MOTDT: Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-identification
MOT16-01
Benchmark:
MOT16 |
Short name:
MOTDT
Detector:
Public
Description:
Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification
Reference:
C. Long, A. Haizhou, Z. Zijie, S. Chong. Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-identification. In ICME, 2018.
Last submitted:
October 30, 2017 (2 years ago)
Published:
July 06, 2018 at 09:12:13 CET
Submissions:
2
Project page / code:
Open source:
Yes
Hardware:
GTX 1080, 2.3 GHz, 1 Core
Runtime:
20.6 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| MOT16 | 47.6 | 50.9 | 74.8 | 115 (15.2) | 291 (38.3) | 9,253 | 85,431 | 53.1 | 91.3 | 1.6 | 792 (14.9) | 1,858 (35.0) |
Detailed performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| MOT16-01 | 40.1 | 42.8 | 71.3 | 4 | 7 | 229 | 3,564 | 44.3 | 92.5 | 0.5 | 35 | 77 |
| MOT16-03 | 55.4 | 54.7 | 74.8 | 39 | 23 | 5,288 | 40,937 | 60.8 | 92.3 | 3.5 | 361 | 848 |
| MOT16-06 | 45.1 | 51.3 | 73.6 | 34 | 98 | 587 | 5,667 | 50.9 | 90.9 | 0.5 | 82 | 219 |
| MOT16-07 | 44.1 | 48.6 | 73.6 | 6 | 16 | 644 | 8,374 | 48.7 | 92.5 | 1.3 | 101 | 263 |
| MOT16-08 | 34.6 | 39.5 | 79.0 | 10 | 23 | 669 | 10,173 | 39.2 | 90.8 | 1.1 | 104 | 143 |
| MOT16-12 | 38.9 | 51.7 | 76.3 | 12 | 35 | 768 | 4,262 | 48.6 | 84.0 | 0.9 | 35 | 76 |
| MOT16-14 | 26.4 | 41.1 | 74.0 | 10 | 89 | 1,068 | 12,454 | 32.6 | 85.0 | 1.4 | 74 | 232 |
Raw data:
