12 is a schematic diagram of an embodiment of generating a target road line in an embodiment of the present application. As shown in FIG. 12, if the vehicle is occluded and the noise is of a short distance type, there will be no target generated. The situation of the target road points corresponding to the vehicle track points is obtained by aggregating and fitting multiple curves and then re-sampling to obtain a continuous and uninterrupted target road line 1200 . It should be understood that the example in FIG. 12 is only used to understand this solution, and the specific manner of generating the target road line needs to be flexibly determined according to the actual situation.
  • the apparatus for determining a road route includes corresponding hardware structures and/or software modules for executing each function.
  • the present application can be implemented in hardware or in the form of a combination of hardware and computer software. Whether a function is performed by hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.
  • the embodiments of the present application may divide the functional modules of the road route determination device based on the foregoing method examples.
  • each functional module may be divided corresponding to each function, or two or more functions may be integrated into one processing module.
  • the above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules. It should be noted that, the division of modules in the embodiments of the present application is schematic, and is only a logical function division, and there may be other division manners in actual implementation.
  • FIG. 13 is a schematic diagram of an embodiment of the road line determination device in the embodiment of the application.
  • the road line determination device 1300 includes:
  • the generating module 1301 is used to generate an initial sliding frame set from the inside to the outside based on the target vehicle trajectory point, wherein each initial sliding frame in the initial sliding frame set is continuous, and the height of each initial sliding frame is based on the initial sliding frame.
  • the height of the laser point of the laser point cloud included in the box is determined;
  • a determination module 1302 configured to determine the first initial sliding frame as a pending sliding frame if the difference between the height of the first initial sliding frame and the height of the second initial sliding frame is greater than the first height threshold, wherein the first initial sliding frame The frame and the second initial sliding frame are adjacent initial sliding frames, and the distance between the second initial sliding frame and the target vehicle trajectory point is smaller than the distance between the first initial sliding frame and the target vehicle trajectory point;
  • the determining module 1302 is further configured to determine the target sliding frame according to the sliding frame to be processed, wherein the target sliding frame is the candidate sliding frame with the highest density, the candidate sliding frame is obtained by dividing the sliding frame to be processed on average, and the density indicates the candidate sliding frame the quantity included in;
  • the determining module 1302 is further configured to determine a target road point from the target sliding frame, wherein the target road point is used to generate a target road line.
  • the road route determination apparatus 1300 further includes an acquisition module 1303;
  • the determining module 1302 is further configured to determine the position information of the center point of the sliding frame to be processed according to the position information of the target vehicle track point;
  • the determining module 1302 is specifically configured to determine the road point to be processed from the target sliding frame according to the position information of the center point of the sliding frame to be processed;
  • the determining module 1302 is specifically configured to equally divide the sliding frame to be processed into multiple candidate sliding frames
  • the candidate sliding box with the highest density is determined as the target sliding box.
  • the obtaining module 1303 is further configured to obtain the initial vehicle track point set before the generating module 1301 generates the initial sliding frame set from the inside to the outside based on the target vehicle track point;
  • the acquisition module is further configured to perform down-sampling processing on the initial vehicle trajectory point set by using a preset sampling density to obtain a target vehicle trajectory point set, wherein the target vehicle trajectory point set includes a plurality of target vehicle trajectory points.
  • the generating module 1301 is further configured to, after the determining module determines the target road point according to the target sliding frame, fit the target road points obtained from multiple target vehicle track points to generate the target road line.
  • the height of the laser spot is less than or equal to the second height threshold.
  • the target road line is a road edge line, or a road lane line.
  • the target road line is used for a high-resolution map map.
  • the present application also provides a computer program product.
  • the method disclosed in FIG. 4 may be implemented as encoded on a computer-readable storage medium in a machine-readable format or encoded in a computer-readable storage medium.
  • FIG. 14 schematically illustrates a conceptual partial view of an example computer program product including a computer program for executing a computer process on a computing device, arranged in accordance with at least some embodiments presented herein.
  • computer program product 1400 is provided using signal bearing medium 1401 .
  • Signal bearing medium 1401 may include one or more program instructions 1402 that, when executed by one or more processors, may provide the functions, or portions thereof, described above with respect to FIG. 4 .
  • steps S401 to S407 may be undertaken by one or more instructions associated with the signal bearing medium 1401 .
  • program instructions 1402 in FIG. 14 also describe example instructions.
  • signal bearing medium 1401 may include computer readable medium 1403, such as, but not limited to, a hard drive, compact disc (CD), digital video disc (DVD), digital tape, memory, ROM or RAM, and the like.
  • computer readable medium 1403 such as, but not limited to, a hard drive, compact disc (CD), digital video disc (DVD), digital tape, memory, ROM or RAM, and the like.
  • the signal bearing medium 1401 may include a computer recordable medium 1404, such as, but not limited to, memory, read/write (R/W) CDs, R/W DVDs, and the like.
  • signal bearing medium 1401 may include communication medium 1405, such as, but not limited to, digital and/or analog communication media (eg, fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).
  • the signal bearing medium 1401 may be conveyed by a wireless form of communication medium 1405 (eg, a wireless communication medium conforming to the IEEE 802.11 standard or other transmission protocol).
  • the one or more program instructions 1402 may be, for example, computer-executable instructions or logic-implemented instructions.
  • a computing device of a computing device may be configured to respond to program instructions 1402 communicated to the computing device through one or more of computer readable media 1403 , computer recordable media 1404 , and/or communication media 1405 , which provides various operations, functions, or actions.
  • each step of the above-mentioned method can be completed by a hardware integrated logic circuit in a processor or an instruction in the form of software.
  • the steps of the methods disclosed in conjunction with the embodiments of the present application may be directly embodied as executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.
  • the software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art.
  • the storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, detailed description is omitted here.
  • the processor in this embodiment of the present application may be an integrated circuit chip, which has a signal processing capability.
  • the steps of the above method embodiments may be completed by hardware integrated logic circuits in the processor or instructions in the form of software.
  • the aforementioned processors may be general purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components .
  • DSPs digital signal processors
  • ASICs application specific integrated circuits
  • FPGAs field programmable gate arrays
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the steps of the method disclosed in conjunction with the embodiments of the present application may be directly embodied as executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor.
  • the software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art.
  • the storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware.
  • the memory in this embodiment of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically programmable Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory.
  • Volatile memory may be random access memory (RAM), which acts as an external cache.
  • RAM static random access memory
  • DRAM dynamic random access memory
  • SDRAM synchronous dynamic random access memory
  • double data rate SDRAM double data rate SDRAM
  • DDR SDRAM double data rate SDRAM
  • ESDRAM enhanced synchronous dynamic random access memory
  • SLDRAM synchronous link dynamic random access memory
  • direct rambus RAM direct rambus RAM
  • the present application also provides a computer program product, the computer program product includes: computer program code, when the computer program code is run on a computer, the computer is made to execute the steps shown in FIGS. 3 to 8 .
  • the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores program codes, and when the program codes are run on a computer, the computer is made to execute FIGS. 3 to 3 . 8. The method performed by the road line determination apparatus in the embodiment shown.
  • a component may be, but is not limited to, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and/or a computer.
  • an application running on a computing device and the computing device may be components.
  • One or more components may reside within a process and/or thread of execution, and a component may be localized on one computer and/or distributed between 2 or more computers.
  • these components can execute from various computer readable media having various data structures stored thereon.
  • a component may, for example, be based on a signal having one or more data packets (such as data from two components interacting with another component between a local system, a distributed system, and/or a network, such as the Internet interacting with other systems via signals) Communicate through local and/or remote processes.
  • data packets such as data from two components interacting with another component between a local system, a distributed system, and/or a network, such as the Internet interacting with other systems via signals
  • the disclosed system, apparatus and method may be implemented in other manners.
  • the apparatus embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.
  • 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 application 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 independent products, may be stored in a computer-readable storage medium.
  • the technical solution of the present application can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution.
  • the computer software product is 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 the various embodiments of the present application.
  • 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

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • Remote Sensing (AREA)
  • Computer Graphics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Traffic Control Systems (AREA)

