[1]MENG Xiangfu,GE Xiwen,YANG Yuzhuo.A seq2seq based trajectory recovery method under the constraint of scenario road network[J].CAAI Transactions on Intelligent Systems,2026,21(2):529-541.[doi:10.11992/tis.202506009]
Copy

A seq2seq based trajectory recovery method under the constraint of scenario road network

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 21 Number of periods: 2026 2 Page number: 529-541 Column: 学术论文—人工智能基础 Public date: 2026-03-05
Title:
A seq2seq based trajectory recovery method under the constraint of scenario road network
Author(s):
MENG Xiangfu;  GE Xiwen;  YANG Yuzhuo
School of Electronic and Information Engineering, Liaoning Technical University, Huludao 125105, China
Keywords:
road network constraint; travel pattern; sparse trajectory; trajectory recovery; sequence-to-sequence; scenario road network; spatiotemporal feature extraction; road segment inference
CLC:
TP183
DOI:
10.11992/tis.202506009
Abstract:
In the real world, trajectory data grows exponentially yet remains sparse, making trajectory recovery crucial for downstream mining tasks. Most existing end-to-end trajectory recovery methods under road network constraints embed static road networks and coordinates into vectors. However, they overlook dynamic road traffic flow and neglect links between drivers’ travel patterns and the functions of regions/road segments, which are hard to extract from sparse trajectory spatio-temporal features and road semantic features. This paper proposes a road network-constrained scenario-based sequence-to-sequence trajectory recovery method (CSTrajRec). It inputs trajectories into a Fourier encoding layer to extract spatio-temporal features and enhance overall pattern representation. In the encoder, each road segment is modeled with text-based points of interest, road type, and regional traffic, which are then used to describe the trajectory sequence for individual travel patterns. In the decoder, a novel segment inference module fusing distance and road scenario information is designed for trajectory recovery. Experiments on three real datasets with sparsely sampled trajectories at varying intervals validate the model’s superiority.
References:
[1] DANG Weizhen, WANG Haibo, PAN Shirui, et al. Predicting human mobility via graph convolutional dual-attentive networks[C]//Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining. Virtual Event: ACM, 2022: 192-200.
[2] BAGHBANI A, RAHMANI S, BOUGUILA N, et al. Predicting passenger flow using graph neural networks with scheduled sampling on bus networks[C]//2023 IEEE 26th International Conference on Intelligent Transportation Systems. Bilbao: IEEE, 2024: 3073-3078.
[3] 孟祥福, 谢伟鹏, 崔江燕. 基于时空动态图的交通流量预测方法研究[J]. 智能系统学报, 2025, 20(4): 776-786 MENG Xiangfu, XIE Weipeng, CUI Jiangyan. Research on traffic flow prediction method based on spatial-temporal dynamic graph convolutional network[J]. CAAI transactions on intelligent systems, 2025, 20(4): 776-786
[4] 孟祥福, 徐永杰, 翁雪. 时空交叉注意力特征融合的交通流量预测模型[J]. 计算机科学与探索, 2025, 19(7): 1931-1944 MENG Xiangfu, XU Yongjie, WENG Xue. Spatio-temporal cross-attention feature fusion model for traffic flow prediction[J]. Journal of frontiers of computer science & technology, 2025, 19(7): 1931-1944
[5] 陈文强, 王东丹, 朱文英, 等. 基于时空图注意力网络的车辆多模态轨迹预测模型[J]. 浙江大学学报(工学版), 2025, 59(3): 443-450 CHEN Wenqiang, WANG Dongdan, ZHU Wenying, et al. Vehicle multimodal trajectory prediction model based on spatio-temporal graph attention network[J]. Journal of Zhejiang University (engineering science), 2025, 59(3): 443-450
[6] 宋绍剑, 徐佳敏, 李刚, 等. 联合TCN和时空多头注意机制的车辆轨迹预测模型[J]. 计算机工程与应用, 2025, 61(12): 352-358 SONG Shaojian, XU Jiamin, LI Gang, et al. Vehicle trajectory prediction model with TCN and spatial-temporal multi-head attention mechanism[J]. Computer engineering and applications, 2025, 61(12): 352-358
[7] TANG Xiaolong, KAN Meina, SHAN Shiguang, et al. HPNet: dynamic trajectory forecasting with historical prediction attention[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 15261-15270.
[8] 孟祥福, 师光启, 张霄雁, 等. 基于深度学习的轨迹相似性度量方法研究综述[J]. 计算机科学与探索, 2025, 19(3): 623-644 MENG Xiangfu, SHI Guangqi, ZHANG Xiaoyan, et al. Survey on deep learning based trajectory similarity measurement approaches[J]. Journal of frontiers of computer science and technology, 2025, 19(3): 623-644
[9] HE Huajun, LI Ruiyuan, RUAN Sijie, et al. TraSS: efficient trajectory similarity search based on key-value data stores[C]//2022 IEEE 38th International Conference on Data Engineering. Kuala Lumpur: IEEE, 2022: 2306-2318.
[10] 孟祥福, 崔江燕, 邓敏超. 基于图卷积神经网络的最短路径距离估计方法[J]. 智能系统学报, 2024, 19(6): 1518-1527 MENG Xiangfu, CUI Jiangyan, DENG Minchao. Road network shortest distance estimation method based on graph convolutional networks[J]. CAAI transactions on intelligent systems, 2024, 19(6): 1518-1527
[11] LIAO Tianxi, HAN Liangzhe, XU Yi, et al. Multi-faceted route representation learning for travel time estimation[J]. IEEE transactions on intelligent transportation systems, 2024, 25(9): 11782-11793
[12] LI Xiucheng, ZHAO Kaiqi, CONG Gao, et al. Deep representation learning for trajectory similarity computation[C]//2018 IEEE 34th International Conference on Data Engineering. Paris: IEEE, 2018: 617-628.
[13] WU Chenhao, XIANG Longgang, CHEN Libiao, et al. Learning universal trajectory representation via a Siamese geography-aware transformer[J]. ISPRS international journal of geo-information, 2024, 13(3): 64
[14] WANG Jingyuan, WU Ning, LU Xinxi, et al. Deep trajectory recovery with fine-grained calibration using Kalman filter[J]. IEEE transactions on knowledge and data engineering, 2021, 33(3): 921-934
[15] LI Mingxiao, GAO Song, LU Feng, et al. Reconstruction of human movement trajectories from large-scale low-frequency mobile phone data[J]. Computers, environment and urban systems, 2019, 77: 101346
[16] XIA Tong, QI Yunhan, FENG Jie, et al. AttnMove: history enhanced trajectory recovery via attentional network[J]. Proceedings of the AAAI conference on artificial intelligence, 2021, 35(5): 4494-4502
[17] 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. Seattle: ACM, 2009: 336-343.
[18] 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: ACM, 2021: 1410-1419.
[19] CHEN Yuqi, ZHANG Hanyuan, SUN Weiwei, et al. RNTrajRec: road network enhanced trajectory recovery with spatial-temporal transformer[C]//2023 IEEE 39th International Conference on Data Engineering. Anaheim: IEEE, 2023: 829-842.
[20] LIU Yu, GE Qian, LUO Wei, et al. GraphMM: graph-based vehicular map matching by leveraging trajectory and road correlations[J]. IEEE transactions on knowledge and data engineering, 2024, 36(1): 184-198
[21] WEI Tonglong, LIN Youfang, LIN Yan, et al. Micro-macro spatial-temporal graph-based encoder-decoder for map-constrained trajectory recovery[J]. IEEE transactions on knowledge and data engineering, 2024, 36(11): 6574-6587
[22] ZHAO Yaya, ZHAO Kaiqi, CHEN Zhiqian, et al. A graph-based representation framework for trajectory recovery via spatiotemporal interval-informed Seq2Seq[C]//Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. Jeju: IJCAI, 2024: 2588-2597.
[23] TANCIK M, SRINIVASAN P P, MILDENHALL B, et al. Fourier features let networks learn high frequency functions in low dimensional domains[C]//34th Conference on Neural Information Processing Systems. Vancouver: Curran Associates Inc. , 2020: 1-11.
[24] HOU Qibin, ZHOU Daquan, FENG Jiashi. Coordinate attention for efficient mobile network design[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 13708-13717.
[25] VELI?KOVI? P, CUCURULL G, CASANOVA A, et al. Graph attention networks[EB/OL]. (2017-10-30)[2025-06-11]. https://arxiv.org/abs/1710.10903.
[26] HADJIELEFTHERIOU M, MANOLOPOULOS Y, THEODORIDIS Y, et al. R-trees: a dynamic index structure for spatial searching[M]//Encyclopedia of GIS. Cham: Springer International Publishing, 2017: 1805-1817.
[27] 刘帅, 乔颖, 罗雄飞, 等. 时序数据库关键技术综述[J]. 计算机研究与发展, 2024, 61(3): 614-638 LIU Shuai, QIAO Ying, LUO Xiongfei, et al. Key techniques of time series databases: a survey[J]. Journal of computer research and development, 2024, 61(3): 614-638
[28] WANG Chenxing, ZHAO Fang, LUO Haiyong, et al. Towards effective transportation mode-aware trajectory recovery: heterogeneity, personalization and efficiency[J]. IEEE transactions on mobile computing, 2025, 24(4): 2832-2846
[29] CHAN T N, IP P L, LEONG HOU U, et al. KDV-explorer: a near real-time kernel density visualization system for spatial analysis[J]. Proceedings of the VLDB endowment, 2021, 14(12): 2655-2658
[30] BOEING G. OSMnx: a Python package to work with graph-theoretic OpenStreetMap street networks[J]. The journal of open source software, 2017, 2(12): 215
[31] HOTEIT S, SECCI S, SOBOLEVSKY S, et al. Estimating human trajectories and hotspots through mobile phone data[J]. Computer networks, 2014, 64: 296-307
[32] YANG Peilun, WANG Hanchen, ZHANG Ying, et al. T3S: effective representation learning for trajectory similarity computation[C]//2021 IEEE 37th International Conference on Data Engineering. Chania: IEEE, 2021: 2183-2188.
[33] HAN Peng, WANG Jin, YAO Di, et al. A graph-based approach for trajectory similarity computation in spatial networks[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. Virtual Event: ACM, 2021: 556-564.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems