1.武汉大学资源与环境科学学院,湖北 武汉,430079
2.浙江省测绘科学技术研究院,浙江 杭州,311100
李伯钊,博士,副研究员,主要从事高精地图和众包数据更新等方面的研究。libozhao@whu.edu.cn
蔡忠亮,博士,教授。zlcai@whu.edu.cn
收稿:2025-01-15,
纸质出版:2026-05-05
移动端阅览
李伯钊,廖成,翁宝凤,等.一种基于车载图像的异常轨迹检测与预校正方法[J].武汉大学学报(信息科学版),2026,51(5):1036-1047.
LI Bozhao,LIAO Cheng,WENG Baofeng,et al.A Method for Abnormal Trajectory Detection and Pre-correction Based on Vehicle-Borne Images[J].Geomatics and Information Science of Wuhan University,2026,51(5):1036-1047.
李伯钊,廖成,翁宝凤,等.一种基于车载图像的异常轨迹检测与预校正方法[J].武汉大学学报(信息科学版),2026,51(5):1036-1047. DOI:10.13203/j.whugis20240116
LI Bozhao,LIAO Cheng,WENG Baofeng,et al.A Method for Abnormal Trajectory Detection and Pre-correction Based on Vehicle-Borne Images[J].Geomatics and Information Science of Wuhan University,2026,51(5):1036-1047. DOI:10.13203/j.whugis20240116
众包是实现高精地图实时更新的必要途径,也是高精地图未来的应用形态。低成本众包设备使得轨迹数据普遍存在位置偏移和属性记录异常等情况,进而影响高精地图更新的精度。地图匹配算法可以根据轨迹与道路之间的时空特征将存在位置偏移的轨迹点垂直匹配到车辆行驶的道路上,但是平行于道路方向的较大位置偏移与异常的行驶角度仍会影响轨迹位置校正的精度。鉴于众包数据中的车载图像能够反映车辆的行驶环境与姿态变化,利用计算机视觉技术和隐马尔可夫模型构建了异常轨迹数据的检测与预校正方法,实现了轨迹数据的异常角度校正和整体位置纠偏。以湖北省武汉市为研究区域,以30条带有车载图像的轨迹数据为研究对象,通过综合实验验证了所提方法在提升轨迹数据质量方面的有效性,并进一步与地图匹配算法结合,证明了轨迹质量增强能够有效提升轨迹位置校正的精度,为推动高精地图众包更新的应用落地提供了相应的技术支撑与方法参考。
Objectives
2
Trajectory data obtained from low-cost crowdsourcing devices often suffer from overall positional offsets and abnormal attribute records
failing to meet the accuracy requirements for high-definition map updates. Given that onboard images in crowdsourcing data can capture changes in the driving environment and vehicle orientation
this paper aims to explore correction methods for overall trajectory position offsets and abnormal driving angles based on continuous onboard images. The goal is to provide high-quality trajectory data that enhances the accuracy of subsequent position correction methods.
Methods
2
This study first employs structure-from-motion technology to estimate the pose of the onboard camera
followed by the detection and correction of abnormal driving angles based on the estimated pose information. Next
the study identifies key trajectory points located at intersections and other critical locations using semantic information extracted from onboard images. The corrected angle values and hidden Markov model are then utilized to match these key trajectory points with nodes
enabling the detection and correction of overall trajectory position offsets. Finally
Wuhan city is selected as the research area
and 30 sets of trajectory data accompanied by onboard images are used to validate the effectiveness of the proposed method.
Results
2
The difference between the estimated driving angle and the true driving angle of the vehicle is within 30°
meeting the accuracy requirements of map-matching algorithms. The overall position correction accuracy of the trajectory is within 30 meters
with potential sub-meter accuracy at best. This performance is primarily influenced by the quality of road network data
highlighting that the proposed method relies on high-quality road network data to effectively address abnormal trajectory data with significant positional offsets. The high-quality trajectory data obtained after pre-correction can significantly enhance the accuracy of map-matching algorithms
resolving issues related to incorrect matches and relative positional deviations.
Conclusions
2
The proposed innovative method effectively detects and corrects abnormal driving angles and overall trajectory offsets
significantly enhancing the quality of crowdsourced trajectory data. This improvement further aids in increasing the accuracy of trajectory position correction in map-matching algorithms. Additionally
it offers valuable technical support and methodological guidance for advancing the application of high-definition map crowdsourcing updates.
李德仁 , 洪勇 , 王密 , 等 . 测绘遥感能为智能驾驶做什么? [J]. 测绘学报 , 2021 , 50 ( 11 ): 1421 - 1431 .
LI Deren , HONG Yong , WANG Mi , et al . What Can Surveying and Remote Sensing Do for Intelligent Driving? [J]. Acta Geodaetica et Cartographica Sinica , 2021 , 50 ( 11 ): 1421 - 1431 .
陈会仙 , 章炜 , 杨蒙蒙 , 等 . 面向无人驾驶的高精地图公开应用趋势研究 [J]. 武汉大学学报(信息科学版) , 2024 , 49 ( 4 ): 537 - 545 .
CHEN Huixian , ZHANG Wei , YANG Mengmeng , et al . Open Application Trend of High Definition Map for Unmanned Driving [J]. Geomatics and Information Science of Wuhan University , 2024 , 49 ( 4 ): 537 - 545 .
齐如煜 , 尹章才 , 顾江岩 , 等 . 高精地图的知识图谱表达 [J]. 武汉大学学报(信息科学版) , 2024 , 49 ( 4 ): 651 - 661 .
QI Ruyu , YIN Zhangcai , GU Jiangyan , et al . Knowledge Graph Expression of High Definition Map [J]. Geomatics and Information Science of Wuhan University , 2024 , 49 ( 4 ): 651 - 661 .
高小莉 , 王翰 , 蔡清华 , 等 . 面向高效更新的地理信息要素属性众包获取机制研究 [J]. 测绘标准化 , 2025 , 41 ( 4 ): 43 - 47 .
GAO Xiaoli , WANG Han , CAI Qinghua , et al . Research on Crowdsourcing-Based Acquisition Mechanism for Geographic Information Feature Attributes Towards Efficient Updating [J]. Standardization of Surveying and Mapping , 2025 , 41 ( 4 ): 43 - 47 .
李月华 . 基于自动驾驶众包地图更新技术方法 [J]. 北京测绘 , 2022 , 36 ( 5 ): 629 - 635 .
LI Yuehua . Crowdsourcing Map Update Technology for Autonomous Driving [J]. Beijing Surveying and Mapping , 2022 , 36 ( 5 ): 629 - 635 .
刘建平 , 郑阳 , 郑望晓 . 高精度地图的应用和更新方案 [J]. 汽车实用技术 , 2021 ( 12 ): 27 - 29 .
LIU Jianping , ZHENG Yang , ZHENG Wangxiao . Application and Update Solution of High Definition Map [J]. Automobile Applied Technology , 2021 ( 12 ): 27 - 29 .
赵肄江 , 付金昊 , 刘毅志 , 等 . 融合车辆轨迹和POI特征的多道路属性识别方法 [J]. 测绘地理信息 , 2025 , 50 ( 3 ): 115 - 120 .
ZHAO Yijiang , FU Jinhao , LIU Yizhi , et al . A Method of Multi-road Attribute Recognition Using Vehicle Trajectories and POI Characteristics [J]. Journal of Geomatics , 2025 , 50 ( 3 ): 115 - 120 .
LI B Z , CAI Z L , KANG M J , et al . A Trajectory Restoration Algorithm for Low-Sampling-Rate Floating Car Data and Complex Urban Road Networks [J]. International Journal of Geographical Information Science , 2021 , 35 ( 4 ): 717 - 740 .
REHRL K , GRÖCHENIG S , WIMMER M . Optimization and Evaluation of a High-Performance Open-Source Map-Matching Implementation [C]// Geospatial Technologies for All , Cham : Springer , 2018 .
李必军 , 郭圆 , 周剑 , 等 . 智能驾驶高精地图发展与展望 [J]. 武汉大学学报(信息科学版) , 2024 , 49 ( 4 ): 491 - 505 .
LI Bijun , GUO Yuan , ZHOU Jian , et al . Development and Prospects of High Definition Map for Intelligent Vehicle [J]. Geomatics and Information Science of Wuhan University , 2024 , 49 ( 4 ): 491 - 505 .
王思远 , 王坚 , 刘培源 . 卫星伪距多路径时空建模研究 [J]. 导航定位与授时 , 2021 , 8 ( 2 ): 114 - 119 .
WANG Siyuan , WANG Jian , LIU Peiyuan . Spatiotemporal Modeling of Satellite Pseudo-Distance Multipath [J]. Navigation Positioning and Timing , 2021 , 8 ( 2 ): 114 - 119 .
