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

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

Short name:

TO

Benchmark:

Description:

n/a

Hardware:

1.6 GHZ, 8 Cores

Detector:

Public

Processing:

Batch

Last submitted:

September 02, 2015 (2 years ago)

Published:

April 19, 2017 at 14:44:27 CET

Submissions:

1

Open source:

No

Project page / code:

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.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
25.772.20.84.3 % 57.4 % 4,77940,5113836001.6 GHZ, 8 CoresPublic
IDF1ID PrecisionID Recall
32.755.523.2

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing57.251.573.10.11323.1 % 23.1 % 264291717
PETS09-S2L240.730.770.61.2427.1 % 19.0 % 5225,049145168
ETH-Jelmoli32.843.075.10.34513.3 % 42.2 % 1391,559721
ETH-Linthescher8.313.377.30.01970.5 % 87.3 % 248,16278
ETH-Crossing16.722.676.50.0260.0 % 73.1 % 283044
AVG-TownCentre18.825.970.00.52262.7 % 61.5 % 2095,53363131
ADL-Rundle-117.938.473.44.73218.8 % 31.3 % 2,3365,2703349
ADL-Rundle-331.636.274.11.1444.5 % 29.5 % 6836,2165150
KITTI-1639.948.074.40.3170.0 % 11.8 % 64951720
KITTI-1932.243.865.70.4626.5 % 33.9 % 4513,13732113
Venice-118.625.274.40.7170.0 % 47.1 % 3233,3751719

Raw data:


TO