Abstract

本申请实施例公开了一种道路线确定的方法，相关装置以及设备，用于提升目标道路点的精准度，由于目标道路点用于生成目标道路线，从而提升道路线确定的准确度。本申请实施例方法中，首先以目标车辆轨迹点为基准，由内向外生成初始滑动框集合，初始滑动框集合中每个初始滑动框是连续的，当第一初始滑动框的高度与第二初始滑动框的高度的差值大于第一高度阈值时，确定第一初始滑动框为待处理滑动框，再对待处理滑动框进行平均划分后得到候选滑动框，确定包括激光点的数量最多的候选滑动框为目标滑动框，最后从目标滑动框中确定目标道路点，该目标道路点用于生成目标道路线。

Description

一种道路线确定的方法，相关装置以及设备
本申请要求于2021年02月03日提交中国国家知识产权局、申请号为202110150102.1、发明名称为“一种道路线确定的方法，相关装置以及设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及无人驾驶领域，尤其涉及一种道路线确定的方法，相关装置以及设备。
背景技术
人工智能技术兴起的今天，无人驾驶领域潜在的价值已经越来越为人们认可，高精度地图作为无人驾驶技术中的一个非常重要的因素，占据非常重要的地位。在高精度地图的制作过程中，道路车道线和道路边沿线作为一种非常重要的要素存在于地图中。可以约束无人驾驶车辆的行驶区域。
目前，可以通过截取空间点云中距离地面高度在预设距离范围内的点云作为待处理点云，按照预设网格范围将待处理点云划分成多个网格，并且以车辆的行驶轨迹为基准，按照右内向外的检测方向对的车辆的行驶轨迹左侧或者右侧的网格进行检测，将所有被第一个检测到的网格存储至网格集合，将网格集合中位置关系连续的网格分入同一个网格组，再选取网格数量最多的网格组，作为道路边沿网格集合。
然而，由于网格的分辨率选择困难，网格的分辨率较高时，会造成时间复杂度的上升并更容易引入噪声，从而降低道路线确定的准确度。其次，网格分辨率较低时，会造成精度的损失，仍然会降低道路线确定的准确度。
发明内容
本申请实施例提供了一种道路线确定的方法，相关装置以及设备，通过激光点的高度以及激光点的数量的两个特征确定目标滑动框，再从目标滑动框中确定目标道路点，由此提升所确定目标道路点的精准度，由于该目标道路点用于生成目标道路线，从而提升道路线确定的准确度。
第一方面，本申请提供了一种道路线确定的方法。该方法可以由终端设备或者服务器执行，或者也可以由配置于终端设备或者服务器中的芯片执行，本申请对此不作限定。在该方法中，首先需要以目标车辆轨迹点为基准，由内向外生成初始滑动框集合，初始滑动框集合中每个初始滑动框是连续的，且每个初始滑动框的激光点高度是根据初始滑动框所包括的激光点云的激光点的高度确定的，当第一初始滑动框的高度与第二初始滑动框的高度的差值大于第一高度阈值，则确定第一初始滑动框为待处理滑动框，第一初始滑动框与第二初始滑动框为相邻的初始滑动框，且第二初始滑动框与目标车辆轨迹点的距离小于第一初始滑动框与目标车辆轨迹点的距离，然后从待处理滑动框中确定目标滑动框，该目标滑动框为密度最大的候选滑动框，候选滑动框是对待处理滑动框进行平均划分后得到的， 密度指示候选滑动框中所包括的激光点的数量，最后从目标滑动框中确定目标道路点，且目标道路点用于生成目标道路线。
在该实施方式中，通过激光点的高度确定待处理滑动框后，通过待处理滑动框中激光点的数量的特征进一步地确定目标滑动框，再从目标滑动框中确定目标道路点，因此提升所确定目标道路点的精准度，由于该目标道路点用于生成目标道路线，从而提升道路线确定的准确度。
在本申请的一种可选实施方式中，获取目标车辆轨迹点的位置信息，然后根据目标车辆轨迹点的位置信息，确定待处理滑动框的中心点的位置信息。其中目标车辆轨迹点的位置信息为目标车辆轨迹点在坐标系中的坐标信息，包括横坐标以及纵坐标，具体位置信息在此不做限定。基于此，对提取出来的待处理道路点进行去噪处理，并且应用多段样条曲线重新离散参数方程，以得到目标道路点。其中，去噪处理可以采用随机抽样一致算法(random sample consensus，RANSAC)，均值偏移(Mean Shift)聚类算法以及迭代最近点算法(iterative closest point，ICP)等，具体此处不做限定。
在该实施方式中，通过具体公式从目标滑动框中确定目标道路点，能够提升本方案的可行性。其次，由于对提取出来的待处理道路点进行去噪处理，能够减少噪声的影响，从而提升目标道路点的准确度以及可靠性。
在本申请的一种可选实施方式中，需要将待处理滑动框平均划分为多个候选滑动框，并且确定多个候选滑动框对应的密度，然后将密度最大的候选滑动框确定为目标滑动框。由于密度指示候选滑动框中所包括的激光点的数量，因此密度最大的候选滑动框即为所包括的激光点的数量最多的候选滑动框。
在该实施方式中，通过待处理滑动框中所包括的激光点的数量的特征进一步地确定目标滑动框，该目标滑动框是通过激光点的高以及激光点的数量的两个特征确定的，即能够使用密度特征对待处理滑动框中更为精准的滑动框的准确位置进行确定，由此提升目标滑动框的精准度，因此提升所确定目标道路点的准确度，由此进一步地提升道路线确定的准确度。
在本申请的一种可选实施方式中，在以目标车辆轨迹点为基准，由内向外生成初始滑动框集合之前，还需要获取初始车辆轨迹点集合，通过预设采样密度对初始车辆轨迹点集合进行降采样处理，以获取目标车辆轨迹点集合，目标车辆轨迹点集合包括多个目标车辆轨迹点。
在该实施方式中，减少车辆轨迹点的数据量，由此降低计算量，从而提升后续步骤确定目标道路点效率。
在本申请的一种可选实施方式中，在根据目标滑动框确定目标道路点之后，对多个目标车辆轨迹点所得到的目标道路点进行拟合，生成目标道路线。
在该实施方式中，应用样条曲线去噪拟合，重采样的方法，去掉噪声以及其他影响，并且补偿可能存在物体遮挡的部分，能够使得所生成的目标道路线是连续且接近真实道路线，由此提升目标道路线确定的准确度以及可靠性。
在本申请的一种可选实施方式中，激光点的高度小于或等于第二高度阈值。
在该实施方式中，减少激光点的数据量，提升后续步骤的计算效率，并且还能够去除 树木，栏杆以及其他干扰物的干扰，从而提升道路线确定的准确度。
申请的一种可选实施方式中，目标道路线为道路边沿线，或，道路车道线。
在该实施方式中，具体限定目标道路线为道路边沿线或道路车道线，由此提升本方案的可行性。
在本申请的一种可选实施方式中，目标道路线用于创建高精度地图地图。
在该实施方式中，通过目标道路线创建高精度地图，能够在无人驾驶车辆行驶时，通过高精度地图中的目标道路线能够约束的无人驾驶车辆的行驶区域，从而提升无人驾驶车辆的行驶路线的准确度。
第二方面，本申请提供了一种道路线确定装置，该道路线确定装置包括：
生成模块，用于以目标车辆轨迹点为基准，由内向外生成初始滑动框集合，其中，初始滑动框集合中每个初始滑动框是连续的，每个初始滑动框的高度是根据初始滑动框所包括的激光点云的激光点的高度确定的；
确定模块，用于若第一初始滑动框的高度与第二初始滑动框的高度的差值大于第一高度阈值，则确定第一初始滑动框为待处理滑动框，其中，第一初始滑动框与第二初始滑动框为相邻的初始滑动框，且第二初始滑动框与目标车辆轨迹点的距离小于第一初始滑动框与目标车辆轨迹点的距离；
确定模块，还用于根据待处理滑动框确定目标滑动框，其中，目标滑动框为密度最大的候选滑动框，候选滑动框是对待处理滑动框进行平均划分后得到的，密度指示候选滑动框中所包括的激光点的数量；
确定模块，还用于从目标滑动框中确定目标道路点，其中，目标道路点用于生成目标道路线。
在本申请的一种可选实施方式中，道路线确定装置还包括获取模块；
获取模块，用于获取目标车辆轨迹点的位置信息；
确定模块，还用于根据目标车辆轨迹点的位置信息，确定待处理滑动框的中心点的位置信息；
确定模块，具体用于根据待处理滑动框的中心点的位置信息，从目标滑动框中确定待处理道路点；
采用样条曲线对待处理道路点进行去噪处理，以得到目标道路点。
在本申请的一种可选实施方式中，确定模块，具体用于将待处理滑动框平均划分为多个候选滑动框；
确定多个候选滑动框对应的密度；
将密度最大的候选滑动框确定为目标滑动框。
在本申请的一种可选实施方式中，获取模块，还用于在生成模块以目标车辆轨迹点为基准，由内向外生成初始滑动框集合之前，获取初始车辆轨迹点集合；
获取模块，还用于通过预设采样密度对初始车辆轨迹点集合进行降采样处理，以获取目标车辆轨迹点集合，其中，目标车辆轨迹点集合包括多个目标车辆轨迹点。
在本申请的一种可选实施方式中，生成模块，还用于在确定模块根据目标滑动框确定目标道路点之后，对多个目标车辆轨迹点所得到的目标道路点进行拟合，生成目标道路线。
在本申请的一种可选实施方式中，激光点的高度小于或等于第二高度阈值。
