MOT17Det Results
Click on a measure to sort the table accordingly. See below for a more detailed description.
| Detector | AP | MODA | MODP | FAF | TP | FP | FN | Precision | Recall |
| DectFrCNN 1. | 0.59 | -2.9 | 73.9 | 13.1 | 74,503 | 77,785 | 40,061 | 48.9 | 65.0 |
| Anonymous submission | |||||||||
| ACF 2. | 0.32 | 18.1 | 72.1 | 2.8 | 37,312 | 16,539 | 77,252 | 69.3 | 32.6 |
| P. Dollar, R. Appel, S. Belongie, P. Perona. Fast Feature Pyramids for Object Detection. In TPAMI, 2014. | |||||||||
| DPM 3. | 0.61 | 31.2 | 75.8 | 7.1 | 78,007 | 42,308 | 36,557 | 64.8 | 68.1 |
| P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan. Object Detection with Discriminatively Trained Part Based Models. In TPAMI, 2010. | |||||||||
| PD_MASK 4. | 0.57 | 33.0 | 76.0 | 9.3 | 92,871 | 55,120 | 21,693 | 62.8 | 81.1 |
| Anonymous submission | |||||||||
| HDGP 5. | 0.45 | 42.1 | 76.4 | 1.3 | 55,680 | 7,436 | 58,884 | 88.2 | 48.6 |
| A. Garcia-Martin, R. Sanchez-Matilla, J. Martinez. Hierarchical detection of persons in groups. In Signal, Image and Video Processing, 2017. | |||||||||
| MDPM 6. | 0.61 | 43.5 | 76.0 | 4.2 | 74,546 | 24,659 | 40,018 | 75.1 | 65.1 |
| Anonymous submission | |||||||||
| uvdetector 7. | 0.68 | 43.6 | 75.3 | 5.8 | 84,348 | 34,376 | 30,216 | 71.0 | 73.6 |
| Uncanny Vision, Bangalore, India | |||||||||
| FRCNNRS101 8. | 0.52 | 47.1 | 75.5 | 1.8 | 64,947 | 10,931 | 49,617 | 85.6 | 56.7 |
| Anonymous submission | |||||||||
| ICO 9. | 0.71 | 56.1 | 77.2 | 2.7 | 80,395 | 16,153 | 34,169 | 83.3 | 70.2 |
| Anonymous submission | |||||||||
| YLHDv2 10. | 0.46 | 56.9 | 73.2 | 2.5 | 80,093 | 14,938 | 34,471 | 84.3 | 69.9 |
| Anonymous submission | |||||||||
| Detector | AP | MODA | MODP | FAF | TP | FP | FN | Precision | Recall |
| yolov3 11. | 0.77 | 62.9 | 74.7 | 3.7 | 94,146 | 22,047 | 20,418 | 81.0 | 82.2 |
| Anonymous submission | |||||||||
| SEN 12. | 0.80 | 65.0 | 78.1 | 3.5 | 95,230 | 20,714 | 19,334 | 82.1 | 83.1 |
| Anonymous submission | |||||||||
| KDNT 13. | 0.89 | 67.1 | 80.1 | 4.8 | 105,473 | 28,623 | 9,091 | 78.7 | 92.1 |
| F. Yu, W. Li, Q. Li, Y. Liu, X. Shi, J. Yan. POI: Multiple Object Tracking with High Performance Detection and Appearance Feature. In BMTT, SenseTime Group Limited, 2016. | |||||||||
| Dector1 14. | 0.71 | 68.4 | 78.4 | 1.1 | 84,864 | 6,459 | 29,700 | 92.9 | 74.1 |
| Anonymous submission | |||||||||
| FRCNN 15. | 0.72 | 68.5 | 78.0 | 1.7 | 88,601 | 10,081 | 25,963 | 89.8 | 77.3 |
| S. Ren, K. He, R. Girshick, J. Sun. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In NIPS, 2015. | |||||||||
| MFRCNN 16. | 0.71 | 69.2 | 78.4 | 1.1 | 86,086 | 6,774 | 28,478 | 92.7 | 75.1 |
| Anonymous submission | |||||||||
| ZIZOM 17. | 0.81 | 72.0 | 79.8 | 2.2 | 95,414 | 12,990 | 19,139 | 88.0 | 83.3 |
| C. Lin, L. Jiwen, G. Wang, J. Zhou. Graininess-Aware Deep Feature Learning for Pedestrian Detection. In ECCV, 2018. | |||||||||
| MKDNT 18. | 0.89 | 75.9 | 80.3 | 2.7 | 103,143 | 16,185 | 11,421 | 86.4 | 90.0 |
| Anonymous submission | |||||||||
| YTLAB 19. | 0.89 | 76.7 | 80.2 | 2.8 | 104,555 | 16,685 | 10,009 | 86.2 | 91.3 |
| Anonymous submission | |||||||||
| SDP 20. | 0.81 | 76.9 | 78.0 | 1.3 | 95,699 | 7,599 | 18,865 | 92.6 | 83.5 |
| F. Yang, W. Choi, Y. Lin. Exploit All the Layers: Fast and Accurate CNN Object Detector With Scale Dependent Pooling and Cascaded Rejection Classifiers. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. | |||||||||
| Detector | AP | MODA | MODP | FAF | TP | FP | FN | Precision | Recall |
| MSDP 21. | 0.81 | 77.4 | 78.1 | 0.8 | 93,738 | 5,024 | 20,826 | 94.9 | 81.8 |
| Anonymous submission | |||||||||
Benchmark Statistics
| Sequences | Frames | Boxes |
| 7 | 5919 | 188076 |
Evaluation Measures
Lower is better. Higher is better.| Measure | Better | Perfect | Description |
| AP | higher | 100 % | Average Precision taken over a set of reference recall values (0:0.1:1) |
| MODA | higher | 100 % | Multiple Object Detection Accuracy [1]. This measure combines false positives and missed targets. |
| MOTP | higher | 100 % | Multiple 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). |
| Precision | higher | 100 % | Ratio of TP / (TP+FP). |
| Recall | higher | 100 % | Ratio of correct detections to total number of GT boxes. |
Legend
| Symbol | Description |
 |
This entry has been submitted or updated less than a week ago. |
