集成时空邻近与卷积网络车道级高精度定位算法

doi:10.13474/j.cnki.11-2246.2022.0162.

测绘通报 ›› 2022, Vol. 0 ›› Issue (6): 1-5,61.doi: 10.13474/j.cnki.11-2246.2022.0162.

• 高精度定位 • 下一篇

集成时空邻近与卷积网络车道级高精度定位算法

滕文鑫^1,2, 张建辰^1,3,4,6, 邵杰⁵

1. 河南大学地理与环境学院, 河南开封 475004;
2. 武汉大学测绘遥感信息工程国家重点实验室, 湖北武汉 430070;
3. 自然资源部城市国土资源监测与仿真重点实验室, 广东深圳 5180384;
4. 河南大学河南省时空大数据产业技术研究院, 河南郑州 450000;
5. 首都师范大学附属红螺寺中学, 北京 101400;
6. 河南大学黄河中下游数字地理技术教育部重点实验室, 河南开封 475004

收稿日期:2021-09-13 发布日期:2022-06-30
通讯作者: 张建辰。E-mail:jczhang@vip.henu.edu.cn
作者简介:滕文鑫(1994-),男,博士,主要研究方向为车辆定位、地图匹配。E-mail:tengwenxin1112@126.com
基金资助:
自然资源部城市国土资源监测与仿真重点实验室开放基金(KF-2020-05-037)

Lane-level high-precision positioning algorithm based on integrated spatio-temporal proximity and CNN

TENG Wenxin^1,2, ZHANG Jianchen^1,3,4,6, SHAO Jie⁵

1. College of Geography and Environment, Henan University, Kaifeng 475004, China;
2. State Key Laboratory of Mapping and Remote Sensing Information Engineering, Wuhan University, Wuhan 430070, China;
3. Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen 5180384, China;
4. Henan Industrial Technology Academy of Spatio-Temporal Big Data, Henan University, Zhengzhou 450000, China;
5. Hongluosi Middle School, Capital Normal University, Beijing 101400, China;
6. Henan University key Laboratory of Geospatial Technology for the Middle and Lower Yellow River Regins, Ministry of Education, Kaifeng 475004, China

Received:2021-09-13 Published:2022-06-30

摘要/Abstract

摘要： 提高车道水平定位精度是智能交通系统发展的重要技术之一。本文提出了一种新的车道级定位方法——时空邻近卷积神经网络(STP-CNN),利用时空附近(STP)动态细化候选匹配道路,再进一步采用个性化卷积神经网络(CNN)自适应识别最优匹配车道。该方法通过优化集成GPS、车速和惯性测量单元等参数,实现了厘米级和车道级车辆位置的平滑估计。试验结果验证了该方法的可行性和有效性。

关键词: 卷积神经网络, 深度学习, 车道级定位, 智能交通系统, 时空邻近, 地图匹配

Abstract: Improving the accuracy of lane-level positioning is one of the most important technologies for the development of intelligent transportation system(ITS). We propose a new lane-level positioning method called spatio-temporal proximity and convolution neural network(STP-CNN), in which STP is designed to dynamically refine candidate matching roads, and personalize CNN is further adopted to adaptively identify the optimal matching lane. By optimally integrating parameters such as GPS receiver, driving speed and inertial measurement unit for the new method, centimeter-level and lane-level vehicle position is estimated smoothly. The test results justify the feasibility and efficiency of the proposed method.

Key words: CNN, deep learning, lane-level positioning, intelligent transportation system, spatio-temporal proximity, map matching

中图分类号:

P228

滕文鑫, 张建辰, 邵杰. 集成时空邻近与卷积网络车道级高精度定位算法[J]. 测绘通报, 2022, 0(6): 1-5,61.

TENG Wenxin, ZHANG Jianchen, SHAO Jie. Lane-level high-precision positioning algorithm based on integrated spatio-temporal proximity and CNN[J]. Bulletin of Surveying and Mapping, 2022, 0(6): 1-5,61.

参考文献

[1] LI D M,DENG L B,CAI Z M,et al. Notice of retraction:intelligent transportation system in Macao based on deep self-coding learning[J]. IEEE Transactions on Industrial Informatics,2018,14(7):3253-3260.
[2] 俞毓锋,赵卉菁,崔锦实,等.基于道路结构特征的智能车单目视觉定位[J].自动化学报,2017,43(5):725-734.
[3] DING D P. Visual positioning technology to be based on pavement structure[J]. Construction Machinery Technology&Management,2017(5):69-72.
[4] 乌萌,郝金明,付浩,等.利用解耦光流运动场模型的双目视觉里程计位姿优化方法[J].测绘学报,2019,48(4):460-472.
[5] ATIA M M,HILAL A R,STELLINGS C,et al. A low-cost lane-determination system using GNSS/IMU fusion and HMM-based multistage map matching[J]. IEEE Transactions on Intelligent Transportation Systems,2017,18(11):3027-3037.
[6] RAYMOND R,MORIMURA T,OSOGAMI T,et al. Map matching with hidden Markov model on sampled road network[C]//Proceedings of the 21st International Conference on Pattern Recognition. Tsukuba:IEEE,2012:2242-2245.
[7] OZGUNALP U,KAYMAK S.Lane detection by estimating and using restricted search space in Hough domain[J]. Procedia Computer Science,2017,120:148-155.
[8] ELSAWY A,ABDEL-MOTTALEB M,SHOUSHA M A. Segmentation of corneal optical coherence tomography images using randomized Hough transform[C]//Proceedings of 2019 SPIE Medical Imaging. San Diego:[s.n.],2019:210-220.
[9] 袁旻川,徐友春,李永乐.基于车道线提取的智能车横向定位技术[J].军事交通学院学报,2018,20(10):35-40.
[10] LEHTOMÄKI M,KUKKO A,MATIKAINEN L,et al. Power line mapping technique using all-terrain mobile laser scanning[J]. Automation in Construction,2019,105:102802.
[11] 董亚波,车凯,张涛,等.基于北斗的高精度定位车载导航系统的设计[J].科技视界,2017(12):63-64.
[12] 马天明,王建敏,祝会忠.长距离网络RTK实时厘米级定位算法[J].测绘科学,2017,42(12):157-162.
[13] 罗卫国.基于北斗的网络RTK实时定位服务分析[J].北京测绘,2019,33(7):787-791.
[14] LEE E K,YANG S,OH S Y,et al. RF-GPS:RFID assisted localization in VANETs[C]//Proceedings of 2009 IEEE International Conference on Mobile Adhoc and Sensor Systems. Macao:IEEE,2009:621-626.
[15] ZHU M.Positioning algorithms for RFID-based multi-sensor indoor/outdoor positioning techniques[D].[S.l.]:RMIT University,2011.
[16] 惠飞,武晓洁,马旭攀.一种基于RFID与OBD的车道定位系统的设计与实现[J].中国科技论文在线精品论文,2016,9(22):2371-2375.
[17] ZHENG C,LIBO C,LINBO Y,et al.Lane-level positioning system based on RFID and vision[C]//Proceedings of 2016 International Conference on Intelligent and Connected Vehicles.Chongqing:IET,2016:1-5.
[18] LI W,GUAN Y,CHEN L G,et al. Millimeter-wave radar and machine vision-based lane recognition[J]. International Journal of Pattern Recognition and Artificial Intelligence,2018,32(5):1850015.
[19] LI L,LUO W T,WANG K C P. Lane marking detection and reconstruction with line-scan imaging data[J]. Sensors (Basel,Switzerland),2018,18(5):1635.
[20] TOLEDO-MOREO R,BETAILLE D,PEYRET F. Lane-level integrity provision for navigation and map matching with GNSS,dead reckoning,and enhanced maps[J].IEEE Transactions on Intelligent Transportation Systems,2010,11(1):100-112.
[21] 吴彦文,张楠,周涛,等.基于多传感融合的车道线检测与跟踪方法的研究[J].计算机应用研究,2018,35(2):600-603.
[22] 叶子豪,孙锐,王慧慧.基于全卷积神经网络与条件随机场的车道识别方法[J].光电工程,2019,46(2):37-48.
[23] NEVEN D,DE BRABANDERE B,GEORGOULIS S,et al. Towards end-to-end lane detection:an instance segmentation approach[C]//Proceedings of 2018 IEEE Intelligent Vehicles Symposium. Changshu:IEEE,2018:286-291.
[24] BADRINARAYANAN V,KENDALL A,CIPOLLA R. SegNet:a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[25] LONG J,SHELHAMER E,DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston:IEEE,2015:3431-3440.
[26] TENG W X,WANG Y H,YU B B,et al. ICCIU:a new real-time lane-level positioning algorithm[J]. IEEE Access,2020,8:44957-44966.

集成时空邻近与卷积网络车道级高精度定位算法

Lane-level high-precision positioning algorithm based on integrated spatio-temporal proximity and CNN

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	柳林, 孙毅, 李万武. 基于CNN海上钻井平台检测模型的构建及训练算法分析[J]. 测绘通报, 2022, 0(7): 26-32,99.
[2]	刘立, 董先敏, 刘娟, 文学虎. 人机融合智能的遥感解译生产新方法[J]. 测绘通报, 2022, 0(7): 118-123,137.
[3]	蔡柔丹. 一种基于用户异步轨迹的身份识别智能方法[J]. 测绘通报, 2022, 0(7): 158-162,167.
[4]	文奴, 郭仁忠, 贺彪, 万远. YOLO v4框架下Multi-Patch多帧增量式交通视频目标检测[J]. 测绘通报, 2022, 0(5): 38-44.
[5]	张晋赫, 秦育罗, 张在岩, 宋伟东, 朱洪波. 复杂场景下农村道路裂缝分割方法[J]. 测绘通报, 2022, 0(5): 74-78,88.
[6]	师芸, 石龙龙, 牛敏杰, 赵侃. 基于单阶段实例分割网络的黄土滑坡多任务自动识别[J]. 测绘通报, 2022, 0(4): 26-31.
[7]	王雪, 梁珂, 隋立春, 钟棉卿, 朱剑锋. 膨胀卷积与金字塔表达的深度学习模型用于农村建筑物提取[J]. 测绘通报, 2022, 0(4): 61-65.
[8]	高鸣, 周鑫鑫, 刘琦, 杨光迪, 吴长彬. 深度学习网络支持下的农房侵占耕地自动化监测[J]. 测绘通报, 2022, 0(3): 47-53.
[9]	王胜利, 朱寿红, 蒋毅. 基于CNN模型迁移的OLI影像光伏电池板场景识别[J]. 测绘通报, 2022, 0(2): 5-9.
[10]	孙琴琴, 蔡国印, 杨柳忠, 张宁, 杜明义. 城市尺度典型地表要素综合提取方法研究[J]. 测绘通报, 2022, 0(2): 62-66.
[11]	张自强, 刘涛, 杜萍, 锁旭宏, 杨国林. 图残差神经网络支持下的建筑物群组模式分类[J]. 测绘通报, 2022, 0(1): 1-7.
[12]	车子杰, 高飞, 吴兆福, 李振轩. 基于改进U-Net网络的多源遥感影像洪涝灾害信息提取与变化分析[J]. 测绘通报, 2022, 0(1): 26-32.
[13]	程瑞, 高建, 邢强, 孙中昶. 一种优化的Faster R-CNN小目标检测方法[J]. 测绘通报, 2021, 0(9): 21-27.
[14]	耿万轩, 周维勋, 金双根. 基于LDCNN特征提取的多核SVM高分辨率遥感影像场景分类[J]. 测绘通报, 2021, 0(8): 14-21.
[15]	淳锦, 张新长, 郭海京, 张建国, 金诗程. 基于多源信息与深度学习特征提取的人口空间抽样方法[J]. 测绘通报, 2021, 0(8): 42-47.