MOT20Det Results
Click on a measure to sort the table accordingly. See below for a more detailed description.
| Tracker | AP | MODA | MODP | FAF | TP | FP | FN | Rcll | Prcn | F1 | Hz |
| SW_YoloX_det 1. | 0.90 | 85.8 | 82.4 | 4.6 | 315,227 | 20,493 | 28,297 | 91.8 | 93.9 | 92.8 | 17.0 |
| C.-Y. Tsai, R.-Y. Wang and Y.-C. Chiu, “SW-YOLOX: A Real-Time Pedestrian Detection System Based on Sliding Window-Mixed Attention Mechanism in YOLOX Lightweight Network,” Neurocomputing, under review | |||||||||||
| SGT_det 2. | 0.90 | 84.3 | 80.6 | 5.0 | 311,920 | 22,183 | 31,604 | 90.8 | 93.4 | 92.1 | 14.3 |
| J. Hyun, M. Kang, D. Wee, D. Yeung. Detection recovery in online multi-object tracking with sparse graph tracker. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023. | |||||||||||
| Persolo_V2 3. | 0.88 | 38.3 | 79.1 | 41.4 | 317,139 | 185,547 | 26,385 | 92.3 | 63.1 | 75.0 | 29.4 |
| M. Elbatel, H. Maher, M. Abouzeid, A. Bayoumi. Persolo: A Pedestrian Is a Person Through Thick and Thin. In , 2022. | |||||||||||
| GNN_SDT 4. | 0.81 | 79.3 | 80.0 | 7.1 | 304,236 | 31,677 | 39,288 | 88.6 | 90.6 | 89.6 | 1.2 |
| Y. Wang, X. Weng, K. Kitani. Joint Detection and Multi-Object Tracking with Graph Neural Networks. In arXiv, 2020. | |||||||||||
| ViPeD20 5. | 0.80 | 46.0 | 79.0 | 31.1 | 297,101 | 139,111 | 46,277 | 86.5 | 68.1 | 76.2 | 11.2 |
| L. Ciampi, N. Messina, F. Falchi, C. Gennaro, G. Amato. Virtual to Real Adaptation of Pedestrian Detectors. In Sensors, 2020. | |||||||||||
| Sequences | Frames | Trajectories | Boxes |
| 4 | 4479 | 1501 | 765465 |
Evaluation Measures
Lower is better. Higher is better.| Measure | Better | Perfect | Description |
| AP | higher | 1 | Average Precision taken over a set of reference recall values (0:0.1:1) |
| MODA | higher | 100% | Multi-Object Detection Accuracy [1]. This measure combines false positives and missed targets. |
| MODP | higher | 100% | Multi-Object Detection Precision [1]. The misalignment between the annotated and the predicted bounding boxes. |
| FAF | lower | 0 | The average number of false alarms per frame. |
| TP | higher | #GT | The total number of true positives. |
| FP | lower | 0 | The total number of false positives. |
| FN | lower | 0 | The total number of false negatives (missed targets). |
| Rcll | higher | 100% | Ratio of correct detections to total number of GT boxes. |
| Prcn | higher | 100% | Ratio of TP / (TP+FP). |
| F1 | higher | 100% | Harmonic mean of precision and recall. |
| Hz | higher | Inf. | Processing speed (in frames per second excluding the detector) on the benchmark. The frequency is provided by the authors and not officially evaluated by the MOTChallenge. |
Legend
| Symbol | Description |
 |
This is an online (causal) method, i.e. the solution is immediately available with each incoming frame and cannot be changed at any later time. |
 |
This method used the provided detection set as input. |
 |
This method used a private detection set as input. |
 |
This entry has been submitted or updated less than a week ago. |
References:
| [1] | Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics. Image and Video Processing, 2008(1):1-10, 2008. |
