Multiple object tracking using a dual‐attention network for autonomous driving
| Autor: | Jing Bie, Ming Gao, Yuying Jiang, Lisheng Jin |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
050210 logistics & transportation
BitTorrent tracker Computer science Mechanical Engineering 05 social sciences Feature extraction Real-time computing Transportation 010501 environmental sciences Object (computer science) 01 natural sciences Object detection Feature (computer vision) Video tracking 0502 economics and business Benchmark (computing) Law 0105 earth and related environmental sciences General Environmental Science Communication channel |
| Zdroj: | IET Intelligent Transport Systems. 14:842-848 |
| ISSN: | 1751-9578 |
| DOI: | 10.1049/iet-its.2019.0536 |
| Popis: | Multiple object tracking (MOT) remains an open and challenging problem for autonomous vehicles. Existing methods mainly ignore prior information from real traffic scenes. Here, the authors propose a novel MOT algorithm that considers traffic safety for vulnerable road users. The proposed method integrates two attention modules with a novel detection refinement strategy. Since skilled drivers pay more attention to pedestrians and cyclists, the authors employ a saliency detection method to extract scene attention region. Then, a detection refinement strategy achieved a good trade-off between parallel single object trackers and detection results. Channel attention can mine the most useful feature channel for traffic road users. In the end, the authors operate their method on the popular MOT 17 benchmark in comparison with other high-level MOT algorithms. The tracking results show that the proposed dual-attention network achieves the state-of-the-art performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text