DP_NMS: Dynamic Programming
Video not available.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Short name:
DP_NMS
Detector:
Public
Description:
A dynamic programming (DP) approximation to the successive shortest path (SSP) solution of a network flow framework.
Parameters:
c_en=18.2882
c_ex=16.8287
c_ij=0.42473
betta=0.24366
max_it=Inf
thr_cost=9.0096
Reference:
H. Pirsiavash, D. Ramanan, C. Fowlkes. Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects. In CVPR, 2011.
Last submitted:
September 23, 2017 (7 years ago)
Published:
November 01, 2014 at 03:09:33 CET
Submissions:
3
Project page / code:
Open source:
Yes
Hardware:
2.6 GHz, 16 Cores
Runtime:
444.8 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| MOT15 | 14.5 | 19.7 | 18.2 | 43 (6.0) | 294 (40.8) | 13,171 | 34,814 | 43.3 | 66.9 | 12.4 | 27.8 | 13.1 | 75.5 | 33.5 | 51.7 | 74.5 | 2.3 | 4,537 (104.7) | 3,090 (71.3) |
Detailed performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| ADL-Rundle-1 | -2.2 | 20.3 | 19.8 | 6 | 8 | 4,213 | 5,058 | 45.6 | 50.2 | 15.1 | 27.0 | 16.4 | 73.8 | 40.6 | 39.0 | 74.6 | 8.4 | 241 | 336 |
| ADL-Rundle-3 | 23.7 | 27.0 | 23.0 | 3 | 9 | 2,193 | 5,407 | 46.8 | 68.5 | 18.5 | 29.1 | 19.2 | 74.5 | 38.1 | 47.0 | 74.8 | 3.5 | 158 | 189 |
| AVG-TownCentre | 13.4 | 15.0 | 14.5 | 8 | 93 | 1,206 | 4,682 | 34.5 | 67.2 | 8.8 | 25.7 | 9.2 | 79.9 | 28.6 | 57.6 | 73.6 | 2.7 | 299 | 414 |
| ETH-Crossing | 21.1 | 22.3 | 18.0 | 0 | 15 | 27 | 757 | 24.5 | 90.1 | 17.4 | 19.0 | 17.7 | 83.4 | 19.7 | 70.4 | 77.9 | 0.1 | 7 | 16 |
| ETH-Jelmoli | 34.8 | 31.0 | 26.0 | 8 | 13 | 314 | 1,280 | 49.5 | 80.0 | 19.6 | 34.9 | 20.8 | 73.3 | 40.8 | 59.4 | 76.9 | 0.7 | 59 | 86 |
| ETH-Linthescher | 12.4 | 15.5 | 14.6 | 3 | 157 | 164 | 7,609 | 14.8 | 89.0 | 14.4 | 14.9 | 15.0 | 80.0 | 15.3 | 71.9 | 77.9 | 0.1 | 49 | 102 |
| KITTI-16 | 26.3 | 19.4 | 15.8 | 0 | 2 | 290 | 896 | 47.3 | 73.5 | 7.5 | 34.0 | 7.7 | 75.5 | 38.1 | 62.6 | 76.2 | 1.4 | 67 | 116 |
| KITTI-19 | 17.7 | 18.2 | 16.6 | 4 | 16 | 1,388 | 2,818 | 47.3 | 64.5 | 10.4 | 28.6 | 10.9 | 70.2 | 34.7 | 48.5 | 71.0 | 1.3 | 191 | 242 |
| PETS09-S2L2 | 38.3 | 15.7 | 13.7 | 4 | 6 | 1,016 | 4,611 | 52.2 | 83.2 | 5.2 | 37.5 | 5.3 | 75.5 | 40.8 | 63.7 | 73.7 | 2.3 | 320 | 417 |
| TUD-Crossing | 57.2 | 33.6 | 27.3 | 4 | 2 | 81 | 348 | 68.4 | 90.3 | 17.0 | 44.7 | 17.7 | 71.6 | 49.0 | 67.7 | 76.5 | 0.4 | 43 | 49 |
| Venice-1 | 12.7 | 12.6 | 13.0 | 0 | 8 | 686 | 3,240 | 29.0 | 65.9 | 7.5 | 23.8 | 7.7 | 78.4 | 28.5 | 50.3 | 75.1 | 1.5 | 56 | 114 |
Raw data:
