Multi-Vehicle Tracking Based on Monocular Camera in Driver View
Multi-vehicle tracking is used in advanced driver assistance systems to track obstacles, which is fundamental for high-level tasks. It requires real-time performance while dealing with object illumination variations and deformations. To this end, we propose a novel multi-vehicle tracking algorithm b...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/23/12244 |
| _version_ | 1827643392513802240 |
|---|---|
| author | Pengfei Lyu Minxiang Wei Yuwei Wu |
| author_facet | Pengfei Lyu Minxiang Wei Yuwei Wu |
| author_sort | Pengfei Lyu |
| collection | DOAJ |
| description | Multi-vehicle tracking is used in advanced driver assistance systems to track obstacles, which is fundamental for high-level tasks. It requires real-time performance while dealing with object illumination variations and deformations. To this end, we propose a novel multi-vehicle tracking algorithm based on a monocular camera in driver view. It follows the tracking-by-detection paradigm and integrates detection and appearance descriptors into a single network. The one-stage detection approach consists of a backbone, a modified BiFPN as a neck layer, and three prediction heads. The data association consists of a two-step matching strategy together with a Kalman filter. Experimental results demonstrate that the proposed approach outperforms state-of-the-art algorithms. It is also able to solve the tracking problem in driving scenarios while maintaining 16 FPS on the test dataset. |
| first_indexed | 2024-03-09T17:53:44Z |
| format | Article |
| id | doaj.art-da095aad3beb46c395a09be94ae9e16e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T17:53:44Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-da095aad3beb46c395a09be94ae9e16e2023-11-24T10:33:22ZengMDPI AGApplied Sciences2076-34172022-11-0112231224410.3390/app122312244Multi-Vehicle Tracking Based on Monocular Camera in Driver ViewPengfei Lyu0Minxiang Wei1Yuwei Wu2College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaCollege of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaCollege of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaMulti-vehicle tracking is used in advanced driver assistance systems to track obstacles, which is fundamental for high-level tasks. It requires real-time performance while dealing with object illumination variations and deformations. To this end, we propose a novel multi-vehicle tracking algorithm based on a monocular camera in driver view. It follows the tracking-by-detection paradigm and integrates detection and appearance descriptors into a single network. The one-stage detection approach consists of a backbone, a modified BiFPN as a neck layer, and three prediction heads. The data association consists of a two-step matching strategy together with a Kalman filter. Experimental results demonstrate that the proposed approach outperforms state-of-the-art algorithms. It is also able to solve the tracking problem in driving scenarios while maintaining 16 FPS on the test dataset.https://www.mdpi.com/2076-3417/12/23/12244multi-vehicle trackingobject detectiondata associationKalman filter |
| spellingShingle | Pengfei Lyu Minxiang Wei Yuwei Wu Multi-Vehicle Tracking Based on Monocular Camera in Driver View Applied Sciences multi-vehicle tracking object detection data association Kalman filter |
| title | Multi-Vehicle Tracking Based on Monocular Camera in Driver View |
| title_full | Multi-Vehicle Tracking Based on Monocular Camera in Driver View |
| title_fullStr | Multi-Vehicle Tracking Based on Monocular Camera in Driver View |
| title_full_unstemmed | Multi-Vehicle Tracking Based on Monocular Camera in Driver View |
| title_short | Multi-Vehicle Tracking Based on Monocular Camera in Driver View |
| title_sort | multi vehicle tracking based on monocular camera in driver view |
| topic | multi-vehicle tracking object detection data association Kalman filter |
| url | https://www.mdpi.com/2076-3417/12/23/12244 |
| work_keys_str_mv | AT pengfeilyu multivehicletrackingbasedonmonocularcameraindriverview AT minxiangwei multivehicletrackingbasedonmonocularcameraindriverview AT yuweiwu multivehicletrackingbasedonmonocularcameraindriverview |