WO2023246342A1 - 一种Freespace边缘点的处理方法以及装置 - Google Patents

一种Freespace边缘点的处理方法以及装置 Download PDF

Info

Publication number
WO2023246342A1
WO2023246342A1 PCT/CN2023/092611 CN2023092611W WO2023246342A1 WO 2023246342 A1 WO2023246342 A1 WO 2023246342A1 CN 2023092611 W CN2023092611 W CN 2023092611W WO 2023246342 A1 WO2023246342 A1 WO 2023246342A1
Authority
WO
WIPO (PCT)
Prior art keywords
freespace
edge points
status information
edge point
effective
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2023/092611
Other languages
English (en)
French (fr)
Inventor
李伟男
刘斌
吴杭哲
高长胜
陈博
刘枫
孟祥哲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
FAW Group Corp
Original Assignee
FAW Group Corp
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 FAW Group Corp filed Critical FAW Group Corp
Publication of WO2023246342A1 publication Critical patent/WO2023246342A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/903Querying
    • G06F16/9035Filtering based on additional data, e.g. user or group profiles
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/906Clustering; Classification
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/16Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization

Definitions

  • the present application relates to the field of intelligent driving control, and specifically to a Freespace edge point processing method, device, storage medium and electronic equipment for an intelligent driving system.
  • This application requests the priority of the patent application submitted to the State Intellectual Property Office of China on June 20, 2022, with the application number 202210700010.0 and the invention title "A Freespace edge point processing method and device”.
  • Freespace In the current mainstream smart driving technology, Freespace technology has become an indispensable part. Freespace here refers to the drivable area of the car, which includes areas that avoid other cars, pedestrians, roadsides, etc. Among them, Freespace edge points refer to scattered points on the boundary of the drivable area. Generally, the resolution of Freespace edge points is 1deg. Accurate Freespace edge point information can provide effective sensory input for the autonomous driving system, thereby providing data assurance for the decision-making and planning layer. However, the existing Freespace edge point information often has problems such as frequent jumps and poor stability.
  • the purpose of this application is to provide a Freespace edge point processing method, device, storage medium and electronic equipment to solve the problems existing in the existing technology.
  • a Freespace edge point processing method which includes:
  • the process before filtering the Freespace edge points based on the first status information and obtaining the Freespace valid edge points, the process includes:
  • the first status information of the Freespace edge point is obtained through the camera device, and the first status information at least includes the longitudinal distance and the lateral distance in the direction of each detected Freespace edge point.
  • filtering the Freespace edge points based on the first status information to obtain valid Freespace edge points includes:
  • a Freespace effective edge point is determined among the Freespace edge points.
  • generating a first cache queue and a second cache queue based on the first status information of the Freespace edge point includes:
  • the first cache queue and the second cache queue are generated based on the historical difference pairs of the Freespace edge points, wherein the maximum number of historical difference pairs saved in the second cache queue is the first cache k 1 times the maximum number of historical difference value pairs saved in the queue, where k 1 is a positive integer.
  • the historical difference value pairs include longitudinal distance historical differences and horizontal distance historical differences.
  • the longitudinal threshold and the lateral threshold are respectively set to values corresponding to predetermined percentiles of the historical difference in longitudinal distance and the historical difference in lateral distance in the second cache queue.
  • classifying the Freespace valid edge points to obtain the second status information of the Freespace valid edge points includes:
  • the attribute category of the Freespace effective edge point is determined based on the similarity matrix.
  • the evaluation of the state information collection quality of the Freespace effective edge point based on the first state information and the second state information includes:
  • the state information collection quality of the Freespace effective edge point is evaluated based on the first fitting function and the second fitting function.
  • This application also provides a Freespace edge point processing device, which includes:
  • the first acquisition module is used to filter the Freespace edge points based on the first status information and obtain Freespace valid edge points;
  • the second acquisition module is used to classify the Freespace valid edge points to obtain the second status information of the Freespace valid edge points;
  • An evaluation module configured to evaluate the status information collection quality of the Freespace effective edge point based on the first status information and the second status information.
  • the present application also provides a storage medium that stores a computer program, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.
  • This application also provides an electronic device, which at least includes a memory and a processor.
  • a computer program is stored on the memory.
  • the processor implements the steps of any of the above methods when executing the computer program on the memory.
  • This application can filter invalid points in Freespace edge points through an effective screening algorithm, thereby forming stable and effective Freespace information, which is of great significance to improving the applicability of Freespace edge points and ensuring the safety of intelligent driving vehicles.
  • FIG. 1 is a schematic diagram of the steps of the Freespace edge point processing method of this application.
  • FIG. 2 is a schematic diagram of the steps of the Freespace edge point processing method of this application.
  • FIG. 3 is a schematic diagram of the steps of the Freespace edge point processing method of this application.
  • Figure 4 is a schematic diagram of the steps of the Freespace edge point processing method of this application.
  • the first embodiment of the present disclosure provides a processing method for Freespace edge points used in an intelligent driving system.
  • the processing method facilitates the vehicle to perform intelligent driving functions, as shown in Figure 1, in which Includes the following steps:
  • S101 Filter the Freespace edge points based on the first status information to obtain valid Freespace edge points.
  • the Freespace edge points are filtered based on the first status information to obtain valid Freespace edge points.
  • the Freespace edge points here are used to detect curbs, road boundaries, etc. on the road.
  • the Freespace edge points here refer to scattered points on the boundary of the drivable area on the road.
  • the Freespace edge points here include ⁇ 45 degrees located in the forward area of the vehicle. Within the range, there are a total of 91 sampling points with a resolution of 1°, and the data sampling frequency here can be set to 25Hz.
  • the first status information can be collected, for example, by a camera or other device installed on the vehicle, wherein a vehicle-mounted camera can be used as a specific example.
  • the first status information of the Freespace edge points here at least includes data information such as longitudinal distance, lateral distance, quality and other data detected in the direction of each Freespace edge point.
  • the CANoe CAN open environment
  • the vehicle-mounted camera can be connected through the CAN line, and the DBC (Data Base CAN) file is loaded in the CANoe to analyze the data of the Freespace edge points collected by the vehicle-mounted camera. Obtain the first status information of the Freespace edge point.
  • CANoe here is used for the development, testing and analysis of CAN bus.
  • the Freespace edge points need to be screened before they can be used. For example, after obtaining the Freespace edge points and the first status information, the first status information of the Freespace edge points can be filtered to obtain Freespace effective edge points among the Freespace edge points.
  • a Freespace effective edge point among the Freespace edge points is obtained based on the first status information. Specifically, for example, based on the first status information located at the Freespace edge point of the vehicle obtained above, screening of Freespace effective edge points is performed, especially for 91 points within the range of ⁇ 45deg in the forward area of the vehicle.
  • the Freespace edge points are filtered separately, as shown in Figure 2.
  • the filtering process here includes Includes the following steps:
  • S201 Generate a first cache queue and a second cache queue based on the first status information of the Freespace edge point.
  • a first cache queue and a second cache queue are generated based on the first status information of the Freespace edge point.
