Deep learning-based map matching considering road network constraints

doi:10.13474/j.cnki.11-2246.2024.0617

Abstract

Abstract: In low-frequency or non-uniform sampling conditions, existing map matching algorithms have problems of low matching accuracy or low efficiency. In this paper, we propose a road network constrained map matching model based on deep learning (RNCMM). Firstly, Seq2Seq framework is used to map the low frequency track point sequence to the high frequency road segment sequence from end to end. Secondly, a fine-grained constraint mask layer is constructed according to the distance and azimuth difference between the road and the trajectory point, which is conducive to alleviating the limitations of the trajectory grid representation and improving the matching accuracy. Then, attention mechanism and multi-task learning mechanism are introduced to mine the spatiotemporal correlation between trajectory points and perform joint prediction of road segments and directions. Finally, experiments are conducted on the Porto taxi trajectory dataset and OSM road network. The results show that compared to traditional hidden Markov model(HMM), the proposed algorithm can effectively improve the matching accuracy and efficiency of low-frequency floating car trajectories.

Key words: map matching, deep learning, sequence-to-sequence model, GRU, multi-task learning, attention mechanism

CLC Number:

ZHONG Qingcen, WU Chenhao, XIANG Longgang, YAO Peng. Deep learning-based map matching considering road network constraints[J]. Bulletin of Surveying and Mapping, 2024, 0(6): 96-102,133.

References

1] 李祎承,杨东晓,高翔,等. 面向智能汽车的地下停车场定位与路径规划[J]. 光学精密工程,2023,31(5):757-766.
[2] 陈伟,杜路遥,孔海洋,等. 面向智能网联汽车定位的协同地图匹配算法[J]. 交通信息与安全,2021,39(6):162-171.
[3] 刘经南,詹骄,郭迟,等. 智能高精地图数据逻辑结构与关键技术[J]. 测绘学报,2019,48(8):939-953.
[4] WHITE C E,BERNSTEIN D,KORNHAUSER A L.Some map matching algorithms for personal navigation assistants[J].Transportation Research Part C:Emerging Technologies,2000,8(1/2/3/4/5/6):91-108.
[5] ALT H,EFRAT A,ROTE G,et al. Matching planar maps[J].Journal of Algorithms,2003,49(2):262-283.
[6] SHARATH M N,VELAGA N R,QUDDUS M A. A dynamic two-dimensional (D2D) weight-based map-matching algorithm[J]. Transportation Research Part C:Emerging Technologies,2019,98:409-432.
[7] 盛彩英,席唱白,钱天陆,等. 浮动车轨迹点地图匹配及插值算法[J]. 测绘科学,2019,44(8):106-112.
[8] NADINE S,KAY W. Map matching of GPS traces on high-resolution navigation networks using the multiple hypothesis technique(MHT) [J].Working Paper Transport and Spatial Planning,2009(10):568-588.
[9] BIERLAIRE M,CHEN Jingmin,NEWMAN J. A probabilistic map matching method for smartphone GPS data[J]. Transportation Research Part C:Emerging Technologies,2013,26:78-98.
[10] NEWSON P,KRUMM J. Hidden Markov map matching through noise and sparseness[C]//Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems.New York:Association for Computing Machinery,2009. 336-343.
[11] LOU Y,ZHANG C,ZHENG Y,et al. Map-Matching for low-sampling-rate GPS trajectories[C]//Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems.New York:Association for Computing Machinery,2009. 352-361.
[12] MOHAMED R,ALY H,YOUSSEF M. Accurate real-time map matching for challenging environments[J]. IEEE Transactions on Intelligent Transportation Systems,2017,18(4):847-857.
[13] XIONG Zhengang,LI Bin,LIU Dongmei. Map-matching using hidden Markov model and path choice preferences under sparse trajectory[J]. Sustainability,2021,13(22):12820.
[14] SHEN Zhihao,DU Wan,ZHAO Xi,et al. DMM:fast map matching for cellular data[C]//Proceedings of the 26th Annual International Conference on Mobile Computing and Networking.London,United Kingdom: ACM Press,2020:1-14.
[15] FENG Jie,LI Yong,ZHAO Kai,et al. DeepMM:deep learning based map matching with data augmentation[C]//Proceedings of 2022 IEEE Transactions on Mobile Computing. [S.l.]:IEEE,2022:2372-2384.
[16] BOEING G. OSMnx:new methods for acquiring,constructing,analyzing,and visualizing complex street networks[J]. Computers,Environment and Urban Systems,2017,65:126-139.
[17] REN Huimin,RUAN Sijie,LI Yanhua,et al. MTrajRec:map-constrained trajectory recovery via Seq2Seq multi-task learning[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. Virtual Event,Singapore:ACM Press,2021:1410-1419.
[18] ECML/PKDD 15:taxi trip time prediction [EB/OL].[2023-08-20].https://www.kaggle.com/competitions/pkdd-15-taxi-trip-time-prediction-ii/overview.
[19] CUI Ge,LUO Jun,WANG Xin. Personalized travel route recommendation using collaborative filtering based on GPS trajectories[J]. International Journal of Digital Earth,2018,11(3):284-307.
[20] HOTEIT S,SECCI S,SOBOLEVSKY S,et al. Estimating human trajectories and hotspots through mobile phone data[J]. Computer Networks:the International Journal of Computer and Telecommunications Networking,2014,64:296-307.

