WO2022083166A1 - 一种卡口数据缺失下的车辆行车轨迹重建方法及系统 - Google Patents

一种卡口数据缺失下的车辆行车轨迹重建方法及系统 Download PDF

Info

Publication number
WO2022083166A1
WO2022083166A1 PCT/CN2021/103201 CN2021103201W WO2022083166A1 WO 2022083166 A1 WO2022083166 A1 WO 2022083166A1 CN 2021103201 W CN2021103201 W CN 2021103201W WO 2022083166 A1 WO2022083166 A1 WO 2022083166A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
trajectory
bayonet
driving trajectory
data
Prior art date
Application number
PCT/CN2021/103201
Other languages
English (en)
French (fr)
Inventor
郭亚娟
Original Assignee
山东交通学院
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 山东交通学院 filed Critical 山东交通学院
Publication of WO2022083166A1 publication Critical patent/WO2022083166A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/029—Location-based management or tracking services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]

Definitions

  • the invention relates to the technical field of traffic information, and in particular, to a method and system for reconstructing a driving trajectory of a vehicle in the absence of bayonet data.
  • Intelligent transportation system is one of the important means to solve the complex traffic problems of urban road network.
  • the intelligence, automation and information processing capabilities of various traffic detection equipment are also constantly improving.
  • the urban video surveillance system represented by the bayonet equipment can better identify and match the vehicle license plate information, and realize the tracking of the vehicle's driving trajectory, but it still faces the loss of track points and trajectories caused by the insufficient space coverage of the bayonet equipment.
  • the chain is not complete, etc.
  • Accurate and complete vehicle trajectory data can provide a wealth of road network traffic operation status information, reproduce complex road traffic operation scenarios, and provide road users with high-quality travel services. Therefore, how to use the missing bayonet data to reconstruct vehicle driving trajectories becomes intelligent transportation.
  • a vehicle trajectory tracking method based on electronic police data.
  • the comparison between the time difference between adjacent detection points of the vehicle and the time threshold Build the information table of the upstream and downstream sections of the vehicle travel, and then obtain the approximate trajectory data of each vehicle;
  • some researchers have provided a vehicle trajectory reconstruction method, which constructs a road network topology map based on the road network data, and uses the starting and ending points of the vehicle trajectory to select the trajectory.
  • Video monitoring points within the range combined with community discovery, shortest path and other algorithms to quickly reconstruct vehicle trajectories;
  • some researchers have provided a path extraction method based on vehicle trajectory data, which is determined by GPS data screening, trajectory segmentation and key node clustering.
  • the rough backbone road network is combined with the open source road network and the least squares support vector machine (LS-SVM) algorithm to fit the high-precision road centerline.
  • LS-SVM least squares support vector machine
  • the present disclosure proposes a method and system for reconstructing a vehicle's driving trajectory under the condition of missing bayonet data. After splitting to form the undetermined path segment, the undetermined path segment is analyzed by the particle swarm optimization algorithm, and the feasible path of the vehicle driving trajectory is determined. , which realizes the reconstruction of the vehicle's driving trajectory when the bayonet data is missing.
  • a vehicle trajectory reconstruction method with missing bayonet data including:
  • the particle swarm optimization algorithm is used to analyze the to-be-determined path segment to determine the feasible path of the vehicle's driving trajectory
  • a vehicle driving trajectory reconstruction system with missing bayonet data including:
  • the bayonet data acquisition module is used to obtain bayonet data
  • the vehicle initial data generation module is used to generate the initial vehicle trajectory according to the bayonet data
  • the vehicle initial trajectory division module is used to split the trajectory of the vehicle initial trajectory to generate multiple undetermined path segments
  • the feasible path generation module of the vehicle driving trajectory is used to analyze the to-be-determined path segment by using the particle swarm optimization algorithm to determine the feasible path of the vehicle driving trajectory;
  • the vehicle driving trajectory generation module is used to select the optimal path among the feasible paths of the vehicle driving trajectory by using the network analysis hierarchy process, which is the final vehicle driving trajectory.
  • an electronic device including a memory, a processor, and computer instructions stored in the memory and executed on the processor, the computer instructions being executed by the processor to complete a kind of checkpoint under the condition of missing bayonet data.
  • the steps are described in the method for reconstructing the driving track of a vehicle.
  • a computer-readable storage medium for storing computer instructions, and when the computer instructions are executed by a processor, the steps described in a method for reconstructing a driving trajectory of a vehicle with missing bayonet data are completed.
  • the vehicle driving trajectory reconstruction method proposed in the present disclosure uses the existing bayonet data to generate the initial vehicle trajectory when the bayonet data is missing, and after splitting the initial vehicle trajectory to form undetermined path segments, the particle swarm optimization is carried out.