  • the first cache queue and the second cache queue are generated based on the historical difference pairs of the Freespace edge points, wherein the maximum number of historical difference pairs saved in the second cache queue is the first cache queue.
  • the maximum number of historical difference pairs stored in a cache queue is k 1 times, where k 1 is a positive integer.
  • the historical difference pairs include historical distance difference values in the vertical direction and historical difference values in the horizontal distance.
  • the longitudinal distance and the lateral distance of the Freespace edge point are obtained by solving The difference between the previous frame and the current frame (usually the absolute value) is used to generate the first cache queue.
  • the quality information of the Freespace edge point indicates that the pixel quality of the current frame is low, then the Freespace edge points do not participate in the calculation.
  • the difference data in the first cache queue is continuously updated, and the update frequency is set to 0.02s, where at most M TH historical difference pairs are stored in the first cache queue, where each historical difference
  • the value pairs include the difference between the longitudinal distance and the lateral distance based on each Freespace edge point.
  • M TH here is a fixed constant. For example, M TH can be set to ⁇ 20. Excessive historical differences will automatically overflow.
  • a second cache queue is also generated based on the first status information of the Freespace edge point.
  • the second cache queue here is also continuously updated, and the update frequency is set to 0.02s.
  • the second cache queue stores at most M TH *k 1 historical difference pairs, and k 1 is a positive integer, where , each historical difference pair includes the difference based on the longitudinal distance and the lateral distance of each Freespace edge point, and excessive historical differences will automatically overflow.
  • S202 Determine a vertical threshold and a horizontal threshold respectively based on the second cache queue.
  • the vertical threshold and the horizontal threshold are respectively determined based on the second cache queue.
  • the longitudinal threshold and the lateral threshold are respectively set to values corresponding to predetermined percentiles of the historical difference in longitudinal distance and the historical difference in lateral distance in the second cache queue.
  • the vertical threshold needs to be set to For example, 95% of the historical differences in longitudinal distances in the second cache queue are less than x, and 5% of the historical differences in longitudinal distances are greater than x, then x is considered to be the 95% percentile of the historical differences in longitudinal distances in the second cache queue.
  • it is also necessary to set the horizontal threshold to Y TH where Y TH is equal to the value corresponding to the 95% percentile of the historical difference in the horizontal distance in the second cache queue.
  • the calculation method here is the same as the above-mentioned vertical threshold. in the same way.
  • S203 Determine a count value in the first cache queue based on the vertical threshold and the horizontal threshold.
  • a count value is determined in the first cache queue based on the vertical threshold and the horizontal threshold. Specifically, statistically count the numerical frequency of the longitudinal distance historical difference and the lateral distance historical difference in the historical difference pairs in the first cache queue, respectively exceeding the longitudinal threshold and the lateral threshold, and Set the count value to N TH .
  • a Freespace effective edge point is determined among the Freespace edge points. . Specifically, when the count value N TH of the Freespace edge point in a specified direction is greater than or equal to M TH *k 2 , where k 2 is a proportional coefficient with a range of 0-1, then the Freespace in that direction If the edge point jumps violently near the current frame, the Freespace edge point in this direction is considered to be an invalid point. Until the count value N TH is less than M TH *k 2 , the Freespace edge point in this direction is considered to be Freespace. Valid edge points.
  • S102 Classify the Freespace valid edge points to obtain second status information of the Freespace valid edge points.
  • the Freespace effective edge points are classified to obtain the third of the Freespace effective edge points.
  • Status information Specifically, perform classification processing on the Freespace effective edge points obtained through screening in the above steps, and obtain, for example, category attributes of each Freespace effective edge point to achieve Characterize the Freespace effective edge points formed by different object types.
  • the category attributes here are used to reflect different object types, such as buildings, other vehicles, pedestrians, etc., as shown in Figure 3.
  • the specific implementation steps are as follows:
  • the original data matrix of the Freespace effective edge point is constructed.
  • y jmax and y jmin respectively represent the maximum value and minimum value of the original data of the Freespace edge point in the jth column.
  • a similarity matrix is established between any two Freespace effective edge points based on the original data matrix. Furthermore, a similarity matrix is established between any two of the Freespace effective edge points, as follows:
  • the attribute category of the Freespace valid edge point is determined based on the similarity matrix.
  • processing method also includes:
  • S103 Evaluate the state information collection quality of the Freespace effective edge point based on the first state information and the second state information.
  • the evaluation is performed based on the first state information and the second state information.
  • the quality of status information collection of Freespace effective edge points is used for testing and result evaluation.
  • the first status information of the Freespace effective edge points of the objects with the same category attribute among the processed Freespace edge points is output, for example, including the longitudinal distance and the lateral distance.
  • the vehicle is actually tested against the same object to verify the quality of status information collection, as shown in Figure 4, which specifically includes:
  • S403 Evaluate the state information collection quality of the Freespace effective edge point based on the first fitting function and the second fitting function.
  • the vehicle is equipped with a vehicle-mounted camera, and there is a road boundary in the form of a curb on the right side of the vehicle.
  • a Freespace edge point whose category attribute is the road boundary in the form of a curb will be used.
  • the Freespace effective edge points related to the right curb are obtained, and the polynomial fitting method is used to calculate the Freespace edge points of the same category of attributes. Effective edge points are fitted to a polynomial.
  • the specific method is as follows:
  • the longitudinal distance and lateral distance data of the Freespace effective edge points based on the same category attribute of the road boundary in the form of a curb on the right side collected by a vehicle-mounted camera, for example, are formed into the following table:
  • the RT-Range system and computing device can be installed on the moving platform.
  • RT -The Range system and the computing device are connected through an Ethernet cable to push the motion platform here to move along the right road boundary.
  • the RT-Range system transmits the position information of the road boundary point to the computing device through the Ethernet cable to realize the road boundary. Collection of point information, in this way, the longitudinal distance and lateral distance data of road boundary points collected based on the RT-Range system are obtained:
  • b i is the corresponding coefficient of x di , so that the fitting function of the road boundary point measured based on the RT-Range system can be obtained:
  • the quality factor is defined here:
  • Q ⁇ Q TH where Q TH is the quality evaluation threshold, it is considered that the quality of the output processed Freespace effective edge point information is good. If Q > Q TH , it is considered that the output processed information of the Freespace effective edge point is good. The quality of the information of Freespace effective edge points is poor, and the screening method of Freespace edge points needs to be optimized.
  • This application can filter invalid points in Freespace edge points through an effective screening algorithm, thereby forming stable and effective Freespace information, which is of great significance to improving the applicability of Freespace edge points and ensuring the safety of intelligent driving vehicles.
  • the second embodiment of the present disclosure relates to a Freespace edge point processing device, which is used to perform the processing method in the first embodiment. It includes a first acquisition module, a second acquisition module and an evaluation module. The above modules are coupled to each other, where :
  • the first acquisition module is used to filter the Freespace edge points based on the first status information and acquire Freespace valid edge points;