在本申请的一种可选实施方式中，目标道路线为道路边沿线，或，道路车道线。
在本申请的一种可选实施方式中，目标道路线用于高精度地图地图。
第三方面，本申请实施例提供一种终端设备，该终端设备可以为上述方法设计中的道路线确定装置，或者，为设置在道路线确定装置中的芯片。该终端设备包括：处理器，与存储器耦合，可用于执行存储器中的指令，以实现上述第一方面及其任意一种可能的实施方式中道路线确定装置所执行的方法。可选地，该终端设备还包括存储器。可选地，该终端设备还包括通信接口，处理器与通信接口耦合。
当终端设备为道路线确定装置时，该通信接口可以是收发器，或，输入/输出接口。
当终端设备为设置于道路线确定装置中的芯片时，该通信接口可以是输入/输出接口。
可选地，该收发器可以为收发电路。可选地，该输入/输出接口可以为输入/输出电路。
第四方面，本申请实施例提供一种服务器，该服务器可以为上述方法设计中的道路线确定装置，或者，为设置在道路线确定装置中的芯片。该服务器包括：处理器，与存储器耦合，可用于执行存储器中的指令，以实现上述第一方面及其任意一种可能的实施方式中道路线确定装置所执行的方法。可选地，该服务器还包括存储器。可选地，该服务器还包括通信接口，处理器与通信接口耦合。
当服务器为道路线确定装置时，该通信接口可以是收发器，或，输入/输出接口。
当服务器为设置于道路线确定装置中的芯片时，该通信接口可以是输入/输出接口。
可选地，该收发器可以为收发电路。可选地，该输入/输出接口可以为输入/输出电路。
第五方面，提供了一种处理器，包括：输入电路，输出电路和处理电路。所述处理电路用于通过所述输入电路接收信号，并通过所述输出电路发射信号，使得所述处理器执行上述第一方面中任一种可能实现方式中的方法。
在具体实现过程中，上述处理器可以为芯片，输入电路可以为输入管脚，输出电路可以为输出管脚，处理电路可以为晶体管，门电路，触发器和各种逻辑电路等。输入电路所接收的输入的信号可以是由例如但不限于接收器接收并输入的，输出电路所输出的信号可以是例如但不限于输出给发射器并由发射器发射的，且输入电路和输出电路可以是同一电路，该电路在不同的时刻分别用作输入电路和输出电路。本申请实施例对处理器及各种电路的具体实现方式不做限定。
第六方面，提供了一种道路线确定装置，包括处理器和存储器。该处理器用于读取存储器中存储的指令，并可通过接收器接收信号，通过发射器发射信号，以使得所述装置执行第一方面中任一种可能实现方式中的方法。
可选地，所述处理器为一个或多个，所述存储器为一个或多个。
可选地，所述存储器可以与所述处理器集成在一起，或者所述存储器与处理器分离设置。
在具体实现过程中，存储器可以为非瞬时性(non-transitory)存储器，例如只读存储器(read only memory，ROM)，其可以与处理器集成在同一块芯片上，也可以分别设置在不同的芯片上，本申请实施例对存储器的类型以及存储器与处理器的设置方式不做限定。
第六方面中的道路线确定装置可以是芯片，该处理器可以通过硬件来实现也可以通过 软件来实现，当通过硬件实现时，该处理器可以是逻辑电路，集成电路等；当通过软件来实现时，该处理器可以是一个通用处理器，通过读取存储器中存储的软件代码来实现，该存储器可以集成在处理器中，可以位于该处理器之外，独立存在。
第七方面，提供了一种计算机程序产品，所述计算机程序产品包括：计算机程序(也可以称为代码，或指令)，当所述计算机程序被运行时，使得计算机执行上述第一方面中任一种可能实现方式中的方法。
第八方面，提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序(也可以称为代码，或指令)当其在计算机上运行时，使得计算机执行上述第一方面中任一种可能实现方式中的方法。
第九方面，本申请提供了一种芯片系统，该芯片系统包括处理器和接口，所述接口用于获取程序或指令，所述处理器用于调用所述程序或指令以实现或者支持终端设备/服务器实现第一方面所涉及的功能，例如，确定或处理上述方法中所涉及的数据和信息中的至少一种。
在一种可能的设计中，所述芯片系统还包括存储器，所述存储器，用于保存终端设备/服务器必要的程序指令和数据。该芯片系统，可以由芯片构成，也可以包括芯片和其他分立器件。
第十方面，本申请提供了一种车辆，该车辆上部署有上述实施例中的道路线确定装置，或者，为设置在道路线确定装置中的芯片。该车辆包括：处理器，与存储器耦合，可用于执行存储器中的指令，以实现上述第一方面及其任意一种可能的实施方式中道路线确定装置所执行的方法。
需要说明的是，本申请第二方面至第十方面的实施方式所带来的有益效果，以及对各方面的实施方式的说明可以参照第一方面的实施方式进行理解，因此没有重复赘述。
附图说明
图1是本申请实施例提供的电子地图数据采集场景示意图；
图2为本申请实施例中道路线确定的方法的一个场景示意图；
图3为本申请实施例中道路线确定的方法的另一场景示意图；
图4为本申请实施例中道路线确定的方法的一个实施例示意图；
图5为本申请实施例中生成初始滑动框集合的一个实施例示意图；
图6为本申请实施例中生成初始滑动框集合的另一实施例示意图；
图7为本申请实施例中初始滑动框的高度的一个实施例示意图；
图8为本申请实施例中确定待处理滑动框的一个实施例示意图；
图9为本申请实施例中确定待处理滑动框的另一实施例示意图；
图10为本申请实施例中确定目标滑动框的一个实施例示意图；
图11为本申请实施例中确定目标道路点的一个实施例示意图；
图12为本申请实施例中生成目标道路线的一个实施例示意图；
图13为本申请实施例中道路线确定装置一个实施例示意图；
图14为本申请实施例中的计算机程序产品示意图。
具体实施方式
为了使本申请的上述目的，技术方案和优点更易于理解，下文提供了详细的描述。所述详细的描述通过使用方框图，流程图和/或示例提出了设备和/或过程的各种实施例。由于这些方框图，流程图和/或示例包含一个或多个功能和/或操作，所以本领域内人员将理解可以通过许多硬件，软件，固件或它们的任意组合单独和/或共同实施这些方框图，流程图或示例内的每个功能和/或操作。本申请的说明书和权利要求书及附图中的术语“第一”，“第二”，“第三”，“第四”等(如果存在)是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的实施例能够以除了在这里图示或描述的内容以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程，方法，系统，产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程，方法，产品或设备固有的其它步骤或单元。
在人工智能技术兴起的今天，无人驾驶领域潜在的价值已经越来越为人们认可，高精度地图作为无人驾驶技术中的一个非常重要的因素，占据非常重要的地位。因此通过本申请实施例所提供的道路线确定的方法，基于所确定的道路点生成道路线，本申请实施例中所描述的道路线可以为道路车道线或道路边沿线等。基于此，再通过道路线创建高精度地图，因此在无人驾驶车辆行驶时，通过高精度地图的道路线能够约束的无人驾驶车辆的行驶区域。
为了便于理解，先对本申请实施例涉及到的一些术语或概念进行解释。
一，激光点
通过传感器(如激光雷达)照射激光束至物体表面，物体表面所反射的激光即为激光点，且激光点会携带该物体表面的方位，距离，反射率以及高度等信息。其次，若将激光束按照某种轨迹线进行扫描，由于扫描极为精细，则能够得到大量的激光点，由此形成激光点云。
基于此，下面先对本发明实施例使用的场景进行描述。图1是本申请实施例提供的电子地图数据采集场景示意图。请参阅图1，电子地图的数据主要通过激光雷达120进行采集，将激光雷达120设置在移动载体的顶部上，移动载体例如可以为采集车辆100，无人机，机器人等，上述车辆100可以为轿车，卡车，摩托车，公共汽车，船，飞机，直升飞机，割草机，娱乐车，游乐场车辆，施工设备，电车，高尔夫球车，火车，和手推车等，本申请实施例不做特别的限定。
具体地，本申请实施例所提供的道路线确定的方法，为无人驾驶车辆实时生成的，或者通过云服务器生成的，或者由采集车进行采集后续计算装置进行生成。为了便于理解，以道路线为道路边沿线作为一个示例进行介绍，请参阅图2，图2为本申请实施例中道路线确定的方法的一个场景示意图，道路线确定装置可以为部署于无人驾驶车辆200的终端设备，如图2中(A)图所示，在无人驾驶车辆200行驶于道路时，终端设备实时获取到无人驾驶车辆200的行驶轨迹，该行驶轨迹为多个连续的轨迹点，如图2中(B)图所示，终端设备基于多个连续的轨迹点实时生成多个连续的道路点，最后如图2中(C)图所示，终端设备通过多个连续的道路点生成道路线，即生成道路边沿线。可以理解的是，在图2所 示出的场景中，终端设备可以是智能手机，平板电脑，笔记本电脑，掌上电脑，个人电脑，智能电视，智能手表等具有高算力的设备，但并不局限于此。