  • the algorithm analyzes the to-be-determined path segment, determines the feasible path of the vehicle's driving trajectory, and finally filters out the optimal path among the feasible paths as the final vehicle's driving trajectory through the network analysis hierarchy process. Reconstruction of driving trajectories.
  • the present disclosure first determines the feasible path of the vehicle driving trajectory through the particle swarm optimization algorithm, and then optimally selects the feasible path through the network analysis hierarchy process, avoiding the one-sidedness of a single path decision-making factor. , which comprehensively considers the influence of factors such as the characteristics of the path itself and the driver's driving preference, which can effectively determine the optimal vehicle travel trajectory and improve the efficiency and accuracy of missing trajectory reconstruction.
  • Embodiment 1 is a flowchart of the method disclosed in Embodiment 1 of the present disclosure
  • FIG. 2 is a flowchart of determining a feasible path of a vehicle driving trajectory by using a particle swarm optimization algorithm according to Embodiment 1 of the present disclosure.
  • orientation or positional relationship is based on the orientation or positional relationship shown in the drawings, and is only a relational word determined for the convenience of describing the structural relationship of each component or element of the present disclosure, and does not specifically refer to any component or element in the present disclosure, and should not be construed as a reference to the present disclosure. public restrictions.
  • a method for reconstructing a driving trajectory of a vehicle with missing bayonet data including:
  • the particle swarm optimization algorithm is used to analyze the to-be-determined path segment to determine the feasible path of the vehicle's driving trajectory
  • the bayonet data is first preprocessed to filter out abnormal data, and then the initial vehicle trajectory is generated by using the bayonet data after filtering out the abnormal data.
  • the bayonet data includes the survey points of the bayonet device, the vehicle data identified by the bayonet device, the frequency that the vehicle is captured by the bayonet device, and the time when the bayonet device captures the vehicle.
  • the outlier identification method based on the quartile range is used to filter out the abnormal data with high and low frequency in the bayonet data.
  • the specific process of splitting the initial trajectory of the vehicle to obtain multiple undetermined path segments is as follows: according to the driving habits, the consistency of the travel time distance, the road network between the adjacent checkpoint detection points of each vehicle is reachable, and After the split, the trajectory segment satisfies the one-time reachable network.
  • the initial trajectory of the vehicle is split to obtain the trajectory segment, and all the inspection points of the bayonet equipment in each trajectory segment are equivalent to a vehicle must pass point.
  • the points are divided into a plurality of undetermined path segments.
  • the undetermined path segments are spliced into a sequence of path segments by encoding to form a particle;
  • each feasible path segment is randomly combined to form an initial particle population, and the initial particle fitness is calculated;
  • the particles corresponding to the fitness of the first K optimal particles are selected to be the feasible paths of the vehicle's driving trajectory.
  • the path is evaluated, and the optimal path among the feasible paths of the vehicle driving trajectory is determined, which is the final vehicle driving trajectory.
  • the bayonet data includes the survey points of bayonet equipment, vehicle data identified by bayonet equipment, the frequency of vehicles captured by bayonet equipment, and the The mouth device captures the time of the vehicle.
  • the GPS positioning information in the survey points and vehicle identification data of the urban road network bayonet equipment is converted into the geographic information system coordinate system GCJ02 formulated by the National Bureau of Surveying and Mapping, so as to better realize the visualization of the positioning information on the electronic map.
  • Q 1 is the 25th percentile and Q 3 is the 75th percentile.
  • the corresponding initial vehicle trajectory is extracted according to the time series captured by the bayonet device for each vehicle.
  • the particle swarm optimization algorithm is used to analyze the to-be-determined path segment to determine the feasible path of the vehicle's driving trajectory.
  • the specific process is shown in Figure 2.
  • S51 Encode the to-be-determined path segment, and splicing the to-be-determined path segment into a sequence of path segments by direct encoding to form a particle;
  • E p is the set of road segments included in the particle p
  • t ij is the free flow travel time of the road segment (i, j)
  • Q ij is the traffic volume of the road segment (i, j)
  • C ij is the road segment (i, j)
  • ⁇ and ⁇ are impedance parameters
  • R ij is the connection coefficient between adjacent nodes i and j.
  • S53 Calculate the particle fitness through the evaluation function, and divide m subgroups according to the order of particle fitness, that is, put the first particle p 1 into the first subgroup, and the second particle p 2 into the second subgroup, ..., the mth particle p m is put into the mth subgroup, the m+1th particle p m+1 is put into the 1st subgroup, ..., the 2mth particle p 2m is put into the mth subgroup, ..., in turn Proceed until all particles are divided.
  • S55 Merge the iteratively updated m subgroups with the particle population of the previous generation, sort and deduplicate the particles according to the latest fitness of the particles, to form a new particle population.
  • S56 Determine whether the maximum number of iterations is satisfied, and if so, output the particles corresponding to the fitness of the top k optimal particles, that is, the top k optimal path, which is a feasible path of the vehicle driving trajectory, otherwise, return to S53 for recalculation.
  • the ANP method is used to comprehensively evaluate the K optimal path (feasible path of the vehicle driving trajectory) to determine the optimal vehicle driving trajectory, which specifically includes the following contents:
  • S61 Construct an ANP double-layer structure that affects the driver's path decision, in which the control layer is each criterion, including the convenience of the path A, the driver's preference for the path B, the economy and safety of the path C, and the environment and other factors D ;
  • the network layer is the network structure under each criterion, including the length of the path A1, the traffic status of the path A2, the driver's familiarity with the path B1, the number of signal lights on the path B2, the traffic guidance information of the path B3, and the toll of the path.
  • C1 the fuel cost of the path C2, the safety attributes of the path (such as linearity, gradient, etc.) C3, the road environment D1 of the path, and the meteorological environment D2 of the path.
  • S63 Calculate the ANP supermatrix according to the pairwise judgment matrix to determine the stable weights of the indicators of the control layer and the network layer.
  • the present embodiment discloses a method for reconstructing a vehicle's driving trajectory in the absence of bayonet data, which makes full use of urban traffic bayonet data detected by nearly full samples, and analyzes the frequency of vehicle capture by bayonet equipment, initial trajectory extraction, and trajectory segments. After preprocessing such as splitting, a reconstruction method based on the PSO algorithm for the feasible path of the vehicle's driving trajectory and a vehicle optimal path decision method based on the ANP algorithm are proposed. Based on the bayonet data in the urban traffic system, the bayonet data is used to capture the vehicle first.
  • Frequency screening secondly, on the basis of extracting the initial trajectory of the vehicle, the trajectory loss point analysis and trajectory segmentation are carried out, and then the particle swarm optimization PSO algorithm is used to reconstruct the feasible path of the vehicle driving trajectory.
  • the final vehicle driving trajectory realizes the reconstruction of the vehicle driving trajectory in the absence of bayonet data.
  • the PSO algorithm is used to obtain multiple feasible paths of the vehicle's driving trajectory, which significantly improves the efficiency and accuracy of the reconstruction of the vehicle's driving trajectory;
  • the ANP algorithm is used to solve the multi-trajectory decision-making problem of the reconstructed vehicle, which avoids the single path decision-making factor.
  • One-sided considering the influence of factors such as the characteristics of the path itself and the driver's driving preference, it can effectively determine the optimal driving trajectory of the vehicle.
  • the ANP algorithm is used to comprehensively consider a variety of influencing factors to achieve a comprehensive evaluation of the feasible path of the vehicle driving trajectory, and accurately obtain the optimal vehicle driving trajectory path, which is the final vehicle driving trajectory.
  • a vehicle driving trajectory reconstruction system with missing bayonet data including:
  • the bayonet data acquisition module is used to obtain bayonet data
  • the vehicle initial data generation module is used to generate the initial vehicle trajectory according to the bayonet data
  • the vehicle initial trajectory division module is used to split the trajectory of the vehicle initial trajectory to generate multiple undetermined path segments
  • the feasible path generation module of the vehicle driving trajectory is used to analyze the to-be-determined path segment by using the particle swarm optimization algorithm to determine the feasible path of the vehicle driving trajectory;
  • the vehicle driving trajectory generation module is used to select the optimal path among the feasible paths of the vehicle driving trajectory by using the network analysis hierarchy process, which is the final vehicle driving trajectory.
  • an electronic device which includes a memory, a processor, and computer instructions stored in the memory and executed on the processor.
  • the computer instructions are executed by the processor, one of the methods disclosed in Embodiment 1 is completed. The steps described in the method for reconstructing the driving trajectory of a vehicle with missing bayonet data.
  • a computer-readable storage medium for storing computer instructions, and when the computer instructions are executed by a processor, the reconstruction of a vehicle driving track in the absence of bayonet data disclosed in Embodiment 1 is completed. the steps described in the method.
  • the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • computer-usable storage media including, but not limited to, disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions
  • the apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Signal Processing (AREA)
  • Economics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Quality & Reliability (AREA)
  • General Business, Economics & Management (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Tourism & Hospitality (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种卡口数据缺失下的车辆行车轨迹重建方法及系统，包括：获取卡口数据；根据卡口数据生成车辆初始轨迹；对车辆初始轨迹进行轨迹拆分，生成多个待定路径段；采用粒子群优化算法对待定路径段进行分析，确定车辆行车轨迹可行路径；利用网络层次分析法选取车辆行车轨迹可行路径中的最优路径，为最终的车辆行车轨迹。实现了卡口数据缺失时的车辆行车轨迹重建。

Description

一种卡口数据缺失下的车辆行车轨迹重建方法及系统 技术领域
本发明涉及交通信息技术领域，尤其涉及一种卡口数据缺失下的车辆行车轨迹重建方法及系统。
背景技术
本部分的陈述仅仅是提供了与本公开相关的背景技术信息，不必然构成在先技术。
智能交通系统是解决城市路网复杂交通问题的重要手段之一。随着智能交通系统的不断发展，各种交通检测设备的智能化、自动化以及信息处理能力也在不断提高。目前，以卡口设备为代表的城市视频监控系统能够较好识别和匹配车辆牌照信息，实现车辆行车轨迹的跟踪，但仍面临着由卡口设备空间覆盖率不足所导致的轨迹丢点、轨迹链不完整等问题。准确完整的车辆轨迹数据能够提供丰富的路网交通运行状态信息，再现复杂的道路交通运行场景，为道路使用者提供优质的出行服务，故如何利用缺失的卡口数据重建车辆行车轨迹成为智能交通领域研究的热点和重点问题之一。
通过检索发现，有研究人员提供了一种基于电子警察数据的车辆轨迹跟踪方法，在对电子警察过车数据进行预处理的基础上，通过车辆相邻检测点之间的时间差与时间阈值的比较构建车辆出行的上下游路段信息表，进而获取每辆车的大概轨迹数据；有研究人员提供了一种车辆轨迹重建方法，根据路网数据构建路网拓扑图，利用车辆轨迹的起讫点选取轨迹范围内的视频监测点，结合 社团发现、最短路径等算法快速重构车辆轨迹；有研究人员提供了一种基于车辆轨迹数据的路径提取方法，通过GPS数据筛选、轨迹分割以及关键节点聚类确定粗糙的骨干路网，结合开源路网及最小二乘支持向量机(LS-SVM)算法拟合出高精度的道路中心线。
上述方案均是利用卡口视频数据或车辆GPS定位数据实现车辆行车轨迹的重建，但是这些方案均没有针对性地解决由卡口设备缺失或故障出现卡口数据缺失所导致的轨迹断链问题，同时，单一的车辆轨迹影响因素(如行驶路径最短)无法获取实时准确的车辆出行轨迹信息。
发明内容
本公开为了解决上述问题，提出了一种卡口数据缺失下的车辆行车轨迹重建方法及系统，在卡口数据缺失的情况下，利用已有的卡口数据生成车辆初始轨迹，对车辆初始轨迹进行拆分形成待定路径段后，通过粒子群优化算法对待定路径段进行分析，确定了车辆行车轨迹可行路径，最后通过网络层次分析法筛选出可行路径中的最优路径为最终的车辆行车轨迹，实现了在卡口数据缺失的情况下对车辆行车轨迹的重建。
为实现上述目的，本公开采用如下技术方案：
第一方面，提出了一种卡口数据缺失下的车辆行车轨迹重建方法，包括：
获取卡口数据；
根据卡口数据生成车辆初始轨迹；
对车辆初始轨迹进行轨迹拆分，生成多个待定路径段；
采用粒子群优化算法对待定路径段进行分析，确定车辆行车轨迹可行路径；
利用网络层次分析法选取车辆行车轨迹可行路径中的最优路径，为最终的 车辆行车轨迹。
第二方面，提出了一种卡口数据缺失下的车辆行车轨迹重建系统，包括：
卡口数据采集模块，用于获取卡口数据；
车辆初始数据生成模块，用于根据卡口数据生成车辆初始轨迹；
车辆初始轨迹划分模块，用于对车辆初始轨迹进行轨迹拆分，生成多个待定路径段；
车辆行车轨迹可行路径生成模块，用于采用粒子群优化算法对待定路径段进行分析，确定车辆行车轨迹可行路径；
车辆行车轨迹生成模块，用于利用网络层次分析法选取车辆行车轨迹可行路径中的最优路径，为最终的车辆行车轨迹。
第三方面，提出了一种电子设备，包括存储器和处理器以及存储在存储器上并在处理器上运行的计算机指令，所述计算机指令被处理器运行时，完成一种卡口数据缺失下的车辆行车轨迹重建方法所述的步骤。
第四方面，提出了一种计算机可读存储介质，用于存储计算机指令，所述计算机指令被处理器执行时，完成一种卡口数据缺失下的车辆行车轨迹重建方法所述的步骤。
与现有技术相比，本公开的有益效果为：
1、本公开提出的车辆行车轨迹重建方法，在卡口数据缺失的情况下，利用已有的卡口数据生成车辆初始轨迹，对车辆初始轨迹进行拆分形成待定路径段后，通过粒子群优化算法对待定路径段进行分析，确定了车辆行车轨迹可行路径，最后通过网络层次分析法筛选出可行路径中的最优路径为最终的车辆行车轨迹，实现了在卡口数据缺失的情况下对车辆行车轨迹的重建。
2、本公开在确定最终的车辆行车轨迹时，首先通过粒子群优化算法确定了车辆行车轨迹可行路径，后通过网络层次分析法对可行路径进行了最优选取，避免了单一路径决策因素的片面性，综合考虑了路径自身特性以及驾驶员行驶偏好等因素的影响，能够有效确定最优的车辆出行轨迹，提高了缺失轨迹重建的效率和准确性。
本发明附加方面的优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本发明的实践了解到。
附图说明
构成本申请的一部分的说明书附图用来提供对本申请的进一步理解，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的不当限定。
图1为本公开实施例1公开方法的流程图；
图2为本公开实施例1采用粒子群优化算法确定车辆行车轨迹可行路径的流程图。
具体实施方式：
下面结合附图与实施例对本公开作进一步说明。
应该指出，以下详细说明都是例示性的，旨在对本申请提供进一步的说明。除非另有指明，本文使用的所有技术和科学术语具有与本申请所属技术领域的普通技术人员通常理解的相同含义。
需要注意的是，这里所使用的术语仅是为了描述具体实施方式，而非意图限制根据本申请的示例性实施方式。如在这里所使用的，除非上下文另外明确指出，否则单数形式也意图包括复数形式，此外，还应当理解的是，当在本说明书中使用术语“包含”和/或“包括”时，其指明存在特征、步骤、操作、器件、组件和/或它们的组合。
在本公开中，术语如“上”、“下”、“左”、“右”、“前”、“后”、“竖直”、“水平”、“侧”、“底”等指示的方位或位置关系为基于附图所示的方位或位置关系，只是为了便于叙述本公开各部件或元件结构关系而确定的关系词，并非特指本公开中任一部件或元件，不能理解为对本公开的限制。
本公开中，术语如“固接”、“相连”、“连接”等应做广义理解，表示可以是固定连接，也可以是一体地连接或可拆卸连接；可以是直接相连，也可以通过中间媒介间接相连。对于本领域的相关科研或技术人员，可以根据具体情况确定上述术语在本公开中的具体含义，不能理解为对本公开的限制。
实施例1
在该实施例中，公开了一种卡口数据缺失下的车辆行车轨迹重建方法，包括：
获取卡口数据；
根据卡口数据生成车辆初始轨迹；
对车辆初始轨迹进行轨迹拆分，生成多个待定路径段；
采用粒子群优化算法对待定路径段进行分析，确定车辆行车轨迹可行路径；
利用网络层次分析法选取车辆行车轨迹可行路径中的最优路径，为最终的车辆行车轨迹。
进一步的，依据卡口数据生成车辆初始轨迹时，首先对卡口数据进行预处理，筛除异常数据，再通过筛除异常数据后的卡口数据生成车辆初始轨迹。
进一步的，卡口数据包括卡口设备调查点位，卡口设备识别的车辆数据，车辆被卡口设备捕捉的频次，卡口设备捕捉车辆的时间。
进一步的，根据车辆被卡口设备捕捉的频次，采用基于四分位极差的离群 点识别方法筛除卡口数据中频次过高和过低的异常数据。
进一步的，对车辆初始轨迹进行轨迹拆分，获得多个待定路径段的具体过程为：依据驾驶习惯，出行时距一致性，每辆车相邻卡口检测点间有路网可达，及拆分后轨迹段满足一次可达网络对车辆初始轨迹进行拆分获取轨迹段，将每段轨迹段中的所有卡口设备调查点位等效为一个车辆必经点，车辆初始轨迹经车辆必经点划分为多个待定路径段。
进一步的，采用粒子群优化算法确定车辆行车轨迹可行路径的具体过程为：
通过编码的方式将待定路径段拼接为路径段序列，形成一个粒子；
任意两个车辆必经点间存在多条可行路径段，将各个可行路径段进行随机组合形成初始粒子种群，计算初始粒子适应度；
通过粒子状态对粒子种群进行迭代更新，并计算更新后的粒子适应度；
选取前K优粒子适应度对应粒子，为车辆行车轨迹可行路径。
进一步的，利用网络层次分析法确定车辆行车轨迹的具体过程为：
选取路径的便利性、驾驶员对于路径的偏好性、路径的经济与安全性以及环境与其他因素，构建影响驾驶员路径决策的二级指标体系，并采用网络层次分析法ANP对车辆行车轨迹可行路径进行评估，确定车辆行车轨迹可行路径中的最优路径，为最终的车辆行车轨迹。
结合图1对一种卡口数据缺失下的车辆行车轨迹重建方法进行说明。
(一)获取卡口数据，并对数据涉及的坐标系进行转换，其中，卡口数据包括，卡口设备调查点位，卡口设备识别的车辆数据，车辆被卡口设备捕捉的频次，卡口设备捕捉车辆的时间。
将城市路网卡口设备调查点位及车辆识别数据中的GPS定位信息转换为国家测绘局制订的地理信息系统坐标体系GCJ02，以更好实现定位信息在电子地图上的可视化。
(二)根据车辆被卡口设备捕捉的频次，删除卡口数据中频次过高和过低的异常数据。
S21:分析一天内所有车辆被卡口设备捕捉的频次，采用基于四分位极差的离群点识别方法筛除频次过高和过低的异常数据，其中四分位极差IQR的计算公式如下：
IQR＝Q 3-Q 1
式中，Q 1是第25个百分位数，Q 3是第75个百分位数。
S22:当车辆一天的捕捉频次小于(Q 1-1.5×IQR)时，则该车辆的捕捉频次过低；当车辆一天的捕捉频次大于(Q 3+1.5×IQR)时，则该车辆的捕捉频次过高，卡口设备识别的上述两种异常情况下的车辆数据均被视为异常数据进行筛除。
(三)通过筛除异常数据后的卡口数据生成车辆初始轨迹。
针对筛选出的车辆捕捉频次合理的卡口数据，依照每辆车被卡口设备捕捉的时间序列提取相应的车辆初始轨迹。
(四)对车辆初始轨迹进行轨迹拆分，生成多个待定路径段。
通过分析发现车牌遮挡、光照强度不足、雨雪雾天气以及卡口设备的缺失与故障均会导致车辆轨迹丢点问题，在对丢点进行成因分析的基础上，通过以下规则对车辆初始轨迹进行拆分获取轨迹段：(1)出行时距的一致性约束，即车辆出行距离与时间成正比例关系；(2)每辆车的相邻卡口检测点之间具有路 网可达性；(3)驾驶习惯约束，即驾驶员不会频繁转弯、掉头和绕行；(4)拆分后的轨迹段需要满足一次可达性网络。
根据车辆经过的有效卡口设备调查点位确定车辆行驶轨迹的必经点，无论拆分后的轨迹段是包含多个连续的有效卡口设备调查点位还是单独一个有效卡口设备调查点位，均等效为一个车辆必经点，并以该车辆必经点为节点将车辆初始轨迹划分为多个待定路径段。
(五)采用粒子群优化算法对待定路径段进行分析，确定车辆行车轨迹可行路径，具体过程如图2所示。
S51：对待定路径段进行编码，通过直接编码方式将待定路径段拼接为路径段序列，形成一个粒子；
S52：任意两个车辆必经点之间存在多条不同长度的可行路径段，将各个可行路径段进行随机组合形成初始粒子种群。种群内任一粒子p的评价函数Fun p为所有拼接可行路径段的阻抗之和，具体计算如下:
Figure PCTCN2021103201-appb-000001
Figure PCTCN2021103201-appb-000002
式中，E p为粒子p包含的路段集合，t ij为路段(i,j)的自由流行程时间，Q ij为路段(i,j)的交通量，C ij为路段(i,j)的通行能力，α,β为阻抗参数，R ij为相邻节点i与j的连接系数。