[1]	GAO Motong, YANG Weifang, LIU Zuyu, CAO Xiaoshuang, ZHANG Ruiqi, HOU Yuhao. LSTM goaf surface subsidence prediction method combining convolutional neural network and attention mechanism [J]. Bulletin of Surveying and Mapping, 2024, 0(6): 53-58,170.
[2]	ZHANG Wei, ZHANG Chaolong, WANG Benlin, CAI Anning. Road extraction of UAV remote sensing image based on deep learning [J]. Bulletin of Surveying and Mapping, 2024, 0(6): 77-81.
[3]	YIN Zezhong, LI Gongquan. Electronic fence out-of-bounds detection method based on 3D field superimposed video stream [J]. Bulletin of Surveying and Mapping, 2024, 0(6): 103-108.
[4]	WANG Lixia, XI Wenfei, SHI Zhengtao, ZHAO Zilong, QIAN Tanghui, ZHAO Lei, MA Yijie. Study on sample unbalance in landslide recognition algorithm based on depth learning [J]. Bulletin of Surveying and Mapping, 2024, 0(5): 12-18.
[5]	YAO Chuxian, CAI Haonan, ZHANG Yuanbo, TANG Keyi, ZHAN Lu, ZHOU Baoding. Road damage detection method based on lightweight vehicle equipment [J]. Bulletin of Surveying and Mapping, 2024, 0(5): 147-150.
[6]	ZHANG Nan, ZHANG Yunling. A method for extracting complex and difficult road networks based on deep learning models [J]. Bulletin of Surveying and Mapping, 2024, 0(5): 155-159.
[7]	ZHAO Mingshu. An updating method of the HD map confidence [J]. Bulletin of Surveying and Mapping, 2024, 0(5): 166-171,177.
[8]	LIN Bokun, DING Yong, LI Denghua. A slope anomaly monitoring technology based on deep learning and image local feature extraction [J]. Bulletin of Surveying and Mapping, 2024, 0(4): 23-28.
[9]	PANG Min. Extraction of domestic satellite images patches based on deep learning [J]. Bulletin of Surveying and Mapping, 2024, 0(4): 124-128,134.
[10]	LI Yuehua. Analysis methods and practice of topological connection problem of road intersections in high definition maps [J]. Bulletin of Surveying and Mapping, 2024, 0(4): 150-155.
[11]	CHEN Chang, ZHANG Yan, LI Kunheng, YANG Runze, ZHANG Junbin, LIANG Yanrong. A method of automatic mapping of gullies based on GF-7 satellite image in the black soil region in Northeast China [J]. Bulletin of Surveying and Mapping, 2024, 0(3): 1-7.
[12]	WANG Hongyan, CHE Xianghong, XU Xinchao, XU Shenghua, LI Hongsheng. Green visible index extraction and analysis of street view image using DeepLabv3+model:taking within the Third Ring Road in Beijing as an example [J]. Bulletin of Surveying and Mapping, 2024, 0(3): 88-94.
[13]	MA Jinshan, JIA Guohuan, ZHANG Sai, ZHANG Jiong. Extraction of typical natural resource elements based on multi-source high-resolution remote sensing images [J]. Bulletin of Surveying and Mapping, 2024, 0(3): 123-126,150.
[14]	WANG Honglei, YAN Wenpu. Remote sensing monitoring of cultivated land occupancy in Guizhou province based on deep learning technology [J]. Bulletin of Surveying and Mapping, 2024, 0(3): 134-139.
[15]	ZHU Weigang, WANG Lun, CHEN Tian, ZOU Bowen. UAV image road crack detection method based on improved YOLOv5 [J]. Bulletin of Surveying and Mapping, 2024, 0(3): 173-178.