Author Affiliations
1School of Aeronautics and Astronautics, Shanghai Jiao Tong University, Shanghai 200240, China2Jiangsu Automation Research Institute, Lianyungang 222061, Chinashow less
Fig. 1. Architecture of our tracker FAANet tracking framework. This framework contains four components: backbone (RepVGG), neck (CSA + FAA), head (Re-ID + detection), and association.
Fig. 2. Architecture of CSA module.
Fig. 3. Architecture of FAA module.
Fig. 4. Procedure of association between detections and tracklets.
Fig. 5. Structural re-parameterization of a RepVGG block.
Fig. 6. MOTA-IDF1-FPS comparison with other UAV-based MOT trackers on the UAVDT test dataset. The horizontal axis is FPS, the vertical axis is MOTA, and the radius of the circle is IDF1.
Fig. 7. IDF1 comparison with other UAV-based MOT trackers on the UAVDT test dataset based on scene attributes. The IDF1 of FAANet is marked outside the circle.
Fig. 8. Examples and comparison of tracking results between DeepSORT and FAANet on the UAVDT test dataset.
MOT Methods | Year | Framework | MOTA | IDF1 | MOTP | MT | ML | FP | FN | IDS | FM | FPS |
---|
SORT[1] | 2016 | Faster RCNN | 39.0 | 43.7 | 74.3 | 33.9 | 28.0 | 33,037 | 172,628 | 2350 | 5787 | Nan | DeepSORT[2] | 2017 | Faster RCNN | 40.7 | 58.2 | 73.2 | 41.7 | 23.7 | 44,868 | 155,290 | 2061 | 6432 | 15.01 | DeepAlign[20] | 2018 | Faster RCNN | 41.6 | 49.0 | 73.3 | 43.7 | 24.3 | 45,420 | 152,224 | 1546 | 3733 | 0.23 | SBMA[21] | 2019 | LSTM | 38.6 | 48.5 | 72.1 | 38.9 | 24.4 | 44,724 | 160,950 | 3489 | 11,796 | Nan | IPGAT[8] | 2020 | LSTM + CGAN | 39.0 | 49.4 | 72.2 | 37.4 | 25.2 | 42,135 | 163,837 | 2091 | 10,057 | Nan | M-CMSN-M[9] | 2020 | Faster RCNN | 43.1 | 62.6 | 73.5 | 45.3 | 22.7 | 45,900 | 147,638 | 390 | 4259 | 0.64 | Quadruplet[22] | 2021 | Faster RCNN | 40.3 | 55.0 | 74.0 | Nan | Nan | 30,065 | 150,837 | 1091 | 3057 | Nan | FAANet | Nan | RepVGG + JDE | 44.0 | 64.6 | 77.9 | 47.9 | 22.6 | 57,146 | 133,496 | 403 | 7202 | 38.24 |
|
Table 1. Results of a Quantitative Comparison among Classic MOT Methods and Recent UAV-Based Methods on the UAVDT Test Dataseta
RepVGG-B0 | CA | SA | FAA | MOTA | IDF1 | FPS |
---|
| | | | 38.2 | 56.8 | 45.70 | | | | | 39.7 | 59.2 | 43.52 | | | | | 39.3 | 59.4 | 43.41 | | | | | 40.4 | 60.2 | 41.35 | | | | | 42.1 | 63.7 | 40.54 | | | | | 44.0 | 64.6 | 38.24 |
|
Table 2. Evaluation of the Critical Factors in FAANeta
Rep | Params (106) | FLOPs (109) | MOTA | IDF1 | FPS |
---|
| 15.9 | 62.3 | 44.0 | 64.6 | 30.32 | | 14.4 | 58.3 | 44.0 | 64.6 | 38.24 |
|
Table 3. The Improvement of Re-parameterization Technique