S53：通过评价函数计算粒子适应度，根据粒子适应度的优劣顺序划分m个子群，即将第1个粒子p 1放入第1个子群，第2个粒子p 2放入第2个子群，…，第m个粒子p m放入第m个子群，第m+1个粒子p m+1放入第1个子群，…，第 2m个粒子p 2m放入第m个子群，…，依次进行直到所有粒子均被划分。
S54：根据粒子状态更新公式实现各子群中粒子的局部搜索，即：
Figure PCTCN2021103201-appb-000003
式中，
Figure PCTCN2021103201-appb-000004
为粒子p的历史最优解，
Figure PCTCN2021103201-appb-000005
为粒子p所在子群m的最优解，x p为随机生成的粒子状态，β 1与β 2为粒子学习系数，β 3为粒子运动系数。
S55：将迭代更新后的m个子群与上一代粒子种群进行合并，根据粒子最新适应度进行排序与去重，形成新的粒子种群。
S56：判断是否满足最大迭代次数，若是则输出前k优粒子适应度对应粒子，即前k优路径，为车辆行车轨迹可行路径，反之则返回S53重新进行计算。
(六)选取路径的便利性、驾驶员对于路径的偏好性、路径的经济与安全性以及环境与其他因素，构建影响驾驶员路径决策的二级指标体系，并采用网络层次分析法ANP对车辆行车轨迹可行路径进行评估，确定车辆行车轨迹可行路径中的最优路径，为最终的车辆行车轨迹。
采用ANP方法对K优路径(车辆行车轨迹可行路径)进行综合评估，确定最佳的车辆行车轨迹，具体包含以下内容：
S61：构建影响驾驶员路径决策的ANP双层结构，其中控制层为各个准则，包含路径的便利性A、驾驶员对于路径的偏好性B、路径的经济与安全性C以及环境与其他因素D；网络层则为各个准则下的网络结构，包括路径的长度A1、路径的交通状态A2、驾驶员对路径的熟悉度B1、路径的信号灯数量B2、路径的交通诱导信息B3、路径的通行费用C1、路径的燃油费用C2、路径的安全属性(如线性、坡度等)C3、路径的道路环境D1、路径的气象环境D2。
S62：采用专家调查法和九分法标定网络层中两两因素之间的相对重要性，获取相应的两两判断矩阵。
S63：根据两两判断矩阵计算ANP超矩阵，以确定控制层和网络层指标的稳定权重。
S64：通过计算网络层中各个指标值与相应权重的乘积之和得到K优路径的综合评估值，取最优路径为最终的完整的车辆行车轨迹。
本实施例公开的一种卡口数据缺失下的车辆行车轨迹重建方法，充分利用了近乎全样本检测的城市交通卡口数据，通过对车辆被卡口设备捕捉频次分析、初始轨迹提取以及轨迹段拆分等预处理，提出基于PSO算法的车辆行车轨迹可行路径的重建方法以及基于ANP算法的车辆最优路径决策方法，以城市交通系统中卡口数据为基础，首先采用卡口数据进行车辆捕捉频次的筛查，其次在提取车辆初始轨迹的基础上进行轨迹丢点分析和轨迹分割，进而采用粒子群优化PSO算法重构车辆行车轨迹可行路径，最后结合ANP算法评估K条优化路径，确定了最终的车辆行车轨迹，实现了卡口数据缺失下的车辆行车轨迹的重建。
采用PSO算法获取了多条车辆行车轨迹可行路径，显著提高了车辆行车轨迹重建的效率和准确性；突破性地采用ANP算法解决重构后的车辆多轨迹决策问题，避免了单一路径决策因素的片面性，综合考虑了路径自身特性以及驾驶员行驶偏好等因素的影响，能够有效确定车辆最佳行车轨迹。具有以下优点：
(1)在对城市卡口数据进行预处理的基础上，采用粒子群优化算法获取了多条车辆行车轨迹可行路径，显著提高了轨迹重建的效率和准确性。
(2)突破了单一路径决策因素的局限性，采用ANP算法综合考虑多种影响因素以实现车辆行车轨迹可行路径的综合评估，精准获取最佳的车辆行车轨 迹路径，为最终的车辆行车轨迹。
(3)仅利用城市路网的部分卡口数据实现车辆行车轨迹重建，较好解决了由卡口设备缺失或故障所导致的车辆轨迹断链问题，具有较高的应用价值。
(4)能够有效利用卡口原始数据中的车辆稀疏轨迹，实现车辆完整出行链的提取，为评估城市交通出行需求和交通系统运行状态提供有力的数据支持。
实施例2
在该实施例中，公开了一种卡口数据缺失下的车辆行车轨迹重建系统，包括：
卡口数据采集模块，用于获取卡口数据；
车辆初始数据生成模块，用于根据卡口数据生成车辆初始轨迹；
车辆初始轨迹划分模块，用于对车辆初始轨迹进行轨迹拆分，生成多个待定路径段；
车辆行车轨迹可行路径生成模块，用于采用粒子群优化算法对待定路径段进行分析，确定车辆行车轨迹可行路径；
车辆行车轨迹生成模块，用于利用网络层次分析法选取车辆行车轨迹可行路径中的最优路径，为最终的车辆行车轨迹。
实施例3
在该实施例中，公开了一种电子设备，包括存储器和处理器以及存储在存储器上并在处理器上运行的计算机指令，所述计算机指令被处理器运行时，完成实施例1公开的一种卡口数据缺失下的车辆行车轨迹重建方法所述的步骤。
实施例4
在该实施例中，公开了一种计算机可读存储介质，用于存储计算机指令， 所述计算机指令被处理器执行时，完成实施例1公开的一种卡口数据缺失下的车辆行车轨迹重建方法所述的步骤。
以上仅为本申请的优选实施例而已，并不用于限制本申请，对于本领域的技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使 得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
最后应当说明的是：以上实施例仅用以说明本发明的技术方案而非对其限制，尽管参照上述实施例对本发明进行了详细的说明，所属领域的普通技术人员应当理解：依然可以对本发明的具体实施方式进行修改或者等同替换，而未脱离本发明精神和范围的任何修改或者等同替换，其均应涵盖在本发明的权利要求保护范围之内。

Claims (10)

  1. 一种卡口数据缺失下的车辆行车轨迹重建方法，其特征在于，包括：
    获取卡口数据；
    根据卡口数据生成车辆初始轨迹；
    对车辆初始轨迹进行轨迹拆分，生成多个待定路径段；
    采用粒子群优化算法对待定路径段进行分析，确定车辆行车轨迹可行路径；
    利用网络层次分析法选取车辆行车轨迹可行路径中的最优路径，为最终的车辆行车轨迹。
  2. 如权利要求1所述的一种卡口数据缺失下的车辆行车轨迹重建方法，其特征在于，卡口数据包括卡口设备调查点位，卡口设备识别的车辆数据，车辆被卡口设备捕捉的频次，卡口设备捕捉车辆的时间。
  3. 如权利要求1所述的一种卡口数据缺失下的车辆行车轨迹重建方法，其特征在于，依据卡口数据生成车辆初始轨迹时，首先对卡口数据进行预处理，筛除异常数据，再通过筛除异常数据后的卡口数据生成车辆初始轨迹。
  4. 如权利要求3所述的一种卡口数据缺失下的车辆行车轨迹重建方法，其特征在于，采用基于四分位极差的离群点识别方法筛除卡口数据中频次过高和过低的异常数据。
  5. 如权利要求1所述的一种卡口数据缺失下的车辆行车轨迹重建方法，其特征在于，对车辆初始轨迹进行轨迹拆分，获得多个待定路径段的具体过程为：依据驾驶习惯，出行时距一致性，每辆车相邻卡口检测点间有路网可达，及拆分后轨迹段满足一次可达网络对车辆初始轨迹进行拆分获取轨迹段，将每段轨迹段中的所有卡口设备调查点位等效为一个车辆必经点，车辆初始轨迹经车辆必经点划分为多个待定路径段。
  6. 如权利要求1所述的一种卡口数据缺失下的车辆行车轨迹重建方法，其特征在于，采用粒子群优化算法确定车辆行车轨迹可行路径的具体过程为：
    通过编码的方式将待定路径段拼接为路径段序列，形成一个粒子；
    任意两个车辆必经点间存在多条可行路径段，将各个可行路径段进行随机组合形成初始粒子种群，计算初始粒子适应度；
    通过粒子状态对粒子种群进行迭代更新，并计算更新后的粒子适应度；
    选取前K优粒子适应度对应粒子，为车辆行车轨迹可行路径。
  7. 如权利要求1所述的一种卡口数据缺失下的车辆行车轨迹重建方法，其特征在于，利用网络层次分析法确定车辆行车轨迹的具体过程为：
    选取路径的便利性、驾驶员对于路径的偏好性、路径的经济与安全性以及环境与其他因素，构建影响驾驶员路径决策的二级指标体系，并采用网络层次分析法ANP对车辆行车轨迹可行路径进行评估，确定车辆行车轨迹可行路径中的最优路径，为最终的车辆行车轨迹。
  8. 一种卡口数据缺失下的车辆行车轨迹重建系统，其特征在于，包括：
    卡口数据采集模块，用于获取卡口数据；
    车辆初始数据生成模块，用于根据卡口数据生成车辆初始轨迹；
    车辆初始轨迹划分模块，用于对车辆初始轨迹进行轨迹拆分，生成多个待定路径段；
    车辆行车轨迹可行路径生成模块，用于采用粒子群优化算法对待定路径段进行分析，确定车辆行车轨迹可行路径；
    车辆行车轨迹生成模块，用于利用网络层次分析法选取车辆行车轨迹可行路径中的最优路径，为最终的车辆行车轨迹。
  9. 一种电子设备，其特征在于，包括存储器和处理器以及存储在存储器上并在处理器上运行的计算机指令，所述计算机指令被处理器运行时，完成权利要求1-7任一项所述的一种卡口数据缺失下的车辆行车轨迹重建方法的步骤。
  10. 一种计算机可读存储介质，其特征在于，用于存储计算机指令，所述计算机指令被处理器执行时，完成权利要求1-7任一项所述的一种卡口数据缺失下的车辆行车轨迹重建方法的步骤。
PCT/CN2021/103201 2020-10-19 2021-06-29 一种卡口数据缺失下的车辆行车轨迹重建方法及系统 WO2022083166A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011116692.8A CN112215427B (zh) 2020-10-19 2020-10-19 一种卡口数据缺失下的车辆行车轨迹重建方法及系统
CN202011116692.8 2020-10-19

Publications (1)

Publication Number Publication Date
WO2022083166A1 true WO2022083166A1 (zh) 2022-04-28

Family

ID=74055736

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/103201 WO2022083166A1 (zh) 2020-10-19 2021-06-29 一种卡口数据缺失下的车辆行车轨迹重建方法及系统

Country Status (2)

Country Link
CN (1) CN112215427B (zh)
WO (1) WO2022083166A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115440037A (zh) * 2022-08-30 2022-12-06 阿波罗智联(北京)科技有限公司 交通流量数据采集方法、装置、电子设备及存储介质
CN115457777A (zh) * 2022-09-06 2022-12-09 北京商海文天科技发展有限公司 一种特定车辆溯源分析方法
CN115512543A (zh) * 2022-09-21 2022-12-23 浙江大学 一种基于深度逆向强化学习的车辆路径链重构方法
CN115936561A (zh) * 2022-11-18 2023-04-07 广州云达供应链管理有限公司 一种物流车轨迹运行异常监测方法
CN117556157A (zh) * 2024-01-10 2024-02-13 每日互动股份有限公司 一种卡口位置的定位方法、装置、介质及设备