  • the second acquisition module is used to classify the Freespace effective edge points to obtain the second status information of the Freespace effective edge points;
  • the evaluation module is used to evaluate the status information collection quality of the Freespace effective edge point based on the first status information and the second status information.
  • the first acquisition module is further configured to acquire the first status information of the Freespace edge point through the camera device.
  • the first status information at least includes the longitudinal distance and the lateral distance in the direction of each detected Freespace edge point. .
  • the first acquisition module includes:
  • a generation unit configured to generate a first cache queue and a second cache queue based on the first status information of the Freespace edge point
  • a threshold determination unit configured to respectively determine a vertical threshold and a horizontal threshold based on the second cache queue. threshold
  • a count value determination unit configured to determine a count value in the first cache queue based on the vertical threshold and the horizontal threshold
  • a valid point determination unit is configured to determine Freespace valid edge points among the Freespace edge points based on the count value.
  • the generating unit is specifically configured to generate the first cache queue and the second cache queue based on the historical difference pairs of the Freespace edge points, wherein the maximum historical difference pair saved in the second cache queue is The number is k 1 times the maximum number of historical difference pairs saved in the first cache queue, where k 1 is a positive integer.
  • the historical difference pairs include longitudinal distance historical differences and lateral distance historical differences.
  • the longitudinal threshold and the lateral threshold are respectively set to values corresponding to predetermined percentiles of the historical difference in longitudinal distance and the historical difference in lateral distance in the second cache queue.
  • the second acquisition module includes:
  • An attribute category determination unit is configured to determine the attribute category of the Freespace effective edge point based on the similarity matrix.
  • the evaluation module includes:
  • a first fitting function acquisition unit configured to acquire a first fitting function based on the first state information collected by a camera device of the Freespace effective edge point, where the Freespace effective edge point has the predetermined second state information.
  • a second fitting function acquisition unit configured to acquire a second fitting function based on the first state information of the Freespace effective edge point collected by the lidar device;
  • An evaluation unit configured to evaluate the state information collection quality of the Freespace effective edge point based on the first fitting function and the second fitting function.
  • This application can filter invalid points in Freespace edge points through an effective screening algorithm, thereby forming stable and effective Freespace information, which is of great significance to improving the applicability of Freespace edge points and ensuring the safety of intelligent driving vehicles.
  • a third embodiment of the present disclosure provides a storage medium that is computer-readable
  • the medium stores a computer program.
  • the computer program is executed by the processor, the method provided by the first embodiment of the present disclosure is implemented, including the following steps S11 to S13:
  • This application can filter invalid points in Freespace edge points through an effective screening algorithm, thereby forming stable and effective Freespace information, which is of great significance to improving the applicability of Freespace edge points and ensuring the safety of intelligent driving vehicles.
  • the fourth embodiment of the present disclosure provides an electronic device.
  • the electronic device at least includes a memory and a processor.
  • a computer program is stored on the memory.
  • the processor implements the method provided by any embodiment of the present disclosure when executing the computer program on the memory. .
  • the electronic device computer program steps are as follows S21 to S23:
  • processor also executes the computer program in the above fourth embodiment
  • This application can filter invalid points in Freespace edge points through an effective screening algorithm, thereby forming stable and effective Freespace information, which is of great significance to improving the applicability of Freespace edge points and ensuring the safety of intelligent driving vehicles.
  • the above-mentioned storage medium may be included in the above-mentioned electronic device; it may also exist separately without being assembled into the electronic device.
  • the above storage medium carries one or more programs.
  • the electronic device obtains at least two Internet Protocol addresses; sends a node evaluation request including at least two Internet Protocol addresses to the node evaluation device, wherein the node evaluation device selects from at least two Internet Protocol addresses, Select an Internet Protocol address and return it; receive the Internet Protocol address returned by the node evaluation device; wherein the obtained Internet Protocol address indicates an edge node in the content distribution network.
  • the storage medium carries one or more programs.
  • the electronic device When the one or more programs are executed by the electronic device, the electronic device: receives a node evaluation request including at least two Internet Protocol addresses; receives a node evaluation request from at least two Internet Protocol addresses; Among the protocol addresses, an Internet Protocol address is selected; the selected Internet Protocol address is returned; wherein the received Internet Protocol address indicates an edge node in the content distribution network.
  • Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, including but not limited to object-oriented programming languages—such as Java, Smalltalk, C++, and Includes conventional procedural programming languages—such as "C” or similar programming languages.
  • the program code may execute entirely on the passenger computer, partly on the passenger computer, as a stand-alone software package, partly on the passenger computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer may be connected to the passenger computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider). Internet connection).
  • LAN local area network
  • WAN wide area network
  • Internet service provider e.g., using an Internet service provider
  • the above-mentioned storage medium of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two.
  • the computer-readable storage medium may be, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof. More specific examples of computer readable storage media may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard drive, random access memory (RAM), read only memory (ROM), removable Programmd read-only memory (EPROM or flash memory), fiber optics, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. This propagated data signal It can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.
  • a computer-readable signal medium may also be any storage medium other than computer-readable storage media that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
  • the program code contained on the storage medium can be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
  • each block in the flowchart or block diagram may represent a module, segment, or portion of code that contains one or more logic functions that implement the specified executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown one after another may actually execute substantially in parallel, or they may sometimes execute in the reverse order, depending on the functionality involved.
  • each block of the block diagram and/or flowchart illustration, and combinations of blocks in the block diagram and/or flowchart illustration can be implemented by special purpose hardware-based systems that perform the specified functions or operations. , or can be implemented using a combination of specialized hardware and computer instructions.
  • the units described in this application can be implemented in software or hardware. Among them, the name of a unit does not constitute a limitation on the unit itself under certain circumstances.
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSPs Application Specific Standard Products
  • SOCs Systems on Chips
  • CPLD Complex Programmable Logical device
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include electrical connections based on one or more wires, laptop disks, hard drives, random access memory (RAM), read only memory (ROM), Erasable programmable read-only memory (EPROM or flash memory), fiber optics, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory Erasable programmable read-only memory
  • CD-ROM portable compact disk read-only memory
  • optical storage devices magnetic storage devices, or any suitable combination of the above.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Algebra (AREA)
  • Software Systems (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)

Abstract

本申请提供一种Freespace边缘点的处理方法以及装置,所述处理方法包括针对所述Freespace边缘点基于第一状态信息进行筛选,获取Freespace有效边缘点;对所述Freespace有效边缘点进行分类以获取所述Freespace有效边缘点的第二状态信息;基于所述第一状态信息和所述第二状态信息评价所述Freespace有效边缘点的状态信息采集质量。本申请能够通过有效的筛选算法对Freespace边缘点中的无效点进行过滤,进而形成稳定有效的Freespace信息,对提高Freespace的边缘点适用性以及保障智能驾驶汽车安全具有重大意义。

Description

一种Freespace边缘点的处理方法以及装置 技术领域
本申请涉及智能驾驶控制领域,具体地涉及一种用于智能驾驶系统的Freespace边缘点的处理方法、装置、存储介质以及电子设备。本申请要求于2022年06月20日提交至中国国家知识产权局、申请号为202210700010.0、发明名称为“一种Freespace边缘点的处理方法以及装置”的专利申请的优先权。
背景技术
在目前的智能驾驶主流技术中,Freespace技术已经成为不可或缺的一部分,这里的Freespace是指汽车的可行驶区域,其包括避开其他汽车、行人、马路边等的区域。其中,Freespace边缘点是指可行驶区域的边界上的散点,一般情况下,Freespace边缘点的分辨率为1deg。准确的Freespace边缘点的信息能够为自动驾驶系统提供有效的感知输入,从而为决策规划层提供数据保障。然而,目前现有的Freespace边缘点的信息往往存在跳变频繁、稳定性差等问题。
发明内容
本申请的目的在于提供一种Freespace边缘点的处理方法、装置、存储介质以及电子设备,以解决现有技术中存在的问题。
为了解决上述技术问题,本申请采用了如下技术方案:
一种Freespace边缘点的处理方法,其包括:
针对所述Freespace边缘点基于第一状态信息进行筛选,获取Freespace有效边缘点;
对所述Freespace有效边缘点进行分类以获取所述Freespace有效边缘点的第二状态信息;
基于所述第一状态信息和所述第二状态信息评价所述Freespace有效 边缘点的状态信息采集质量。
在一些实施例中,在所述针对所述Freespace边缘点基于第一状态信息进行筛选,获取Freespace有效边缘点之前,包括:
通过摄像装置获取Freespace边缘点的第一状态信息,所述第一状态信息至少包括检测到的每个所述Freespace边缘点所在方向上的纵向距离和横向距离。
在一些实施例中,所述针对所述Freespace边缘点基于第一状态信息进行筛选,获取Freespace有效边缘点,包括:
基于所述Freespace边缘点的第一状态信息,生成第一缓存队列和第二缓存队列;
基于所述第二缓存队列分别确定纵向阈值和横向阈值;
基于所述纵向阈值和所述横向阈值在所述第一缓存队列中确定计数值;
基于所述计数值,在所述Freespace边缘点中确定Freespace有效边缘点。
在一些实施例中,所述基于所述Freespace边缘点的第一状态信息,生成第一缓存队列和第二缓存队列,包括:
基于所述Freespace边缘点的历史差值对生成所述第一缓存队列和所述第二缓存队列,其中,所述第二缓存队列中保存的历史差值对的最大数量是所述第一缓存队列中保存的历史差值对的最大数量对的k1倍,其中k1为正整数,所述历史差值对包括纵向距离历史差值和横向距离历史差值。
在一些实施例中,所述纵向阈值和所述横向阈值分别设置为所述第二缓存队列中的纵向距离历史差值和横向距离历史差值的预定百分位对应的数值。
在一些实施例中,所述对所述Freespace有效边缘点进行分类以获取所述Freespace有效边缘点的第二状态信息,包括:
构建所述Freespace有效边缘点的原始数据矩阵;
基于所述原始数据矩阵对于任意两个所述Freespace有效边缘点之间建立相似矩阵;
基于所述相似矩阵确定所述Freespace有效边缘点的属性类别。
在一些实施例中,所述基于所述第一状态信息和所述第二状态信息评价所述Freespace有效边缘点的状态信息采集质量,包括:
获取基于摄像装置采集所述Freespace有效边缘点的所述第一状态信息的第一拟合函数,所述Freespace有效边缘点具有预定的所述第二状态信息;
获取基于激光雷达装置采集所述Freespace有效边缘点的所述第一状态信息的第二拟合函数;
基于所述第一拟合函数和所述第二拟合函数评价所述Freespace有效边缘点的状态信息采集质量。
本申请还提供一种Freespace边缘点的处理装置,其包括:
第一获取模块,用于针对所述Freespace边缘点基于第一状态信息进行筛选,获取Freespace有效边缘点;
第二获取模块,用于对所述Freespace有效边缘点进行分类以获取所述Freespace有效边缘点的第二状态信息;
评价模块,用于基于所述第一状态信息和所述第二状态信息评价所述Freespace有效边缘点的状态信息采集质量。
本申请还提供一种存储介质,存储有计算机程序,所述计算机程序被处理器执行时实现上述任一项所述方法的步骤。
本申请还提供一种电子设备,至少包括存储器、处理器,所述存储器上存储有计算机程序,所述处理器在执行所述存储器上的计算机程序时实现上述任一项所述方法的步骤。
本申请能够通过有效的筛选算法对Freespace边缘点中的无效点进行过滤,进而形成稳定有效的Freespace信息,对提高Freespace的边缘点适用性以及保障智能驾驶汽车安全具有重大意义。
附图说明
为了更清楚地说明本申请或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请中记载的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1为本申请的Freespace边缘点的处理方法的步骤示意图;
图2为本申请的Freespace边缘点的处理方法的步骤示意图;
图3为本申请的Freespace边缘点的处理方法的步骤示意图;
图4为本申请的Freespace边缘点的处理方法的步骤示意图。
具体实施方式
此处参考附图描述本申请的各种方案以及特征。
应理解的是,可以对此处申请的实施例做出各种修改。因此,上述说明书不应该视为限制,而仅是作为实施例的范例。本领域的技术人员将想到在本申请的范围和精神内的其他修改。
包含在说明书中并构成说明书的一部分的附图示出了本申请的实施例,并且与上面给出的对本申请的大致描述以及下面给出的对实施例的详细描述一起用于解释本公开的原理。
通过下面参照附图对给定为非限制性实例的实施例的优选形式的描述,本公开的这些和其它特性将会变得显而易见。
还应当理解,尽管已经参照一些具体实例对本公开进行了描述,但本领域技术人员能够确定地实现本公开的很多其它等效形式,它们具有如权利要求所述的特征并因此都位于借此所限定的保护范围内。
当结合附图时,鉴于以下详细说明,本公开的上述和其他方面、特征和优势将变得更为显而易见。
此后参照附图描述本公开的具体实施例;然而,应当理解,所申请的实施例仅仅是本公开的实例,其可采用多种方式实施。熟知和/或重复的功能和结构并未详细描述以避免不必要或多余的细节使得本公开模糊不清。因此,本文所申请的具体的结构性和功能性细节并非意在限定,而是仅仅作为权利要求的基础和代表性基础用于教导本领域技术人员以实质上任意合适的详细结构多样地使用本公开。
本说明书可使用词组“在一种实施例中”、“在另一个实施例中”、“在又一实施例中”或“在其他实施例中”,其均可指代根据本公开的相同或不同实施例中的一个或多个。
本公开的第一实施例提供一种用于智能驾驶系统的Freespace边缘点的处理方法,所述处理方法便于车辆执行智能驾驶功能,如图1所示,其 包括以下步骤:
S101,针对所述Freespace边缘点基于第一状态信息进行筛选,获取Freespace有效边缘点。
