TO: Leveraging single for multi-target tracking using a novel trajectory overlap affinity measure

TUD-Crossing


Benchmark:

Short name:

TO

Detector:

Public

Description:

n/a

Reference:

S. Manen, R. Timofte, D. Dai, L. Gool. Leveraging single for multi-target tracking using a novel trajectory overlap affinity measure. In 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), 2016.

Last submitted:

September 02, 2015 (4 years ago)

Published:

April 19, 2017 at 14:44:27 CET

Submissions:

1

Project page / code:

n/a

Open source:

No

Hardware:

1.6 GHZ, 8 Cores

Runtime:

5.0 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
2D MOT 201525.732.772.231 (4.3)414 (57.4)4,77940,51134.181.40.8383 (11.2)600 (17.6)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
ADL-Rundle-117.938.473.46102,3365,27043.463.34.73349
ADL-Rundle-331.636.274.12136836,21638.985.31.15150
AVG-TownCentre18.825.970.061392095,53322.688.50.563131
ETH-Crossing16.722.676.5019283017.298.90.044
ETH-Jelmoli32.843.075.16191391,55938.587.60.3721
ETH-Linthescher8.313.377.31172248,1628.697.00.078
KITTI-1639.948.074.4026495144.192.10.3720
KITTI-1932.243.865.74214513,13741.383.00.432113
PETS09-S2L240.730.770.6385225,04947.689.81.2145168
TUD-Crossing57.251.573.1332642961.196.30.11717
Venice-118.625.274.4083233,37526.078.60.71719

Raw data: