Reinforcement learning-based vehicle travel path reconstruction from sparse automatic licence plate recognition data
Automatic licence plate recognition (ALPR) data is a vital source for acquiring large-scale vehicle trajectory data in urban transportation research. However, the sparse distribution of ALPR sensors often results in incomplete vehicle trajectories with unobserved travel paths between adjacent ALPR s...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-01-01
|
| Series: | Annals of GIS |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/19475683.2025.2453553 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592623750086656 |
|---|---|
| author | Qiuping Li Hui Meng Li Zhuo |
| author_facet | Qiuping Li Hui Meng Li Zhuo |
| author_sort | Qiuping Li |
| collection | DOAJ |
| description | Automatic licence plate recognition (ALPR) data is a vital source for acquiring large-scale vehicle trajectory data in urban transportation research. However, the sparse distribution of ALPR sensors often results in incomplete vehicle trajectories with unobserved travel paths between adjacent ALPR sensors. To address this challenge, this study proposes a novel travel path reconstruction model based on reinforcement learning. First, the maximum entropy inverse reinforcement learning (MaxEnt IRL) method is employed to learn vehicle path selection strategy, i.e. the reward function, from the real data. Then, a comprehensive reward function is formulated by integrating destination rewards. Finally, the Q-learning algorithm is utilized to reconstruct vehicle travel paths between adjacent ALPR sensors based on the comprehensive reward function. Evaluation on a randomly selected set of 100 pairs of adjacent ALPR sensors demonstrates that the proposed model significantly outperforms two baseline methods, achieving reductions of 24.3% and 22.5% in deviation from the real paths. |
| format | Article |
| id | doaj-art-18667d179caa433da8ae0842384c2b34 |
| institution | Kabale University |
| issn | 1947-5683 1947-5691 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Annals of GIS |
| spelling | doaj-art-18667d179caa433da8ae0842384c2b342025-01-21T06:04:37ZengTaylor & Francis GroupAnnals of GIS1947-56831947-56912025-01-0111310.1080/19475683.2025.2453553Reinforcement learning-based vehicle travel path reconstruction from sparse automatic licence plate recognition dataQiuping Li0Hui Meng1Li Zhuo2School of Geography and Planning, Sun Yat-sen University, Guangzhou, ChinaSchool of Geography and Planning, Sun Yat-sen University, Guangzhou, ChinaSchool of Geography and Planning, Sun Yat-sen University, Guangzhou, ChinaAutomatic licence plate recognition (ALPR) data is a vital source for acquiring large-scale vehicle trajectory data in urban transportation research. However, the sparse distribution of ALPR sensors often results in incomplete vehicle trajectories with unobserved travel paths between adjacent ALPR sensors. To address this challenge, this study proposes a novel travel path reconstruction model based on reinforcement learning. First, the maximum entropy inverse reinforcement learning (MaxEnt IRL) method is employed to learn vehicle path selection strategy, i.e. the reward function, from the real data. Then, a comprehensive reward function is formulated by integrating destination rewards. Finally, the Q-learning algorithm is utilized to reconstruct vehicle travel paths between adjacent ALPR sensors based on the comprehensive reward function. Evaluation on a randomly selected set of 100 pairs of adjacent ALPR sensors demonstrates that the proposed model significantly outperforms two baseline methods, achieving reductions of 24.3% and 22.5% in deviation from the real paths.https://www.tandfonline.com/doi/10.1080/19475683.2025.2453553Vehicle travel path reconstructionreinforcement learninginverse reinforcement learningQ-learningautomatic licence plate recognition data |
| spellingShingle | Qiuping Li Hui Meng Li Zhuo Reinforcement learning-based vehicle travel path reconstruction from sparse automatic licence plate recognition data Annals of GIS Vehicle travel path reconstruction reinforcement learning inverse reinforcement learning Q-learning automatic licence plate recognition data |
| title | Reinforcement learning-based vehicle travel path reconstruction from sparse automatic licence plate recognition data |
| title_full | Reinforcement learning-based vehicle travel path reconstruction from sparse automatic licence plate recognition data |
| title_fullStr | Reinforcement learning-based vehicle travel path reconstruction from sparse automatic licence plate recognition data |
| title_full_unstemmed | Reinforcement learning-based vehicle travel path reconstruction from sparse automatic licence plate recognition data |
| title_short | Reinforcement learning-based vehicle travel path reconstruction from sparse automatic licence plate recognition data |
| title_sort | reinforcement learning based vehicle travel path reconstruction from sparse automatic licence plate recognition data |
| topic | Vehicle travel path reconstruction reinforcement learning inverse reinforcement learning Q-learning automatic licence plate recognition data |
| url | https://www.tandfonline.com/doi/10.1080/19475683.2025.2453553 |
| work_keys_str_mv | AT qiupingli reinforcementlearningbasedvehicletravelpathreconstructionfromsparseautomaticlicenceplaterecognitiondata AT huimeng reinforcementlearningbasedvehicletravelpathreconstructionfromsparseautomaticlicenceplaterecognitiondata AT lizhuo reinforcementlearningbasedvehicletravelpathreconstructionfromsparseautomaticlicenceplaterecognitiondata |