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

Short name:

CNNTCM

Benchmark:

Description:

n/a

Hardware:

2.60GHz, 4 core

Detector:

Public

Processing:

Batch

Last submitted:

September 27, 2015 (2 years ago)

Published:

October 11, 2015 at 05:27:01 CET

Submissions:

1

Open source:

No

Project page / code:

n/a

Reference:

B. Wang, K. L. Chan, L. Wang, B. Shuai, Z. Zuo, T. Liu, G. Wang. Joint Learning of Convolutional Neural Networks and Temporally Constrained Metrics for Tracklet Association. In DeepVision Workshop (CVPR), 2016.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
29.671.81.311.2 % 44.0 % 7,78634,7337129432.60GHz, 4 corePublic
IDF1ID PrecisionID Recall
36.851.228.7

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing60.568.373.70.31346.2 % 23.1 % 663521714
PETS09-S2L249.633.970.71.84211.9 % 11.9 % 7803,886192218
ETH-Jelmoli41.352.174.50.54517.8 % 28.9 % 2331,2262938
ETH-Linthescher14.623.576.50.11974.1 % 80.2 % 727,546611
ETH-Crossing26.641.775.10.0263.8 % 69.2 % 1072512
AVG-TownCentre31.345.969.52.122616.8 % 33.2 % 9523,825137246
ADL-Rundle-118.524.173.04.63218.8 % 34.4 % 2,3035,149128121
ADL-Rundle-327.835.873.42.8449.1 % 22.7 % 1,7745,46510391
KITTI-1648.060.772.90.6170.0 % 17.6 % 1337361634
KITTI-1931.147.865.90.8628.1 % 22.6 % 8812,73271155
Venice-119.238.074.11.3170.0 % 41.2 % 5823,0911213

Raw data:


CNNTCM