Dynamic Programming

TUD-Crossing PETS09-S2L2 ETH-Jelmoli ETH-Linthescher ETH-Crossing AVG-TownCentre ADL-Rundle-1 ADL-Rundle-3 KITTI-16 KITTI-19

Short name:

DP_NMS

Benchmark:

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

Hardware:

2.6 GHz, 16 Cores

Detector:

Public

Processing:

Batch

Last submitted:

September 23, 2017 (2 months ago)

Published:

November 01, 2014 at 03:09:33 CET

Submissions:

3

Open source:

Yes

Project page / code:

Reference:

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

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
14.570.82.36.0 % 40.8 % 13,17134,8144,5373,0902.6 GHz, 16 CoresPublic
IDF1ID PrecisionID Recall
19.725.016.2

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing48.633.672.70.41315.4 % 15.4 % 883938569
PETS09-S2L233.815.769.42.2427.1 % 9.5 % 9484,4101,029705
ETH-Jelmoli29.131.073.20.94517.8 % 28.9 % 4141,211173122
ETH-Linthescher15.915.574.20.11972.0 % 72.6 % 1247,154233180
ETH-Crossing20.022.374.40.1263.8 % 61.5 % 267482824
AVG-TownCentre6.615.069.41.92264.4 % 35.8 % 8764,4821,317562
ADL-Rundle-1-3.720.370.99.63225.0 % 12.5 % 4,7874,421438394
ADL-Rundle-312.827.071.85.3449.1 % 22.7 % 3,2845,210374288
KITTI-1623.219.473.21.1170.0 % 11.8 % 230895181146
KITTI-198.318.266.31.4624.8 % 22.6 % 1,4442,965490417
Venice-110.912.671.72.1170.0 % 29.4 % 9502,925189183

Raw data:


DP_NMS