进一步地，再次以道路线为道路边沿线作为一个示例进行介绍，请参阅图3，图3为本申请实施例中道路线确定的方法的另一场景示意图，道路线确定装置部署于服务器，服务器可以存储无人驾驶车辆300的行驶轨迹，服务器也可以实时获取无人驾驶车辆300的车辆行驶轨迹。因此如图3中(A)图所示，服务器实时获取无人驾驶车辆300的车辆行驶轨迹，或者从存储器中获取无人驾驶车辆300的车辆行驶轨迹，并且如图3中(B)图所示，由于行驶轨迹为多个连续的轨迹点，因此服务器基于多个连续的轨迹点生成多个连续的道路点，如图3中(C)图所示，服务器通过多个连续的道路点生成道路线，即生成道路边沿线。基于此，从而通过服务器可以完成道路线的实时生成，或者在需要时进行生成。可以理解的是，在图3所示出的场景中，服务器可以是独立的物理服务器，也可以是多个物理服务器构成的服务器集群或者分布式系统，还可以是提供云服务，云数据库，云计算，云函数，云存储，网络服务，云通信，中间件服务，域名服务，安全服务，内容分发网络(Content Delivery Network，CDN)，以及大数据和人工智能平台等基础云计算服务的云服务器。无人驾驶车辆与服务器之间可以通过有线或无线通信方式进行直接或间接地连接，本申请在此不做限制。
通过前述介绍可以了解本申请实施例的应用场景，下面对本申请实施例所提供的道路线确定的方法进行详细介绍，请参阅图4，图4为本申请实施例中道路线确定的方法的一个实施例示意图，如图4所示，道路线确定的方法的具体步骤如下。
S401.获取激光点。
本实施例中，由于在无人驾驶车辆行驶时，道路两旁可能存在树木，栏杆以及其他干扰物，为了减少确定道路线的干扰，道路线确定装置首先需获取激光雷达所采集的多个激光点，由于每个激光点均能够携带激光雷达所扫描物体表面的方位，距离，高度以及反射率等信息，因此将激光雷达所采集的多个激光点中，激光点的高度小于或等于高度阈值的激光点确定为本方案所需的激光点。由此减少激光点的数据量，提升后续步骤的计算效率，并且还能够去除树木，栏杆以及其他干扰物的干扰，提升道路线确定的准确度。
具体地，激光点的高度为激光雷达扫描的道路线距离道路路面的高度。本实施例中第二高度阈值被设置为50厘米(centimetre，cm)，因此本方案所需的激光点距离道路路面的高度均小于或等于50cm，大于50cm的初始激光点不应用于后续步骤的计算。应理解，在实际应用中，第二高度阈值还可以为60cm，80cm或者90cm等，具体第二高度阈值需要通过道路的具体环境以及道路布局等多种方面灵活确定，因此本实施例对第二高度阈值的示例不应理解为本申请的限定。
S402.获取目标车辆轨迹点集合。
本实施例中，在无人驾驶车辆行驶时，能够获取到车辆的车辆行驶轨迹，而车辆行驶轨迹能够被分为多个连续的车辆轨迹点，道路线确定装置基于多个连续的车辆轨迹点能够获取初始车辆轨迹点集合，因此初始车辆轨迹点集合中每个初始车辆轨迹点为连续的，此时初始车辆轨迹点的数量较大，此时通过预设采样密度对初始车辆轨迹点集合进行降采样处理，从而获取包括多个目标车辆轨迹点的目标车辆轨迹点集合，由此减少车辆轨迹点的 数据量，提升后续步骤确定目标道路点效率。
具体地，本实施例中预设采样密度被设置1米(meter，m)，即车辆获取到初始车辆轨迹点集合后，从多个连续的初始车辆轨迹点中，每间隔1m获取一个目标车辆轨迹点。例如，初始车辆轨迹点集合中包括100个初始车辆轨迹点，并且每个初始车辆轨迹点之间间隔为10cm，若通过1m的预设采样密度对初始车辆轨迹点集合进行降采样处理，即连续的10个初始车辆轨迹点中，将最后一个初始车辆轨迹点确定为所需的目标车辆轨迹点，然后下一个连续的10个初始车辆轨迹点中，采用类似方式确定目标车辆轨迹点，因此可以在100个初始车辆轨迹点中确定10个目标车辆轨迹点，从而生成包括10个目标车辆轨迹点的目标车辆轨迹点集合。应理解，在实际应用中，预设采样密度还可以为50cm，80cm或者1.2m等，具体预设采样密度需要通过初始车辆轨迹点的具体数量灵活确定，因此本实施例对预设采样密度的示例不应理解为本申请的限定。
S403.以目标车辆轨迹点为基准，由内向外生成初始滑动框集合。
本实施例中，道路线确定装置通过步骤S401以及步骤S402获取到包括多个激光点的激光点集合，以及包括多个目标车辆轨迹点的目标车辆轨迹点集合后，需要以目标车辆轨迹点集合中的一个目标车辆轨迹点为基准，由内向外生成初始滑动框集合，该初始滑动框集合中每个初始滑动框是连续的，并且每个初始滑动框包括激光点云，而激光点云包括至少一个激光点，因此能够通过所包括的激光点云的激光点的高度确定初始滑动框的高度。其中，每个初始滑动框的长度一致，例如第一个初始滑动框的长度为40cm，那么初始滑动框集合中所有初始滑动框的长度均为40cm，应理解，每个初始滑动框的长度是是基于目标车辆轨迹点与道路线的距离的实际情况灵活确定。
其次，道路线确定装置在确定待处理滑动框后，将停止生成初始滑动框。或者，多个连续的初始滑动框的总长度超出目标车辆轨迹点与道路线的距离，则停止生成初始滑动框，在这种情况下，可能存在该段道路的道路线破损或者被遮挡的情况，因此无法基于该目标车辆轨迹点确定待处理滑动框，即不进行后续步骤。
具体地，道路线确定装置可以从目标车辆轨迹点的右侧由内向外生成多个连续的初始滑动框，或者从目标车辆轨迹点的左侧由内向外生成多个连续的初始滑动框，具体为目标车辆轨迹点的左侧还是右侧不为本申请的限定。
为了便于理解，请参阅图5，图5为本申请实施例中生成初始滑动框集合的一个实施例示意图，如图5所示，目标车辆轨迹点集合500中包括目标车辆轨迹点501，以目标车辆轨迹点501为基准，从目标车辆轨迹点501的右侧由内向外生成初始滑动框集合A3。其次，请参阅图6，图6为本申请实施例中生成初始滑动框集合的另一实施例示意图，如图6所示，目标车辆轨迹点集合600中包括目标车辆轨迹点601，以目标车辆轨迹点601为基准，从目标车辆轨迹点601的右侧由内向外生成初始滑动框集合602，并且在初始滑动框集合602的总长度603与目标车辆轨迹点601与道路线的距离604相等时，停止继续生成初始滑动框集合。应理解，图5以及图6的示例仅用于理解本方案，具体初始滑动框集合需要根据目标车辆轨迹点集合以及道路宽度等实际情况灵活确定。
进一步地，通过前述介绍可知，每个激光点均能够携带激光雷达所扫描物体表面的方位，距离，高度以及反射率等信息，而每个初始滑动框均包括至少一个激光点，基于此， 每个初始滑动框通过所包括的至少一个激光点确定初始滑动框的高度。示例性地，图7为本申请实施例中初始滑动框的高度的一个实施例示意图，如图7所示，初始滑动框700包括激光点701，激光点702以及激光点703，激光点A的高度为40cm，激光点B的高度为35cm，激光点C的高度为45cm。若初始滑动框700的高度为所包括的激光点云的激光点的高度的平均值，即需要计算激光点701的高度，激光点702的高度以及激光点703的高度的平均值，通过计算可知初始滑动框700的高度为40cm。或者，若初始滑动框700的高度为所包括的激光点云的激光点的高度的最大值，即激光点C的高度为45cm为初始滑动框700的高度，可以确定初始滑动框700的高度为45cm。可以理解的是，前述示例仅用于理解本方案，初始滑动框的高度的具体确定方式需要根据实际情况灵活确定，在此不进行限定。
S404.确定待处理滑动框。
本实施例中，道路线确定装置需要对多个连续的初始滑动框对应的激光点高度进行对比，当多个连续的初始滑动框中存在第一初始滑动框对应的激光点高度与第二初始滑动框对应的激光点高度的差值大于第一高度阈值，此时第一初始滑动框与第二初始滑动框为相邻的初始滑动框，并且第二初始滑动框与目标车辆轨迹点距离更近，确定第一初始滑动框为待处理滑动框。通过前述实施例可知，在没有确定待处理滑动框之前，道路线确定装置会一直由内向外生成连续的初始滑动框，在确定待处理滑动框后，则停止生成初始滑动框集合的步骤。
示例性地，以第一高度阈值为5cm作为一个示例进行说明，请参阅图8，图8为本申请实施例中确定待处理滑动框的一个实施例示意图，如图8所示，初始滑动框集合800中包括初始滑动框801，初始滑动框802，初始滑动框803，初始滑动框804以及805，且初始滑动框801至初始滑动框802与目标车辆轨迹点806的距离越来越大。当初始滑动框801的高度为40cm，初始滑动框802的高度为37cm时，此时初始滑动框801与初始滑动框802之间差值为3cm，小于5cm，此时不确定待处理滑动框。其次，在初始滑动框803的高度为39cm时，此时初始滑动框802与初始滑动框803之间差值为2cm，小于5cm，此时不确定待处理滑动框。在初始滑动框804的高度为41cm时，此时初始滑动框803与初始滑动框804之间差值为2cm，小于5cm，也不确定待处理滑动框。再次，在初始滑动框805的高度为46cm时，此时初始滑动框804与初始滑动框805之间差值为5cm，由于初始滑动框804与目标车辆轨迹点806的距离更近，而初始滑动框805与目标车辆轨迹点806的距离更远，因此初始滑动框804为第二初始滑动框，初始滑动框805为第一初始滑动框，即确定初始滑动框805为待处理滑动框。应理解，图8的示例仅用于理解本方案，待处理滑动框的具体确定方式需要根据道路实际情况灵活确定。