在本步骤中,针对所述Freespace边缘点基于第一状态信息进行筛选,获取Freespace有效边缘点。具体地,这里的所述Freespace边缘点用于实现对道路上的路沿、道路边界等的检测。
在本步骤之前,需要首先获取Freespace边缘点的第一状态信息。这里的所述Freespace边缘点是指道路上可行驶区域的边界上的散点,其中,在具体的实施方式中,这里的所述Freespace边缘点包括位于所述车辆的前向区域的±45度范围内,分辨率为1°的共计91个采样点,这里的数据采样频率可以设置为25Hz。
进一步地,所述第一状态信息例如可以通过设置在所述车辆上的摄像装置或者其他装置采集得到,其中,车载摄像头可以作为具体的举例。这里的所述Freespace边缘点的第一状态信息至少包括每个所述Freespace边缘点所在方向上检测到的纵向距离、横向距离、质量等数据信息。在一个具体的实施方式中,可以通过CAN线连接CANoe(CAN open environment)与车载摄像头,在CANoe中加载DBC(Data Base CAN)文件实现对车载摄像头采集的所述Freespace边缘点的数据进行解析以获取所述Freespace边缘点的第一状态信息。其中,这里的CANoe用于CAN总线的开发、测试和分析。
考虑到由于所述Freespace边缘点的跳变较大、信号稳定性差等原因,需要对所述Freespace边缘点的进行筛选处理后才能加以使用。例如在获取所述Freespace边缘点以及所述第一状态信息后,可以针对所述Freespace边缘点的所述第一状态信息进行筛选,以获取所述Freespace边缘点中的Freespace有效边缘点。
进一步地,在获取所述Freespace边缘点的第一状态信息之后,在本步骤中,基于所述第一状态信息以获取所述Freespace边缘点中的Freespace有效边缘点。具体地,例如针对上述获取的位于所述车辆的所述Freespace边缘点的所述第一状态信息后,进行Freespace有效边缘点的筛选,尤其针对所述车辆的前向区域±45deg范围内的91个所述Freespace边缘点分别进行筛选,如图2所示,这里的所述筛选的过程包 括以下步骤:
S201,基于所述Freespace边缘点的第一状态信息,生成第一缓存队列和第二缓存队列。
在本步骤中,基于所述Freespace边缘点的第一状态信息,生成第一缓存队列和第二缓存队列。其中,基于所述Freespace边缘点的历史差值对生成所述第一缓存队列和所述第二缓存队列,其中,所述第二缓存队列中保存的历史差值对的最大数量是所述第一缓存队列中保存的历史差值对的最大数量对的k1倍,其中k1为正整数,所述历史差值对包括纵向距离历史差值和横向距离历史差值。
具体地,在基于所述Freespace边缘点的第一状态信息,生成第一缓存队列中,在获取任意方向的所述Freespace边缘点的数据后,求解获取所述Freespace边缘点的纵向距离以及横向距离的前一帧与当前帧的差值(一般取绝对值)以生成第一缓存队列,同时,如果所述Freespace边缘点的质量信息表示当前帧的像素质量较低,则当前帧中的所述Freespace边缘点不参与计算。
进一步地,所述第一缓存队列中的差值数据保持不断更新,更新频率设置为0.02s,其中,所述第一缓存队列中最多保存MTH个历史差值对,其中,每个历史差值对包括基于每个所述Freespace边缘点的纵向距离以及横向距离的差值,这里的MTH为固定常数,例如可以设置MTH≥20,过多的历史差值将自动溢出。
此外,在本步骤中,还基于所述Freespace边缘点的第一状态信息,生成第二缓存队列。具体地,这里的所述第二缓存队列同样保持不断更新,更新频率设置为0.02s,所述第二缓存队列中最多保存MTH*k1个历史差值对,k1为正整数,其中,每个历史差值对包括基于每个所述Freespace边缘点的纵向距离以及横向距离的差值,过多的历史差值将自动溢出。
S202,基于所述第二缓存队列分别确定纵向阈值和横向阈值。
在通过上述步骤S201基于所述Freespace边缘点的第一状态信息,生成第一缓存队列和第二缓存队列之后,在本步骤中,基于所述第二缓存队列分别确定纵向阈值和横向阈值。其中,所述纵向阈值和所述横向阈值分别设置为所述第二缓存队列中的纵向距离历史差值和横向距离历史差值的预定百分位对应的数值。
具体地,在本步骤中需要设置纵向阈值为XTH,这里的XTH等于所述第二缓存队列中的纵向距离历史差值的例如95%百分位对应的数值,也就是,如果所述第二缓存队列中例如95%的纵向距离历史差值小于x,5%的纵向距离历史差值大于x,则认为x为所述第二缓存队列中纵向距离历史差值的95%百分位对应的数值,同时还需要设置横向阈值为YTH,这里的YTH等于所述第二缓存队列中的横向距离历史差值的95%百分位对应的数值,这里的计算方式与上述纵向阈值的方式相同。
S203,基于所述纵向阈值和所述横向阈值在所述第一缓存队列中确定计数值。
在通过上述步骤S202基于所述第二缓存队列分别确定纵向阈值和横向阈值之后,在本步骤中,基于所述纵向阈值和所述横向阈值在所述第一缓存队列中确定计数值。具体地,对所述第一缓存队列中的历史差值对中的纵向距离历史差值和横向距离历史差值的大小分别超过所述纵向阈值和所述横向阈值的数值频次进行统计计数,并将计数值设置为NTH
S204,基于所述计数值,在所述Freespace边缘点中确定Freespace有效边缘点。
通过上述步骤S203基于所述纵向阈值和所述横向阈值在所述第一缓存队列中确定计数值之后,在本步骤中,基于所述计数值,在所述Freespace边缘点中确定Freespace有效边缘点。具体地,当某指定方向的所述Freespace边缘点的计数值NTH大于等于MTH*k2时,这里的k2为比例系数,其范围为0-1,则该方向上的所述Freespace边缘点在当前帧附近跳变剧烈,则认为该方向上的所述Freespace边缘点为无效点,直至计数值NTH小于MTH*k2后,认为该方向上的所述Freespace边缘点为Freespace有效边缘点。
S102,对所述Freespace有效边缘点进行分类以获取所述Freespace有效边缘点的第二状态信息。
在通过上述步骤S101针对所述Freespace边缘点基于第一状态信息进行筛选,获取Freespace有效边缘点之后,在本步骤中,对所述Freespace有效边缘点进行分类以获取所述Freespace有效边缘点的第二状态信息。具体地,针对上述步骤中经过筛选获取的所述Freespace有效边缘点进行分类处理,获取每个所述Freespace有效边缘点的例如类别属性,以实现 对不同物体类型形成的Freespace有效边缘点进行特征划分,这里的类别属性用于体现不同物体类型,例如建筑物、其他车辆、行人等,如图3所示,具体实现步骤如下:
S301,构建所述Freespace有效边缘点的原始数据矩阵。
在本步骤中,在获取所述Freespace有效边缘点的第二状态信息的过程中,构建所述Freespace有效边缘点的原始数据矩阵,所述原始数据矩阵如下表示:
A=(yij)n×m
式中,i=1,2,3,其分别对应所述Freespace有效边缘点的X坐标、Y坐标以及运动速度;j=1,2,…91,其表示所述Freespace有效边缘点的序号;yij即代表第j个Freespace有效边缘点的第i项参数,这样n=3;m=91。
进一步地,还可以对所述Freespace有效边缘点的原始数据矩阵中的数据进行归一化处理,归一化后的样本集为X=(xij)n×m,其中:
式中,yjmax、yjmin分别表示第j列Freespace边缘点的原始数据的最大值和最小值。
S302,基于所述原始数据矩阵对于任意两个所述Freespace有效边缘点之间建立相似矩阵。
在通过上述步骤S301构建所述Freespace有效边缘点的原始数据矩阵之后,在本步骤中,基于所述原始数据矩阵对于任意两个所述Freespace有效边缘点之间建立相似矩阵。进一步,对于任意两个所述Freespace有效边缘点之间建立相似矩阵,具体如下:
其中:

S303,基于所述相似矩阵确定所述Freespace有效边缘点的属性类别。
在通过上述步骤S302基于所述原始数据矩阵对于任意两个所述Freespace有效边缘点之间建立相似矩阵之后,在本步骤中,基于所述相似矩阵确定所述Freespace有效边缘点的属性类别。具体地,在所述相似矩阵的基础上建立R矩阵,如下所示:
t(R)=R2
其中,设置以下表达式:
t(R)=(r′ij)91×91

其中,取k3=0.9。
S304,基于所述原始数据矩阵确定所述第二状态信息。
在通过上述步骤S301构建Freespace边缘点的原始数据矩阵之后,在本步骤中,基于所述原始数据矩阵确定所述第二状态信息。根据上述确定的原始数据矩阵,如果若r′ij(λ)=1,则认为第i个所述Freespace有效边缘点与第j个所述Freespace有效边缘点的属于同一个对象,例如属于同一个物体;这样,在对所有所述Freespace有效边缘点进行计算和类别判断后,进而得到所有的所述Freespace有效边缘点的类别属性。
此外,所述处理方法还包括:
S103,基于所述第一状态信息和所述第二状态信息评价所述Freespace有效边缘点的状态信息采集质量。
在通过上述步骤S101和S102分别获取所述Freespace有效边缘点的第一状态信息和所述第二状态信息后,在本步骤中基于所述第一状态信息和所述第二状态信息评价所述Freespace有效边缘点的状态信息采集质量。也就是,本步骤用于测试及结果评价。具体地,基于上述步骤S101-S103输出处理后的所述Freespace边缘点中具有相同类别属性的对象的Freespace有效边缘点的所述第一状态信息,例如包括纵向距离以及横向 距离信息等之后,将所述车辆针对相同对象进行实际测试,以验证状态信息采集的质量,如图4所示,具体包括:
S401,获取基于摄像装置采集所述Freespace有效边缘点的所述第一状态信息的第一拟合函数,所述Freespace有效边缘点具有预定的所述第二状态信息;
S402,获取基于激光雷达装置采集所述Freespace有效边缘点的所述第一状态信息的第二拟合函数;
S403,基于所述第一拟合函数和所述第二拟合函数评价所述Freespace有效边缘点的状态信息采集质量。
在测试的实施方式中,例如在所述车辆上搭载车载摄像头,在所述车辆的右侧存在路缘石形式的道路边界,这里将采用类别属性为路缘石形式的道路边界的Freespace边缘点,在通过车载摄像头采集得到的道路边界的所述Freespace边缘点并通过上述步骤处理后,获取与右侧路缘石相关的所述Freespace有效边缘点,并采用多项式拟合方法对同一类别属性的所述Freespace有效边缘点进行拟合,从而拟合为多项式,具体方法如下:
基于所述车辆上的例如车载摄像头采集得到的右侧路缘石形式的道路边界的同一类别属性的所述Freespace有效边缘点的纵向距离以及横向距离数据并形成如下表格:
在拟合方程中输入纵向距离数据x=[x1、x2…xm]和横向距离数据y=[Y1、Y2…Ym],之后通过以下基于最小二乘法的程序确定道路边界的所述Freespace有效边缘点的拟合方程的阶数d,其中,程序可以如下

这样,通过上述程序可以获得拟合方程的阶数在误差值平方和小于0.05时的拟合方程阶数d,进一步输入最小二乘法的函数:
y1=polyfit(x,y,d)
从而获得多项式拟合函数系数即:
a0、a1……、ad
其中,d为拟合方程的阶数,ai是对应的xd-i的系数,如此便可获得道路边界的所述Freespace有效边缘点的拟合函数如下:
进一步地,为了实现本步骤中的验证,还需要获得道路边界点的真实位置信息作为真值以进行验证,例如可以在运动平台上安装固定有RT-Range系统以及计算装置(例如计算机),RT-Range系统与计算装置之间通过以太网电缆连接,推动这里的运动平台沿着右侧道路边界运动,RT-Range系统将道路边界点的位置信息通过以太网电缆传输至计算装置进而实现道路边界点信息的采集,这样获取基于RT-Range系统采集得到的道路边界点的纵向距离以及横向距离数据:
在重新输入纵向距离数据x=[x1、x2…xq],横向距离数据y=[Y1、Y2…Yq]后输入最小二乘法函数:
y2=polyfit(x,y,d)
同时获得多项式拟合函数系数:
b0、b1……、bd
其中,bi是对应的xd-i的系数,如此便可获得基于RT-Range系统测量得到的道路边界点的拟合函数:
所述的a0、a1……、ad及b0、b1……、bd参数计算完成后,结果分析,以期实现对步骤S101输出处理后的所述Freespace有效边缘点信息的质量的评价,在这里定义质量因数:
如果Q≤QTH,这里的QTH为质量评价阈,值则认为输出处理后的所述Freespace有效边缘点的信息的质量较好,如果Q>QTH,则认为输出的处理后的所述Freespace有效边缘点的信息的质量不佳,需要对所述Freespace边缘点的筛选方式进行优化。
本申请能够通过有效的筛选算法对Freespace边缘点中的无效点进行过滤,进而形成稳定有效的Freespace信息,对提高Freespace的边缘点适用性以及保障智能驾驶汽车安全具有重大意义。
本公开的第二实施例涉及一种Freespace边缘点的处理装置,其用于执行上述第一实施例中的处理方法包括第一获取模块、第二获取模块以及评价模块,上述模块相互耦合,其中:
所述第一获取模块,用于针对所述Freespace边缘点基于第一状态信息进行筛选,获取Freespace有效边缘点;
所述第二获取模块,用于对所述Freespace有效边缘点进行分类以获取所述Freespace有效边缘点的第二状态信息;
所述评价模块,用于基于所述第一状态信息和所述第二状态信息评价所述Freespace有效边缘点的状态信息采集质量。
所述第一获取模块,进一步用于通过摄像装置获取Freespace边缘点的第一状态信息,所述第一状态信息至少包括检测到的每个所述Freespace边缘点所在方向上的纵向距离和横向距离。
所述第一获取模块,包括:
生成单元,用于基于所述Freespace边缘点的第一状态信息,生成第一缓存队列和第二缓存队列;
阈值确定单元,用于基于所述第二缓存队列分别确定纵向阈值和横向 阈值;
计数值确定单元,用于基于所述纵向阈值和所述横向阈值在所述第一缓存队列中确定计数值;
有效点确定单元,用于基于所述计数值,在所述Freespace边缘点中确定Freespace有效边缘点。
所述生成单元具体用于基于所述Freespace边缘点的历史差值对生成所述第一缓存队列和所述第二缓存队列,其中,所述第二缓存队列中保存的历史差值对的最大数量是所述第一缓存队列中保存的历史差值对的最大数量对的k1倍,其中k1为正整数,所述历史差值对包括纵向距离历史差值和横向距离历史差值。
进一步地,所述纵向阈值和所述横向阈值分别设置为所述第二缓存队列中的纵向距离历史差值和横向距离历史差值的预定百分位对应的数值。
所述第二获取模块,包括:
构建单元,用于构建所述Freespace有效边缘点的原始数据矩阵;
建立单元,用于基于所述原始数据矩阵对于任意两个所述Freespace有效边缘点之间建立相似矩阵;
属性类别确定单元,用于基于所述相似矩阵确定所述Freespace有效边缘点的属性类别。
所述评价模块,包括:
第一拟合函数获取单元,用于获取基于摄像装置采集所述Freespace有效边缘点的所述第一状态信息的第一拟合函数,所述Freespace有效边缘点具有预定的所述第二状态信息;
第二拟合函数获取单元,用于获取基于激光雷达装置采集所述Freespace有效边缘点的所述第一状态信息的第二拟合函数;
评价单元,用于基于所述第一拟合函数和所述第二拟合函数评价所述Freespace有效边缘点的状态信息采集质量。
本申请能够通过有效的筛选算法对Freespace边缘点中的无效点进行过滤,进而形成稳定有效的Freespace信息,对提高Freespace的边缘点适用性以及保障智能驾驶汽车安全具有重大意义。
本公开的第三实施例提供了一种存储介质,该存储介质为计算机可读 介质,存储有计算机程序,该计算机程序被处理器执行时实现本公开第一实施例提供的方法,包括如下步骤S11至S13:
S11,针对所述Freespace边缘点基于第一状态信息进行筛选,获取Freespace有效边缘点;
S12,对所述Freespace有效边缘点进行分类以获取所述Freespace有效边缘点的第二状态信息;
S13,基于所述第一状态信息和所述第二状态信息评价所述Freespace有效边缘点的状态信息采集质量。
进一步地,该计算机程序被处理器执行时实现本公开第一实施例提供的其他方法
本申请能够通过有效的筛选算法对Freespace边缘点中的无效点进行过滤,进而形成稳定有效的Freespace信息,对提高Freespace的边缘点适用性以及保障智能驾驶汽车安全具有重大意义。
本公开的第四实施例提供了一种电子设备,该电子设备至少包括存储器和处理器,存储器上存储有计算机程序,处理器在执行存储器上的计算机程序时实现本公开任意实施例提供的方法。示例性的,电子设备计算机程序步骤如下S21至S23:
S21,针对所述Freespace边缘点基于第一状态信息进行筛选,获取Freespace有效边缘点;
S22,对所述Freespace有效边缘点进行分类以获取所述Freespace有效边缘点的第二状态信息;
S23,基于所述第一状态信息和所述第二状态信息评价所述Freespace有效边缘点的状态信息采集质量。
进一步地,处理器还执行上述第四实施例中的计算机程序
本申请能够通过有效的筛选算法对Freespace边缘点中的无效点进行过滤,进而形成稳定有效的Freespace信息,对提高Freespace的边缘点适用性以及保障智能驾驶汽车安全具有重大意义。
上述存储介质可以是上述电子设备中所包含的;也可以是单独存在,而未装配入该电子设备中。
上述存储介质承载有一个或者多个程序,当上述一个或者多个程序被 该电子设备执行时,使得该电子设备:获取至少两个网际协议地址;向节点评价设备发送包括至少两个网际协议地址的节点评价请求,其中,节点评价设备从至少两个网际协议地址中,选取网际协议地址并返回;接收节点评价设备返回的网际协议地址;其中,所获取的网际协议地址指示内容分发网络中的边缘节点。
或者,上述存储介质承载有一个或者多个程序,当上述一个或者多个程序被该电子设备执行时,使得该电子设备:接收包括至少两个网际协议地址的节点评价请求;从至少两个网际协议地址中,选取网际协议地址;返回选取出的网际协议地址;其中,接收到的网际协议地址指示内容分发网络中的边缘节点。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码,上述程序设计语言包括但不限于面向对象的程序设计语言—诸如Java、Smalltalk、C++,还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在乘客计算机上执行、部分地在乘客计算机上执行、作为一个独立的软件包执行、部分在乘客计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中,远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到乘客计算机,或者,可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
需要说明的是,本公开上述的存储介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件,或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于:具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中,计算机可读存储介质可以是任何包含或存储程序的有形介质,该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中,计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号,其中承载了计算机可读的程序代码。这种传播的数据信号 可以采用多种形式,包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何存储介质,该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。存储介质上包含的程序代码可以用任何适当的介质传输,包括但不限于:电线、光缆、RF(射频)等等,或者上述的任意合适的组合。
附图中的流程图和框图,图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分,该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意,在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个接连地表示的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或操作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令的组合来实现。
描述于本申请中所涉及到的单元可以通过软件的方式实现,也可以通过硬件的方式来实现。其中,单元的名称在某种情况下并不构成对该单元本身的限定。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如,非限制性地,可以使用的示范类型的硬件逻辑部件包括:现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
在本公开的上下文中,机器可读介质可以是有形的介质,其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备,或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、 可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解,本公开中所涉及的公开范围,并不限于上述技术特征的特定组合而成的技术方案,同时也应涵盖在不脱离上述公开构思的情况下,由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
此外,虽然采用特定次序描绘了各操作,但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下,多任务和并行处理可能是有利的。同样地,虽然在上面论述中包含了若干具体实现细节,但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地,在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题,但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反,上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。
以上对本公开多个实施例进行了详细说明,但本公开不限于这些具体的实施例,本领域技术人员在本公开构思的基础上,能够做出多种变型和修改实施例,这些变型和修改都应落入本公开所要求保护的范围。

Claims (10)

