Nan Xiao
ABSTRACT
Vehicular path flow (trajectories) is an important data source for smart mobility, from which many road traffic parameters can be inferred. However, it has been a long-existing challenge that single source of trajectory data is biased in terms of its spatiotemporal coverage. In this paper, we leverage two types of large traffic datasets - point flows and sample trajectories - to generate the full city-scale vehicular paths. Our method consists of a low-granularity data fusion (LGDF) module, which uses point flow data to estimate the sparse paths that pass through some specific links (where sensors are mounted), and a high-granularity model training (HGMT) component, which uses sample trajectory data to pre-train a bi-gram sequence generation model. Afterwards, the results from LGDF and HGMT are combined to produce detailed on-road spatiotemporal paths. In this way, the data safety of single trajectory is protected while the full-scale city traffic can be reproduced for transportation analytics. The proposed method is verified via real-data case studies. As a result, starting from August 2019, this method has been implemented in Alibaba's city brain project and successively deployed in many cities in China for the purpose of traffic analysis and optimization.
Supplemental Material
- Yousra A.A.S. Aldeen and Mazleena Salleh. 2019. Chapter 10 - Techniques for Privacy Preserving Data Publication in the Cloud for Smart City Applications. In Smart Cities Cybersecurity and Privacy, Danda B. Rawat and Kayhan Z. Ghafoor (Eds.). Elsevier, 129 -- 145.Google Scholar
- Gowtham Atluri, Anuj Karpatne, and Vipin Kumar. 2018. Spatio-temporal data mining: A survey of problems and methods. Comput. Surveys, Vol. 51, 4 (2018), 1--37.Google ScholarDigital Library
- Michael G.H. Bell. 1991. The real time estimation of origin-destination flows in the presence of platoon dispersion. Transportation Research Part B: Methodological, Vol. 25, 2 (1991), 115--125.Google ScholarCross Ref
- Michael G.H. Bell, Chris Cassir, Sergio Grosso, and Stuart J. Clement. 1997. Path flow estimation in traffic system management. IFAC Proceedings Volumes, Vol. 30, 8 (1997), 1247--1252.Google Scholar
- Francesco Calabrese, Mi Diao, Giusy Di Lorenzo, Joseph Ferreira Jr, and Carlo Ratti. 2013. Understanding individual mobility patterns from urban sensing data: A mobile phone trace example. Transportation Research Part C: Emerging Technologies, Vol. 26 (2013), 301--313.Google ScholarCross Ref
- Peng Cao, Tomio Miwa, Toshiyuki Yamamoto, and Takayuki Morikawa. 2013. Bilevel generalized least squares estimation of dynamic origin--destination matrix for urban network with probe vehicle data. Transportation Research Record, Vol. 2333, 1 (2013), 66--73.Google ScholarCross Ref
- Ennio Cascetta and Sang Nguyen. 1988. A unified framework for estimating or updating origin/destination matrices from traffic counts. Transportation Research Part B: Methodological, Vol. 22, 6 (1988), 437--455.Google ScholarCross Ref
- Enrique Castillo, José M. Menéndez, and Pilar Jiménez. 2008. Trip matrix and path flow reconstruction and estimation based on plate scanning and link observations. Transportation Research Part B: Methodological, Vol. 42, 5 (2008), 455--481.Google ScholarCross Ref
- Palash Goyal and Emilio Ferrara. 2018. Graph embedding techniques, applications, and performance: A survey. Knowledge-Based Systems, Vol. 151 (2018), 78--94.Google ScholarCross Ref
- Thomas Holleczek, Liang Yu, Joseph K. Lee, Oliver Senn, Carlo Ratti, and Patrick Jaillet. 2014. Detecting weak public transport connections from cellphone and public transport data. In 2014 International Conference on Big Data Science and Computing. 1--8.Google ScholarDigital Library
- Daniel Jurafsky and James H. Martin. 2009. Speech and Language Processing. Prentice Hall.Google ScholarDigital Library
- Michael J. Maher. 1983. Inferences on trip matrices from observations on link volumes: A Bayesian statistical approach. Transportation Research Part B: Methodological, Vol. 17, 6 (1983), 435--447.Google ScholarCross Ref