具体地，图9为本申请实施例中确定待处理滑动框的另一实施例示意图，如图9中(A)图所示，在道路线确定装置从目标车辆轨迹点900的左侧由内向外生成多个连续的初始滑动框时，基于公式(1)确定待处理滑动框：
Figure PCTCN2021132672-appb-000001
其中，i为待处理滑动框，L id为第i个初始滑动框的高度，L (i-1)d为第i-1个初始滑 动框的高度，θ为第一高度阈值，L为目标车辆轨迹点与道路线的距离，w为初始滑动框的长度。
其次，如图9中(B)图所示，在道路线确定装置从目标车辆轨迹点900的右侧由内向外生成多个连续的初始滑动框时，基于公式(2)确定待处理滑动框：
Figure PCTCN2021132672-appb-000002
其中，i为待处理滑动框，R id为第i个初始滑动框的激光点高度，R (i-1)d为第i-1个初始滑动框的激光点高度，θ为第一高度阈值，L为目标车辆轨迹点与道路线的距离，w为初始滑动框的长度。
S405.从待处理滑动框中确定目标滑动框。
本实施例中，道路线确定装置将待处理滑动框平均划分为多个候选滑动框，即每个候选滑动框的长度以及大小均相同，然后确定多个候选滑动框对应的密度，将密度最大的候选滑动框确定为目标滑动框。由于密度指示候选滑动框中所包括的激光点的数量，因此密度最大的候选滑动框即为所包括的激光点的数量最多的候选滑动框。
示例性地，请参阅图10，图10为本申请实施例中确定目标滑动框的一个实施例示意图，如图10所示，将待处理滑动框1000平均划分为多个候选滑动框，分别为候选滑动框1001，候选滑动框1002，候选滑动框1003，候选滑动框1004，以及候选滑动框1005，且每个待处理滑动框中存包括激光点(图10中黑点)。其中，候选滑动框1001所包括的激光点的数量为2，候选滑动框1002所包括的激光点的数量为4，候选滑动框1003所包括的激光点的数量为7，候选滑动框1004所包括的激光点的数量为3，候选滑动框1005所包括的激光点的数量为1，即候选滑动框1003中所包括激光点的数量最多，因此可以确定候选滑动框1003为目标滑动框。应理解，图10的示例仅用于理解本方案，目标滑动框的具体确定方式需要根据候选滑动框的实际情况灵活确定。
S406.从目标滑动框中确定目标道路点。
本实施例中，道路线确定装置需要先获取目标车辆轨迹点的位置信息，然后根据目标车辆轨迹点的位置信息，确定待处理滑动框的中心点的位置信息。其中目标车辆轨迹点的位置信息为目标车辆轨迹点在坐标系中的坐标信息，包括横坐标以及纵坐标，具体位置信息在此不做限定。
具体地，图11为本申请实施例中确定目标道路点的一个实施例示意图，如图11中(A)图所示，在道路线确定装置从目标车辆轨迹点1100的左侧由内向外生成多个连续的初始滑动框时，通过前述实施例所介绍的方式确定待处理滑动框，并基于公式(3)确定待处理滑动框的中心点1101，然后获取待处理滑动框的中心点1101在坐标系中的坐标信息，该坐标信息即为待处理滑动框的中心点的位置信息：
Figure PCTCN2021132672-appb-000003
其中，L io为待处理滑动框的中心点1101的位置信息，P x为目标车辆轨迹点1100的 位置信息中的横坐标信息，P y为目标车辆轨迹点1100的位置信息中的纵坐标信息，i为待处理滑动框，L为目标车辆轨迹点1100与道路线的距离。
其次，如图11中(B)图所示，在道路线确定装置从目标车辆轨迹点1100的右侧由内向外生成多个连续的初始滑动框时，通过前述实施例所介绍的方式确定待处理滑动框，并基于公式(4)确定待处理滑动框的中心点1101，然后获取待处理滑动框的中心点1101在坐标系中的坐标信息，该坐标信息即为待处理滑动框的中心点的位置信息：
Figure PCTCN2021132672-appb-000004
其中，R io为待处理滑动框的中心点1101的位置信息，P x为目标车辆轨迹点1100的位置信息中的横坐标信息，P y为目标车辆轨迹点1100的位置信息中的纵坐标信息，i为待处理滑动框，L为目标车辆轨迹点1100与道路线的距离。
进一步地，如图11中(C)图所示，根据待处理滑动框的中心点1101的位置信息，从目标滑动框中确定待处理道路点，具体基于公式(5)以及公式(6)确定待处理道路点：
Figure PCTCN2021132672-appb-000005
Figure PCTCN2021132672-appb-000006
其中，P j为待处理道路点，P ix为待处理滑动框的中心点1101的位置信息中的横坐标信息，P iy为待处理滑动框的中心点1101的位置信息中的纵坐标信息，j为目标滑动框，L为目标车辆轨迹点1100与道路线的距离，n为将待处理滑动框平均划分为多个候选滑动框的数量。
最后，对提取出来的待处理道路点进行去噪处理，并且应用多段样条曲线重新离散参数方程，以得到目标道路点。其中，去噪处理可以采用RANSAC，Mean Shift聚类算法以及ICP等，具体此处不做限定。
S407.生成目标道路线。
本实施例中，道路线确定装置对目标车辆轨迹点集合中的所有目标车辆轨迹点执行步骤S403至S406，从而得到基于每个目标车辆轨迹点所得到的目标道路点，然后根据距离阈值，对候选点就行欧拉聚类。例如，短距离会聚成一类，例如车辆遮挡，噪声等聚成一类，而长距离会聚合成另一类，例如路口等聚成一类，从而聚合成两种类型。再拟合多段曲线后重新采样，最终生成目标道路线，本申请实施例中所描述的道路线可以为道路车道线或道路边沿线等。具体地，目标道路线用于创建高精度地图地图。因此在无人驾驶车辆行驶时，通过高精度地图的道路线能够约束的无人驾驶车辆的行驶区域。
为了便于理解，请参阅图12，图12为本申请实施例中生成目标道路线的一个实施例示意图，如图12所示，若为车辆遮挡，噪声的短距离类型，那么会出现未生成目标车辆轨迹点所对应的目标道路点的情况，此时通过聚合并且拟合多段曲线得到后重新采样，得到 连续无中断的目标道路线1200。应理解，图12的示例仅用于理解本方案，生成目标道路线的具体方式需要根据实际情况灵活确定。
上述主要以方法的角度对本申请实施例提供的方案进行了介绍。可以理解的是，道路线确定装置为了实现上述功能，其包含了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本文中所公开的实施例描述的各示例的模块及算法步骤，本申请能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
本申请实施例可以基于上述方法示例对道路线确定装置进行功能模块的划分，例如，可以对应各个功能划分各个功能模块，也可以将两个或两个以上的功能集成在一个处理模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。需要说明的是，本申请实施例中对模块的划分是示意性的，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。
由此，下面对本申请中的道路线确定装置进行详细描述，请参阅图13，图13为本申请实施例中道路线确定装置一个实施例示意图，如图所示，道路线确定装置1300包括：
生成模块1301，用于以目标车辆轨迹点为基准，由内向外生成初始滑动框集合，其中，初始滑动框集合中每个初始滑动框是连续的，每个初始滑动框的高度是根据初始滑动框所包括的激光点云的激光点的高度确定的；
确定模块1302，用于若第一初始滑动框的高度与第二初始滑动框的高度的差值大于第一高度阈值，则确定第一初始滑动框为待处理滑动框，其中，第一初始滑动框与第二初始滑动框为相邻的初始滑动框，且第二初始滑动框与目标车辆轨迹点的距离小于第一初始滑动框与目标车辆轨迹点的距离；
确定模块1302，还用于根据待处理滑动框确定目标滑动框，其中，目标滑动框为密度最大的候选滑动框，候选滑动框是对待处理滑动框进行平均划分后得到的，密度指示候选滑动框中所包括的的数量；
确定模块1302，还用于从目标滑动框中确定目标道路点，其中，目标道路点用于生成目标道路线。
在本申请的一些可选实施例中，道路线确定装置1300还包括获取模块1303；
获取模块1303，用于获取目标车辆轨迹点的位置信息；
