Linear Programming Learned With Structured SVM

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

Short name:

LP_SSVM

Benchmark:

Description:

Min-cost network flow model with pairwise interactions; network cost is learned using structured SVM.

Hardware:

2.4GHz, 1 Core

Detector:

Public

Processing:

Batch

Last submitted:

April 20, 2015 (2 years ago)

Published:

April 21, 2015 at 04:22:07 CET

Submissions:

1

Open source:

No

Project page / code:

n/a

Reference:

S. Wang, C. Fowlkes. Learning Optimal Parameters for Multi-target Tracking with Contextual Interactions. In International Journal of Computer Vision, 2016.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
25.271.71.45.8 % 53.0 % 8,36936,9326468492.4GHz, 1 CorePublic
IDF1ID PrecisionID Recall
34.048.826.1

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing60.055.074.20.21330.8 % 15.4 % 483751820
PETS09-S2L241.527.970.51.4427.1 % 16.7 % 6294,803212249
ETH-Jelmoli39.552.474.40.54517.8 % 35.6 % 2241,2931729
ETH-Linthescher15.623.575.60.01972.5 % 79.7 % 417,4831115
ETH-Crossing24.937.575.60.0263.8 % 65.4 % 1074122
AVG-TownCentre14.724.370.11.02262.7 % 61.5 % 4595,515123141
ADL-Rundle-114.038.371.97.03221.9 % 21.9 % 3,5074,4236992
ADL-Rundle-328.036.972.93.0449.1 % 22.7 % 1,8555,3888183
KITTI-1639.241.773.60.4170.0 % 11.8 % 909242029
KITTI-1928.239.665.90.8626.5 % 29.0 % 8102,95570162
Venice-117.831.973.01.5170.0 % 41.2 % 6963,0322327

Raw data:


LP_SSVM