  1. 一种Freespace边缘点的处理方法,其特征在于,包括:
    针对所述Freespace边缘点基于第一状态信息进行筛选,获取Freespace有效边缘点;
    对所述Freespace有效边缘点进行分类以获取所述Freespace有效边缘点的第二状态信息;
    基于所述第一状态信息和所述第二状态信息评价所述Freespace有效边缘点的状态信息采集质量。
  2. 根据权利要求1所述的处理方法,其特征在于,在所述针对所述Freespace边缘点基于第一状态信息进行筛选,获取Freespace有效边缘点之前,包括:
    通过摄像装置获取Freespace边缘点的第一状态信息,所述第一状态信息至少包括检测到的每个所述Freespace边缘点所在方向上的纵向距离和横向距离。
  3. 根据权利要求1所述的处理方法,其特征在于,所述针对所述Freespace边缘点基于第一状态信息进行筛选,获取Freespace有效边缘点,包括:
    基于所述Freespace边缘点的第一状态信息,生成第一缓存队列和第二缓存队列;
    基于所述第二缓存队列分别确定纵向阈值和横向阈值;
    基于所述纵向阈值和所述横向阈值在所述第一缓存队列中确定计数值;
    基于所述计数值,在所述Freespace边缘点中确定Freespace有效边缘点。
  4. 根据权利要求3所述的处理方法,其特征在于,所述基于所述Freespace边缘点的第一状态信息,生成第一缓存队列和第二缓存队列,包括:
    基于所述Freespace边缘点的历史差值对生成所述第一缓存队列和所述第二缓存队列,其中,所述第二缓存队列中保存的历史差值对的最大数量是所述第一缓存队列中保存的历史差值对的最大数量对的k1倍,其中k1为正整数,所述历史差值对包括纵向距离历史差值和横向距离历史差值。
  5. 根据权利要求4所述的处理方法,其特征在于,所述纵向阈值和所述横向阈值分别设置为所述第二缓存队列中的纵向距离历史差值和横向距离历 史差值的预定百分位对应的数值。
  6. 根据权利要求1所述的处理方法,其特征在于,所述对所述Freespace有效边缘点进行分类以获取所述Freespace有效边缘点的第二状态信息,包括:
    构建所述Freespace有效边缘点的原始数据矩阵;
    基于所述原始数据矩阵对于任意两个所述Freespace有效边缘点之间建立相似矩阵;
    基于所述相似矩阵确定所述Freespace有效边缘点的属性类别。
  7. 根据权利要求1所述的处理方法,其特征在于,所述基于所述第一状态信息和所述第二状态信息评价所述Freespace有效边缘点的状态信息采集质量,包括:
    获取基于摄像装置采集所述Freespace有效边缘点的所述第一状态信息的第一拟合函数,所述Freespace有效边缘点具有预定的所述第二状态信息;
    获取基于激光雷达装置采集所述Freespace有效边缘点的所述第一状态信息的第二拟合函数;
    基于所述第一拟合函数和所述第二拟合函数评价所述Freespace有效边缘点的状态信息采集质量。
  8. 一种Freespace边缘点的处理装置,其特征在于,包括:
    第一获取模块,用于针对所述Freespace边缘点基于第一状态信息进行筛选,获取Freespace有效边缘点;
    第二获取模块,用于对所述Freespace有效边缘点进行分类以获取所述Freespace有效边缘点的第二状态信息;
    评价模块,用于基于所述第一状态信息和所述第二状态信息评价所述Freespace有效边缘点的状态信息采集质量。
  9. 一种存储介质,存储有计算机程序,其特征在于,所述计算机程序被处理器执行时实现权利要求1至7中任一项所述方法的步骤。
  10. 一种电子设备,至少包括存储器、处理器,所述存储器上存储有计算机程序,其特征在于,所述处理器在执行所述存储器上的计算机程序时实现权利要求1至7中任一项所述方法的步骤。
PCT/CN2023/092611 2022-06-20 2023-05-06 一种Freespace边缘点的处理方法以及装置 Ceased WO2023246342A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210700010.0 2022-06-20
CN202210700010.0A CN115114494B (zh) 2022-06-20 2022-06-20 一种Freespace边缘点的处理方法以及装置

Publications (1)

Publication Number Publication Date
WO2023246342A1 true WO2023246342A1 (zh) 2023-12-28

Family

ID=83328264

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/092611 Ceased WO2023246342A1 (zh) 2022-06-20 2023-05-06 一种Freespace边缘点的处理方法以及装置

Country Status (2)

Country Link
CN (1) CN115114494B (zh)
WO (1) WO2023246342A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115114494B (zh) * 2022-06-20 2025-02-21 中国第一汽车股份有限公司 一种Freespace边缘点的处理方法以及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3619643A1 (en) * 2017-05-03 2020-03-11 Mobileye Vision Technologies Ltd. Detection and classification systems and methods for autonomous vehicle navigation
CN111754583A (zh) * 2020-05-29 2020-10-09 江苏大学 一种车载三维激光雷达和相机外参联合标定的自动化方法
CN112164090A (zh) * 2020-09-04 2021-01-01 杭州海康威视系统技术有限公司 数据处理方法、装置、电子设备及机器可读存储介质
CN113064179A (zh) * 2021-03-22 2021-07-02 上海商汤临港智能科技有限公司 一种点云数据筛选方法、车辆控制方法及装置
CN113744518A (zh) * 2020-05-30 2021-12-03 华为技术有限公司 一种车辆可行驶区域的检测方法及装置
CN115114494A (zh) * 2022-06-20 2022-09-27 中国第一汽车股份有限公司 一种Freespace边缘点的处理方法以及装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114981138A (zh) * 2020-02-13 2022-08-30 华为技术有限公司 车辆可行驶区域的检测方法以及检测装置
CN112348122B (zh) * 2020-12-03 2024-10-29 苏州挚途科技有限公司 可行驶区域的标注方法、装置和电子设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3619643A1 (en) * 2017-05-03 2020-03-11 Mobileye Vision Technologies Ltd. Detection and classification systems and methods for autonomous vehicle navigation
CN111754583A (zh) * 2020-05-29 2020-10-09 江苏大学 一种车载三维激光雷达和相机外参联合标定的自动化方法
CN113744518A (zh) * 2020-05-30 2021-12-03 华为技术有限公司 一种车辆可行驶区域的检测方法及装置
CN112164090A (zh) * 2020-09-04 2021-01-01 杭州海康威视系统技术有限公司 数据处理方法、装置、电子设备及机器可读存储介质
CN113064179A (zh) * 2021-03-22 2021-07-02 上海商汤临港智能科技有限公司 一种点云数据筛选方法、车辆控制方法及装置
CN115114494A (zh) * 2022-06-20 2022-09-27 中国第一汽车股份有限公司 一种Freespace边缘点的处理方法以及装置

Also Published As

Publication number Publication date
CN115114494A (zh) 2022-09-27
CN115114494B (zh) 2025-02-21

Similar Documents

Publication Publication Date Title
CN112634181B (zh) 用于检测地面点云点的方法和装置
CN109284348B (zh) 一种电子地图的更新方法、装置、设备和存储介质
US10885352B2 (en) Method, apparatus, and device for determining lane line on road
CN108872991A (zh) 目标物检测与识别方法、装置、电子设备、存储介质
CN113313654B (zh) 激光点云滤波去噪方法、系统、设备及存储介质
CN113895460A (zh) 行人轨迹预测方法、装置及存储介质
CN112084810A (zh) 一种障碍物检测方法、装置、电子设备及存储介质
CN113759348A (zh) 一种雷达标定方法、装置、设备及存储介质
CN110132291A (zh) 用于港口的栅格地图生成方法、系统、设备及存储介质
CN110390346A (zh) 目标对象识别方法、装置、电子设备及存储介质
CN115346183A (zh) 一种车道线检测方法、终端及存储介质
CN113284337B (zh) 基于车辆轨迹多维数据的od矩阵计算方法及装置
JP7710700B1 (ja) 車両損傷識別方法、装置、電子デバイス及び記憶媒体
CN114862944A (zh) 一种车辆位姿检测方法、装置及电子设备
CN103365886A (zh) 车联网中的空间事件的查询方法和优化查询器
CN115112122A (zh) 基于多传感器融合的定位方法、系统、设备及存储介质
WO2023246342A1 (zh) 一种Freespace边缘点的处理方法以及装置
CN113762035B (zh) 一种车道监测方法、装置、电子设备
CN114724414B (zh) 城市空中交通分担率的确定方法、装置、电子设备及介质
CN110614631A (zh) 确定目标点的方法、装置、电子设备及计算机可读介质
CN114676175B (zh) 一种道路颠簸点检测方法、装置、设备及介质
CN115986921A (zh) 配电网的巡检方法、装置、计算机设备和存储介质
CN112069899A (zh) 一种路肩检测方法、装置及存储介质
Duman et al. YOLOv5-based vehicle objects detection using UAV images
CN112598668A (zh) 基于三维图像的缺陷识别方法、装置及电子设备

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: 23825992

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: 23825992

Country of ref document: EP

Kind code of ref document: A1