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112215427B (zh) * 2020-10-19 2022-12-23 山东交通学院 一种卡口数据缺失下的车辆行车轨迹重建方法及系统
CN115206095B (zh) * 2022-06-28 2024-05-14 公安部交通管理科学研究所 一种卡口过车轨迹数据重构方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106023589A (zh) * 2016-06-16 2016-10-12 北京航空航天大学 一种基于卡口数据的车辆轨迹重构方法
US20190257664A1 (en) * 2018-02-20 2019-08-22 Autoliv Asp, Inc. System and method for generating a target path for a vehicle
CN110276950A (zh) * 2019-06-24 2019-09-24 华南理工大学 一种基于卡口视频数据的城市交通出行链重构方法
CN110928297A (zh) * 2019-10-28 2020-03-27 中南大学 基于多目标动态粒子群优化的智能公交车辆路径规划方法
CN112215427A (zh) * 2020-10-19 2021-01-12 山东交通学院 一种卡口数据缺失下的车辆行车轨迹重建方法及系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI425454B (zh) * 2010-12-28 2014-02-01 Ind Tech Res Inst 行車路徑重建方法、系統及電腦程式產品
CN105429877B (zh) * 2015-11-10 2018-08-10 中山大学 一种基于粒子群优化的路径寻优方法
CN109584553B (zh) * 2018-11-29 2020-09-22 浙江海康智联科技有限公司 一种基于时空信息的路段关联度缺失补全方法
CN111243277B (zh) * 2020-03-09 2021-08-20 山东大学 基于车牌识别数据的通勤车辆时空轨迹重构方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106023589A (zh) * 2016-06-16 2016-10-12 北京航空航天大学 一种基于卡口数据的车辆轨迹重构方法
US20190257664A1 (en) * 2018-02-20 2019-08-22 Autoliv Asp, Inc. System and method for generating a target path for a vehicle
CN110276950A (zh) * 2019-06-24 2019-09-24 华南理工大学 一种基于卡口视频数据的城市交通出行链重构方法
CN110928297A (zh) * 2019-10-28 2020-03-27 中南大学 基于多目标动态粒子群优化的智能公交车辆路径规划方法
CN112215427A (zh) * 2020-10-19 2021-01-12 山东交通学院 一种卡口数据缺失下的车辆行车轨迹重建方法及系统

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115440037A (zh) * 2022-08-30 2022-12-06 阿波罗智联(北京)科技有限公司 交通流量数据采集方法、装置、电子设备及存储介质
CN115440037B (zh) * 2022-08-30 2024-03-26 阿波罗智联(北京)科技有限公司 交通流量数据采集方法、装置、电子设备及存储介质
CN115457777A (zh) * 2022-09-06 2022-12-09 北京商海文天科技发展有限公司 一种特定车辆溯源分析方法
CN115457777B (zh) * 2022-09-06 2023-09-19 北京商海文天科技发展有限公司 一种特定车辆溯源分析方法
CN115512543A (zh) * 2022-09-21 2022-12-23 浙江大学 一种基于深度逆向强化学习的车辆路径链重构方法
CN115512543B (zh) * 2022-09-21 2023-11-28 浙江大学 一种基于深度逆向强化学习的车辆路径链重构方法
CN115936561A (zh) * 2022-11-18 2023-04-07 广州云达供应链管理有限公司 一种物流车轨迹运行异常监测方法
CN117556157A (zh) * 2024-01-10 2024-02-13 每日互动股份有限公司 一种卡口位置的定位方法、装置、介质及设备
CN117556157B (zh) * 2024-01-10 2024-04-05 每日互动股份有限公司 一种卡口位置的定位方法、装置、介质及设备

Also Published As

Publication number Publication date
CN112215427B (zh) 2022-12-23
CN112215427A (zh) 2021-01-12

Similar Documents

Publication Publication Date Title
WO2022083166A1 (zh) 一种卡口数据缺失下的车辆行车轨迹重建方法及系统
Fang et al. FTPG: A fine-grained traffic prediction method with graph attention network using big trace data
CN110298500B (zh) 一种基于出租车数据和城市路网的城市交通轨迹数据集生成方法
CN106323301B (zh) 一种道路情报的获取方法及装置
Huang et al. Survey on vehicle map matching techniques
CN111368095A (zh) 基于水利知识-事理耦合网络的决策支持系统架构与方法
WO2022227303A1 (zh) 信息处理方法、装置、计算机设备及存储介质
CN113963539B (zh) 高速公路交通事故识别方法、模块及系统
CN108765961A (zh) 一种基于改进型限幅平均滤波的浮动车数据处理方法
CN114881356A (zh) 基于粒子群算法优化bp神经网络的城市交通碳排预测方法
CN113868492A (zh) 一种基于电警、卡口数据的可视化od分析方法及应用
CN114819589A (zh) 城市空间高质量利用测定方法、系统、计算机设备及终端
CN114328780A (zh) 基于六角格的智慧城市地理信息更新方法、设备及介质
CN114969263A (zh) 一种城市交通知识图谱的构建方法、构建装置及应用
CN114578848A (zh) 一种基于离散点密度与全局规划的无人机巡检路径规划方法
Tang et al. A novel method for road intersection construction from vehicle trajectory data
US11537767B2 (en) Automated control through a traffic model
CN116824868A (zh) 车辆非法停驻点识别及拥堵预测方法、装置、设备及介质
CN115293585B (zh) 一种基于gis-t搭建路网机动车动态排放清单的方法
Li et al. A simulation approach to detect arterial traffic congestion using cellular data
Wang et al. Grid mapping for road network abstraction and traffic congestion identification based on probe vehicle data
Dao et al. Fusion-3DCNN-max3P: A dynamic system for discovering patterns of predicted congestion
Xu et al. An assistant decision-supporting method for urban transportation planning over big traffic data
Sun et al. Metropolitan congestion performance measures based on mass floating car data
Liu et al. Extracting campus’ road network from walking gps trajectories

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: 21881586

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

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

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 31.08.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21881586

Country of ref document: EP

Kind code of ref document: A1