DP_NMS: Dynamic Programming


Benchmark:

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

Project page / code:

Reference:

H. Pirsiavash, D. Ramanan, C. Fowlkes. Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects. In CVPR, 2011.

Processing:

Batch

Last submitted:

September 23, 2017 (2 years ago)

Published:

November 01, 2014 at 03:09:33 CET

Submissions:

3

Open source:

Yes

Hardware:

2.6 GHz, 16 Cores

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 201514.519.770.843.0294.013,17134,8144,537

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-1-3.720.370.98.04.04,7874,421438
ADL-Rundle-312.827.071.84.010.03,2845,210374
AVG-TownCentre6.615.069.410.081.08764,4821,317
ETH-Crossing20.022.374.41.016.02674828
ETH-Jelmoli29.131.073.28.013.04141,211173
ETH-Linthescher15.915.574.24.0143.01247,154233
KITTI-1623.219.473.20.02.0230895181
KITTI-198.318.266.33.014.01,4442,965490
PETS09-S2L233.815.769.43.04.09484,4101,029
TUD-Crossing48.633.672.72.02.08839385
Venice-110.912.671.70.05.09502,925189

Raw data:


DP_NMS