- Adolf D. May. 1990. Traffic Flow Fundamentals. Prentice Hall. 89039687Google Scholar
- Chuishi Meng, Xiuwen Yi, Lu Su, Jing Gao, and Yu Zheng. 2017. City-wide traffic volume inference with loop detector data and taxi trajectories. In 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. 1--10.Google ScholarDigital Library
- Tomas Mikolov, Martin Karafiát, Lukás Burget, Jan Cernocký, and Sanjeev Khudanpur. 2010. Recurrent neural network based language model. In INTERSPEECH. 1045--1048.Google Scholar
- Pierre Robillard. 1975. Estimating the O-D matrix from observed link volumes. Transportation Research, Vol. 9, 2 (1975), 123--128.Google ScholarCross Ref
- Yuanhui Sun and Yaying Zhang. 2016. Path restoring algorithm based on vehicle trajectory mining. 2016 IEEE International Conference on Big Data Analysis (2016), 1--6.Google ScholarCross Ref
- Xianfeng Yang, Yang Lu, and Wei Hao. 2017. Origin-destination estimation using probe vehicle trajectory and link counts. Journal of Advanced Transportation (2017), 1--18.Google Scholar
- Liang Yu, Wei Wu, Xiaohui Li, Guangxia Li, Wee Siong Ng, See-Kiong Ng, Zhongwen Huang, Anushiya Arunan, and Hui Min Watt. 2015. iVizTRANS: Interactive visual learning for home and work place detection from massive public transportation data. In 2015 IEEE Conference on Visual Analytics Science and Technology. 49--56.Google ScholarCross Ref
- Liang Yu, Jinqiang Yu, Maolei Zhang, Xin Zhang, Yuehu Liu, Hui Zhang, and Wanli Min. 2019. Large scale traffic signal network optimization - A paradigm shift driven by big data. In 35th IEEE International Conference on Data Engineering. 1832--1840.Google ScholarCross Ref
- Yan Zhao, Wai Wong, Jianfeng Zheng, Shihong Huang, and Henry X. Liu. 2019. OD estimation using probe vehicle trajectories. In Transportation Research Board 98th Annual Meeting. 1--7.Google Scholar
- Yu Zheng. 2015. Trajectory data mining: An overview. ACM Transactions on Intelligent Systems and Technology, Vol. 6, 3 (2015), 1--41.Google ScholarDigital Library
- Xuesong Zhou and Hani S. Mahmassani. 2006. Dynamic origin-destination demand estimation using automatic vehicle identification data. IEEE Transactions on Intelligent Transportation Systems, Vol. 7, 1 (2006), 105--114.Google ScholarDigital Library
- Li Zhu, Fei R. Yu, Yige Wang, Bin Ning, and Tao Tang. 2019. Big data analytics in intelligent transportation systems: A survey. IEEE Transactions on Intelligent Transportation Systems, Vol. 20, 1 (2019), 383--398.Google ScholarCross Ref
- Henk J. Van Zuylen and Luis G. Willumsen. 1980. The most likely trip matrix estimated from traffic counts. Transportation Research Part B: Methodological, Vol. 14, 3 (1980), 281--293.Google ScholarCross Ref
Index Terms
- Generating Full Spatiotemporal Vehicular Paths: A Data Fusion Approach
Recommendations
Cooperative vehicle positioning with multi-sensor data fusion and vehicular communications
Vehicular positioning with multi-sensor fusion has achieved promising results in recent years. Having potential benefit from the emerging vehicular communications based on IEEE 802.11p dedicated short-range communication (DSRC), cooperative positioning ...
Dynamic Vehicle Full-View Driver Assistance System in Vehicular Networks
RVSP '13: Proceedings of the 2013 Second International Conference on Robot, Vision and Signal ProcessingThe Cooperative Collision Avoidance Warning System (CCAWS) for vehicle safety in vehicular networks has become very important in recent years. However, the advanced positioning methods will affect the accuracy of the CCAWS warning information. Hence, we ...
A path generation for automated vehicle based on Bezier curve and via-points
This paper presents a path generation method for automated vehicle based on Bezier curve. Derivation of smooth path is one of important subjects for vehicle navigation system. Bezier curve is a smooth parametric curve, but adequate assignment of its ...
Comments