Joint Multicut Model

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

Short name:

JointMC

Benchmark:

Description:

n/a

Hardware:

3 GHZ, 1 Core

Detector:

Public

Processing:

Batch

Last submitted:

July 20, 2016 (1 year ago)

Published:

July 14, 2016 at 10:23:52 CET

Submissions:

3

Open source:

No

Project page / code:

n/a

Reference:

M. Keuper, S. Tang, Z. Yu, B. Andres, T. Brox, B. Schiele. A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects. In CoRR, 2016.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
35.671.91.823.2 % 39.3 % 10,58028,5084579693 GHZ, 1 CorePublic
IDF1ID PrecisionID Recall
45.154.438.5

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing80.960.275.30.21376.9 % 7.7 % 361631215
PETS09-S2L256.041.171.42.24223.8 % 4.8 % 9423,162142220
ETH-Jelmoli44.458.573.91.34535.6 % 28.9 % 5588371647
ETH-Linthescher25.734.775.80.319710.2 % 69.5 % 3546,2503065
ETH-Crossing21.935.073.30.4267.7 % 61.5 % 9168756
AVG-TownCentre43.162.269.82.022629.2 % 32.3 % 9223,11628213
ADL-Rundle-116.140.872.27.63240.6 % 25.0 % 3,7783,9695888
ADL-Rundle-339.343.973.41.84420.5 % 25.0 % 1,1255,0014870
KITTI-1641.756.671.31.71723.5 % 11.8 % 3506162654
KITTI-1925.745.966.51.56221.0 % 24.2 % 1,5622,34166155
Venice-128.740.072.71.91723.5 % 29.4 % 8622,3662636

Raw data:


JointMC