LI B Z , CAI Z L , KANG M J , et al . An Improved Hidden Markov Model-Based Map Matching Algorithm Considering Candidate Point Grouping and Trajectory Connectivity [J]. Cartography and Geographic Information Science , 2023 , 50 ( 4 ): 351 - 370 .
胡钊政 , 孙莹妹 , 李祎承 . 路面路标高精度地图构建与多尺度车辆定位 [J]. 哈尔滨工业大学学报 , 2019 , 51 ( 9 ): 149 - 156 .
HU Zhaozheng , SUN Yingmei , LI Yicheng . High Definition Map Construction from Pavement Landmarks for Multi-scale Vehicle Localization [J]. Journal of Harbin Institute of Technology , 2019 , 51 ( 9 ): 149 - 156 .
NEVEN D , DE BRABANDERE B , GEORGOULIS S , et al . Towards End-to-End Lane Detection: An Instance Segmentation Approach [C]// IEEE Intelligent Vehicles Symposium , Changshu, China , 2018 .
LIU Y Y , PENG J Y , XUE J H , et al . TSingNet: Scale-Aware and Context-Rich Feature Learning for Traffic Sign Detection and Recognition in the Wild [J]. Neurocomputing , 2021 , 447 : 10 - 22 .
LEE T J , YI D H , DAN CHO D I , et al . A Monocular Vision Sensor-Based Obstacle Detection Algorithm for Autonomous Robots [J]. Sensors , 2016 , 16 ( 3 ): 311 .
周苏 , 支雪磊 , 林飞滨 , 等 . 基于车载视频图像的车辆检测与跟踪算法 [J]. 同济大学学报(自然科学版) , 2019 , 47 ( S1 ): 191 - 198 .
ZHOU Su , ZHI Xuelei , LIN Feibin , et al . Research on Vehicle Detection and Tracking Algorithm Based on Onboard Video Images [J]. Journal of Tongji University (Natural Science) , 2019 , 47 ( S1 ): 191 - 198 .
MUR-ARTAL R , TARDÓS J D . ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras [J]. IEEE Transactions on Robotics , 2017 , 33 ( 5 ): 1255 - 1262 .
YANG Z H , LI J , LI H Y . Real-Time Pedestrian and Vehicle Detection for Autonomous Driving [C]// IEEE Intelligent Vehicles Symposium , Changshu, China , 2018 .
ZHANG W W , LIU H , WU X C , et al . Lane Marking Detection and Classification with Combined Deep Neural Network for Driver Assistance [J]. Proceedings of the Institution of Mechanical Engineers , Part D: Journal of Automobile Engineering, 2019 , 233 ( 5 ): 1259 - 1268 .
LI B Z , WANG M Q , CAI Z L , et al . VIS-MM: A Novel Map-Matching Algorithm with Semantic Fusion from Vehicle-Borne Images [J]. International Journal of Geographical Information Science , 2023 , 37 ( 5 ): 1069 - 1098 .
ZHOU M J , CHEN X , SAMANO N , et al . Efficient Localisation Using Images and OpenStreetMaps [C]// IEEE/RSJ International Conference on Intelligent Robots and Systems , Prague, Czech Republic , 2021 .
ULLMAN S . The Interpretation of Structure from Motion [J]. Proceedings of the Royal Society of London Series B , Biological Sciences, 1979 , 203 ( 1153 ): 405 - 426 .
CUI Z P , TAN P . Global Structure-from-Motion by Similarity Averaging [C]// IEEE International Conference on Computer Vision , Santiago, Chile , 2016 .
陈武 , 姜三 , 李清泉 , 等 . 无人机影像增量式运动恢复结构研究进展 [J]. 武汉大学学报(信息科学版) , 2022 , 47 ( 10 ): 1662 - 1674 .
CHEN Wu , JIANG San , LI Qingquan , et al . Recent Research of Incremental Structure from Motion for Unmanned Aerial Vehicle Images [J]. Geomatics and Information Science of Wuhan University , 2022 , 47 ( 10 ): 1662 - 1674 .
许彪 , 董友强 , 张力 , 等 . 分区优化混合 SfM 方法 [J]. 测绘学报 , 2022 , 51 ( 1 ): 115 - 126 .
XÜ Biao, DONG Youqiang, ZHANG Li, et al, A Hybrid SfM Method Based on Partition Optimization [J]. Acta Geodaetica et Cartographica Sinica , 2022 , 51 ( 1 ): 115 - 126 .
0
浏览量
2
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621