确定模块1302，还用于根据目标车辆轨迹点的位置信息，确定待处理滑动框的中心点的位置信息；
确定模块1302，具体用于根据待处理滑动框的中心点的位置信息，从目标滑动框中确定待处理道路点；
采用样条曲线对待处理道路点进行去噪处理，以得到目标道路点。
在本申请的一些可选实施例中，确定模块1302，具体用于将待处理滑动框平均划分为多个候选滑动框；
确定多个候选滑动框对应的密度；
将密度最大的候选滑动框确定为目标滑动框。
在本申请的一些可选实施例中，获取模块1303，还用于在生成模块1301以目标车辆轨迹点为基准，由内向外生成初始滑动框集合之前，获取初始车辆轨迹点集合；
获取模块，还用于通过预设采样密度对初始车辆轨迹点集合进行降采样处理，以获取目标车辆轨迹点集合，其中，目标车辆轨迹点集合包括多个目标车辆轨迹点。
在本申请的一些可选实施例中，生成模块1301，还用于在确定模块根据目标滑动框确定目标道路点之后，对多个目标车辆轨迹点所得到的目标道路点进行拟合，生成目标道路线。
在本申请的一些可选实施例中，激光点的高度小于或等于第二高度阈值。
在本申请的一些可选实施例中，目标道路线为道路边沿线，或，道路车道线。
在本申请的一些可选实施例中，目标道路线用于高精度地图地图。
参照图14，本申请还提供了一种计算机程序产品，在一些实施例中，上述图4所公开的方法可以实施为以机器可读格式被编码在计算机可读存储介质上的或者被编码在其它非瞬时性介质或者制品上的计算机程序指令。
图14示意性地示出根据这里展示的至少一些实施例而布置的示例计算机程序产品的概念性局部视图，示例计算机程序产品包括用于在计算设备上执行计算机进程的计算机程序。
在一个实施例中，计算机程序产品1400是使用信号承载介质1401来提供的。信号承载介质1401可以包括一个或多个程序指令1402，其当被一个或多个处理器运行时可以提供以上针对图4描述的功能或者部分功能。因此，例如，参考图4中所示的实施例，步骤S401至步骤S407可以由与信号承载介质1401相关联的一个或多个指令来承担。此外，图14中的程序指令1402也描述示例指令。
在一些示例中，信号承载介质1401可以包含计算机可读介质1403,诸如但不限于，硬盘驱动器，紧密盘(CD)，数字视频光盘(DVD)，数字磁带，存储器，ROM或RAM等等。
在一些实施方式中，信号承载介质1401可以包含计算机可记录介质1404，诸如但不限于，存储器，读/写(R/W)CD，R/W DVD，等等。在一些实施方式中，信号承载介质1401可以包含通信介质1405,诸如但不限于，数字和/或模拟通信介质(例如，光纤电缆，波导，有线通信链路，无线通信链路，等等)。因此，例如，信号承载介质1401可以由无线形式的通信介质1405(例如，遵守IEEE 802.11标准或者其它传输协议的无线通信介质)来传达。
一个或多个程序指令1402可以是，例如，计算机可执行指令或者逻辑实施指令。在一些示例中，计算设备的计算设备可以被配置为，响应于通过计算机可读介质1403，计算机可记录介质1404，和/或通信介质1405中的一个或多个传达到计算设备的程序指令1402，提供各种操作，功能，或者动作。
在实现过程中，上述方法的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。结合本申请实施例所公开的方法的步骤可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存，只读存储器，可编程只读存储器或者电可擦写可编程存储器，寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成上 述方法的步骤。为避免重复，这里不再详细描述。
应注意，本申请实施例中的处理器可以是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法实施例的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器可以是通用处理器，数字信号处理器(DSP)，专用集成电路(ASIC)，现场可编程门阵列(FPGA)或者其他可编程逻辑器件，分立门或者晶体管逻辑器件，分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法，步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存，只读存储器，可编程只读存储器或者电可擦写可编程存储器，寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成上述方法的步骤。
可以理解，本申请实施例中的存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(read-only memory，ROM)，可编程只读存储器(programmable ROM，PROM)，可擦除可编程只读存储器(erasable PROM，EPROM)，电可擦除可编程只读存储器(electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(static RAM，SRAM)，动态随机存取存储器(dynamic RAM，DRAM)，同步动态随机存取存储器(synchronous DRAM，SDRAM)，双倍数据速率同步动态随机存取存储器(double data rate SDRAM，DDR SDRAM)，增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)，同步连接动态随机存取存储器(synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM，DR RAM)。应注意，本文描述的系统和方法的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
根据本申请实施例提供的方法，本申请还提供一种计算机程序产品，该计算机程序产品包括：计算机程序代码，当该计算机程序代码在计算机上运行时，使得该计算机执行图3至图8所示实施例中的道路线确定装置执行的方法。
根据本申请实施例提供的方法，本申请还提供一种计算机可读存储介质，该计算机可读存储介质存储有程序代码，当该程序代码在计算机上运行时，使得该计算机执行图3至图8所示实施例中的道路线确定装置执行的方法。
在本说明书中使用的术语“部件”，“模块”，“系统”等用于表示计算机相关的实体，硬件，固件，硬件和软件的组合，软件，或执行中的软件。例如，部件可以是但不限于，在处理器上运行的进程，处理器，对象，可执行文件，执行线程，程序和/或计算机。通过图示，在计算设备上运行的应用和计算设备都可以是部件。一个或多个部件可驻留在进程和/或执行线程中，部件可位于一个计算机上和/或分布在2个或更多个计算机之间。此外，这些部件可从在上面存储有各种数据结构的各种计算机可读介质执行。部件可例如根据具有一个或多个数据分组(例如来自与本地系统，分布式系统和/或网络间的另一部件交互的二个部件的数据，例如通过信号与其它系统交互的互联网)的信号通过本地和/或远程进程来通信。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件，或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
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，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请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。例如，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，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，在本申请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，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请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)执行本申请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。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (20)

