Online map-matching assisted by object-based classification of driving scenario

Abstract

Different types of roads in complex road networks may run side-by-side or across in 2D or 3D spaces, which causes mismatched segments using existing online map-matching algorithms. A driving scenario that represents the driving environment can inform map-matching algorithms. Images from vehicle cameras contain extensive information about driving scenarios, such as surrounding key objects. This research utilized vehicle images and developed an object-based method to classify driving scenarios (Object-Based Driving-Scenario Classification: OBDSC) to calculate the probabilities of the current image in predefined types of driving scenarios. We implemented an online map-matching algorithm with the OBDSC method (OMM-OBDSC) to obtain optimal matching segments. The algorithm was tested on nine trajectories and OpenStreetMap data in Shanghai and compared with five benchmark algorithms in terms of the match rate, recall and accuracy. The OBDSC method is also applied to the benchmark algorithms to verify the effectiveness of map matching. The results show that our algorithm outperforms the benchmark algorithms with both the original interval and downsampled intervals (96.6%, 96.5%, 93.7% on average with 1–20 s intervals for the three metrics, respectively). The average match rate has improved by 8.9% for all benchmark algorithms after the addition of the OBDSC method.

Keywords:

• Online map-matching
• driving scenario classification
• complex road network
• GNSS

Acknowledgements

We gratefully acknowledge Yiren Technology Co. (Shanghai) for providing the experimental dataset. We also sincerely thank all editors and anonymous reviewers for their valuable comments and suggestions.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data and code availability statement

The data and codes that support this study are available in Figshare with the link https://doi.org/10.6084/m9.figshare.21782267.

Additional information

Funding

This work was supported by the National Key Research and Development Program of China [2021YFB2501103]; the Key Research and Development Projects of Shanghai Science and Technology Commission [21DZ1204102]; the National Science Foundation of China [42271429]; and the Fundamental Research Funds for the Central Universities of China [2022-5-ZD-05].

Notes on contributors

Hangbin Wu

Hangbin Wu received a B.E. degree in Surveying and Mapping Engineering and a Ph.D. degree in Geodetic from Tongji University, Shanghai, P.R. China. He is an Associate Professor of the College of Surveying and Geo-Informatics, Tongji University. His research interests are the collection and processing of point clouds, high-definition maps for autonomous driving and data mining from BIG navigation data, where he has contributed more than 50 publications.

Shengke Huang

Shengke Huang received a Bachelor of Engineering degree from Tongji University, Shanghai, P.R. China in 2021. He is currently a master’s candidate at the College of Surveying and Geo-Informatics, Tongji University. His research interests include high-definition maps for autonomous driving.

Chen Fu

Chen Fu received a Bachelor of Engineering degree from Tongji University, Shanghai, P.R. China, in 2021. She is currently a master’s candidate at the School of Earth and Space Sciences, Peking University. Her research interests include geospatial data mining and machine learning.

Shan Xu

Shan Xu received a B.E. degree in geographic Information science from Southwest Jiaotong University, Sichuan, China, in 2020. She is currently pursuing an M.S. degree in science and technology of surveying and mapping with Tongji University, Shanghai, China. Her research interests include map matching and spatial data analysis.

Junhua Wang

Junhua Wang received a B.E. degree in Civil Engineering and a Ph.D. degree in Highway and Railway Engineering from Tongji University, Shanghai, P.R. China. He is a Professor of the College of Transportation Engineering, Tongji University. His research interests include Road Safety, Accident Modelling and Highway Geometric Design where he has contributed more than 100 publications.

Wei Huang

Wei Huang received his Ph.D. degree from the Department of Civil Engineering at Ryerson University, Toronto, Canada in 2016. He is currently a Professor of the College of Surveying and Geo-Informatics, Tongji University. His research interests include urban mobility, spatial analytics and GIScience.

Chun Liu

Chun Liu was the Research Fellow with the Hong Kong Polytechnic University, Nottingham University and The Ohio State University. He currently works as the Deputy Director of the Office of Science and Technology with the duty on research project management with Tongji University and is also a Professor with the College of Surveying and Geo-Informatics, Tongji University, Shanghai, China. His research interests focus on LiDAR data processing, vision-based navigation, and integrated geographical data and global positioning system measurements for urban and engineering applications.