  1. 一种道路线确定的方法，其特征在于，包括：
    以目标车辆轨迹点为基准，由内向外生成初始滑动框集合，其中，所述初始滑动框集合中每个初始滑动框是连续的，每个所述初始滑动框的高度是根据所述初始滑动框所包括的激光点云的激光点的高度确定的；
    若第一初始滑动框的高度与第二初始滑动框的高度的差值大于第一高度阈值，则确定所述第一初始滑动框为待处理滑动框，其中，所述第一初始滑动框与所述第二初始滑动框为相邻的初始滑动框，且所述第二初始滑动框与所述目标车辆轨迹点的距离小于所述第一初始滑动框与所述目标车辆轨迹点的距离；
    根据所述待处理滑动框确定目标滑动框，其中，所述目标滑动框为密度最大的候选滑动框，所述候选滑动框是对所述待处理滑动框进行平均划分后得到的，所述密度指示所述候选滑动框中所包括的所述激光点的数量；
    从所述目标滑动框中确定目标道路点，其中，所述目标道路点用于生成目标道路线。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    获取所述目标车辆轨迹点的位置信息；
    根据所述目标车辆轨迹点的位置信息，确定所述待处理滑动框的中心点的位置信息；
    所述从所述目标滑动框中确定目标道路点，包括：
    根据所述待处理滑动框的中心点的位置信息，从所述目标滑动框中确定待处理道路点；
    采用样条曲线对所述待处理道路点进行去噪处理，以得到所述目标道路点。
  3. 根据权利要求1或2所述的方法，其特征在于，所述根据所述待处理滑动框确定目标滑动框，包括：
    将所述待处理滑动框平均划分为多个所述候选滑动框；
    确定多个所述候选滑动框对应的密度；
    将密度最大的所述候选滑动框确定为所述目标滑动框。
  4. 根据权利要求1至3中任一项所述的方法，其特征在于，在所述以目标车辆轨迹点为基准，由内向外生成初始滑动框集合之前，所述方法还包括：
    获取初始车辆轨迹点集合；
    通过预设采样密度对所述初始车辆轨迹点集合进行降采样处理，以获取目标车辆轨迹点集合，其中，所述目标车辆轨迹点集合包括多个所述目标车辆轨迹点。
  5. 根据权利要求1至4中任一项所述的方法，其特征在于，在所述根据所述目标滑动框确定目标道路点之后，所述方法还包括：
    对多个所述目标车辆轨迹点所得到的所述目标道路点进行拟合，生成所述目标道路线。
  6. 根据权利要求1所述的方法，其特征在于，所述激光点的高度小于或等于第二高度阈值。
  7. 根据权利要求1所述的方法，其特征在于，所述目标道路线为道路边沿线，或，道路车道线。
  8. 根据权利要求1所述的方法，其特征在于，所述目标道路线用于创建高精度地图地图。
  9. 一种道路线确定装置，其特征在于，包括：
    生成模块，用于以目标车辆轨迹点为基准，由内向外生成初始滑动框集合，其中，所述初始滑动框集合中每个初始滑动框是连续的，每个所述初始滑动框的高度是根据所述初始滑动框所包括的激光点云的激光点的高度确定的；
    确定模块，用于若第一初始滑动框的高度与第二初始滑动框的高度的差值大于第一高度阈值，则确定所述第一初始滑动框为待处理滑动框，其中，所述第一初始滑动框与所述第二初始滑动框为相邻的初始滑动框，且所述第二初始滑动框与所述目标车辆轨迹点的距离小于所述第一初始滑动框与所述目标车辆轨迹点的距离；
    所述确定模块，还用于根据所述待处理滑动框确定目标滑动框，其中，所述目标滑动框为密度最大的候选滑动框，所述候选滑动框是对所述待处理滑动框进行平均划分后得到的，所述密度指示所述候选滑动框中所包括的所述激光点的数量；
    所述确定模块，还用于从所述目标滑动框中确定目标道路点，其中，所述目标道路点用于生成目标道路线。
  10. 根据权利要求9所述道路线确定装置，其特征在于，所述道路线确定装置还包括获取模块；
    所述获取模块，用于获取所述目标车辆轨迹点的位置信息；
    所述确定模块，还用于根据所述目标车辆轨迹点的位置信息，确定所述待处理滑动框的中心点的位置信息；
    所述确定模块，具体用于根据所述待处理滑动框的中心点的位置信息，从所述目标滑动框中确定待处理道路点；
    采用样条曲线对所述待处理道路点进行去噪处理，以得到所述目标道路点。
  11. 根据权利要求9或10所述道路线确定装置，其特征在于，所述确定模块，具体用于将所述待处理滑动框平均划分为多个所述候选滑动框；
    确定多个所述候选滑动框对应的密度；
    将密度最大的所述候选滑动框确定为所述目标滑动框。
  12. 根据权利要求9至11中任一项所述道路线确定装置，其特征在于，所述获取模块，还用于在所述生成模块以目标车辆轨迹点为基准，由内向外生成初始滑动框集合之前，获取初始车辆轨迹点集合；
    所述获取模块，还用于通过预设采样密度对所述初始车辆轨迹点集合进行降采样处理，以获取目标车辆轨迹点集合，其中，所述目标车辆轨迹点集合包括多个所述目标车辆轨迹点。
  13. 根据权利要求9至12中任一项所述道路线确定装置，其特征在于，所述生成模块，还用于在所述确定模块根据所述目标滑动框确定目标道路点之后，对多个所述目标车辆轨迹点所得到的所述目标道路点进行拟合，生成所述目标道路线。
  14. 根据权利要求9所述道路线确定装置，其特征在于，所述激光点的高度小于或等于第二高度阈值。
  15. 根据权利要求9所述道路线确定装置，其特征在于，所述目标道路线为道路边沿线，或，道路车道线。
  16. 根据权利要求9所述道路线确定装置，其特征在于，所述目标道路线用于高精度地图地图。
  17. 一种终端设备，其特征在于，包括：
    处理器，存储器，输入输出(I/O)接口；
    所述处理器与所述存储器，所述输入输出接口耦合；
    所述处理器通过运行所述存储器中的代码执行如权利要求1至8中任一项所述的方法。
  18. 一种服务器，其特征在于，包括：
    处理器，存储器，输入输出(I/O)接口；
    所述处理器与所述存储器，所述输入输出接口耦合；
    所述处理器通过运行所述存储器中的代码执行如权利要求1至8中任一项所述的方法。
  19. 一种计算机可读存储介质，包括指令，当其在计算机上运行时，使得计算机执行如权利要求1至8中任一项所述的方法。
  20. 一种计算机程序产品，其特征在于，所述计算机程序产品在计算机上执行时，使得所述计算机执行如权利要求1至8中任一项所述的方法。
PCT/CN2021/132672 2021-02-03 2021-11-24 一种道路线确定的方法，相关装置以及设备 WO2022166323A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110150102.1 2021-02-03
CN202110150102.1A CN114862895A (zh) 2021-02-03 2021-02-03 一种道路线确定的方法，相关装置以及设备

Publications (1)

Publication Number Publication Date
WO2022166323A1 true WO2022166323A1 (zh) 2022-08-11

Family

ID=82622785

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/132672 WO2022166323A1 (zh) 2021-02-03 2021-11-24 一种道路线确定的方法，相关装置以及设备

Country Status (2)

Country Link
CN (1) CN114862895A (zh)
WO (1) WO2022166323A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115907596A (zh) * 2022-12-30 2023-04-04 重庆赛迪奇智人工智能科技有限公司 一种运输车辆定位展示方法、装置、存储介质及设备
CN116331190A (zh) * 2023-03-30 2023-06-27 阿波罗智联(北京)科技有限公司 记忆泊车的记忆路线的修正方法、装置、设备及车辆
CN116449335A (zh) * 2023-06-14 2023-07-18 上海木蚁机器人科技有限公司 可行驶区域检测方法、装置、电子设备以及存储介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105551082A (zh) * 2015-12-02 2016-05-04 百度在线网络技术（北京）有限公司 一种基于激光点云的路面识别方法及装置
US9530225B1 (en) * 2013-03-11 2016-12-27 Exelis, Inc. Point cloud data processing for scalable compression
CN106840175A (zh) * 2016-12-06 2017-06-13 北京中交兴路信息科技有限公司 一种车辆行驶轨迹匹配路网的方法及装置
CN107274422A (zh) * 2017-05-08 2017-10-20 燕山大学 一种基于法线信息和k邻域搜索结合的点云边缘提取方法
CN107818550A (zh) * 2017-10-27 2018-03-20 广东电网有限责任公司机巡作业中心 一种基于LiDAR的点云顶部噪点剔除方法
CN108021844A (zh) * 2016-10-31 2018-05-11 高德软件有限公司 一种道路边沿识别方法及装置
CN108171720A (zh) * 2018-01-08 2018-06-15 武汉理工大学 一种基于几何统计信息的倾斜摄影模型对象边界探测方法
CN111915662A (zh) * 2019-05-07 2020-11-10 北京京东尚科信息技术有限公司 一种三维激光点云数据预处理方法和装置

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9530225B1 (en) * 2013-03-11 2016-12-27 Exelis, Inc. Point cloud data processing for scalable compression
CN105551082A (zh) * 2015-12-02 2016-05-04 百度在线网络技术（北京）有限公司 一种基于激光点云的路面识别方法及装置
CN108021844A (zh) * 2016-10-31 2018-05-11 高德软件有限公司 一种道路边沿识别方法及装置
CN106840175A (zh) * 2016-12-06 2017-06-13 北京中交兴路信息科技有限公司 一种车辆行驶轨迹匹配路网的方法及装置
CN107274422A (zh) * 2017-05-08 2017-10-20 燕山大学 一种基于法线信息和k邻域搜索结合的点云边缘提取方法
CN107818550A (zh) * 2017-10-27 2018-03-20 广东电网有限责任公司机巡作业中心 一种基于LiDAR的点云顶部噪点剔除方法
CN108171720A (zh) * 2018-01-08 2018-06-15 武汉理工大学 一种基于几何统计信息的倾斜摄影模型对象边界探测方法
CN111915662A (zh) * 2019-05-07 2020-11-10 北京京东尚科信息技术有限公司 一种三维激光点云数据预处理方法和装置

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115907596A (zh) * 2022-12-30 2023-04-04 重庆赛迪奇智人工智能科技有限公司 一种运输车辆定位展示方法、装置、存储介质及设备
CN115907596B (zh) * 2022-12-30 2024-02-27 重庆赛迪奇智人工智能科技有限公司 一种运输车辆定位展示方法、装置、存储介质及设备
CN116331190A (zh) * 2023-03-30 2023-06-27 阿波罗智联(北京)科技有限公司 记忆泊车的记忆路线的修正方法、装置、设备及车辆
CN116449335A (zh) * 2023-06-14 2023-07-18 上海木蚁机器人科技有限公司 可行驶区域检测方法、装置、电子设备以及存储介质
CN116449335B (zh) * 2023-06-14 2023-09-01 上海木蚁机器人科技有限公司 可行驶区域检测方法、装置、电子设备以及存储介质

Also Published As

Publication number Publication date
CN114862895A (zh) 2022-08-05

Similar Documents

Publication Publication Date Title
WO2022166323A1 (zh) 一种道路线确定的方法，相关装置以及设备
JP7112993B2 (ja) レーザレーダの内部パラメータ精度検証方法とその装置、機器及び媒体
WO2021097618A1 (zh) 点云分割方法、系统及计算机存储介质
KR20160123668A (ko) 무인자동주차 기능 지원을 위한 장애물 및 주차구획 인식 장치 및 그 방법
CN112513679B (zh) 一种目标识别的方法和装置
US11035933B2 (en) Transition map between lidar and high-definition map
US10810749B2 (en) Image processing apparatus, moving body device control system, computer-readable medium, and image processing method
WO2021056516A1 (zh) 目标检测方法、设备及可移动平台
WO2020237516A1 (zh) 点云的处理方法、设备和计算机可读存储介质
CN113985405A (zh) 障碍物检测方法、应用于车辆的障碍物检测设备
CN114170596A (zh) 姿态识别方法、装置、电子设备、工程机械和存储介质
CN112630798B (zh) 用于估计地面的方法和装置
JP2022537557A (ja) 運転可能な領域情報を決定するための方法及び装置
CN116161040A (zh) 车位信息生成方法、装置、电子设备和计算机可读介质
CN114783172B (zh) 一种停车场空车位识别方法及系统、计算机可读存储介质
CN116502479B (zh) 一种三维物体在仿真环境中的碰撞检测方法和装置
US20240134021A1 (en) Time-of-flight motion misalignment artifact correction
WO2021054339A1 (ja) 物体検出装置、物体検出システム、移動体及び物体検出方法
US20240134020A1 (en) Time-of-flight motion misalignment artifact correction
WO2021054341A1 (ja) 物体検出装置、物体検出システム、移動体及び物体検出方法
CN112558072B (zh) 车辆定位方法、装置、系统、电子设备及存储介质
WO2021054340A1 (ja) 物体検出装置、物体検出システム、移動体及び物体検出方法
Ban et al. A Real-Time Detection Algorithm for Semi-structured Boundaries in the Park Based on 3D LiDAR
CN115685236A (zh) 机器人、机器人打滑处理方法、装置和可读存储介质
Bai et al. Drivable Area Detection and Vehicle Localization Based on Multi-Sensor Information

Legal Events

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

Ref document number: 21924318

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: 21924318

Country of ref document: EP

Kind code of ref document: A1