HAM_INTP15: Historical Appearance Matching and Scene Adaptive Detection Filtering (VisBest)

TUD-Crossing


Benchmark:

Short name:

HAM_INTP15

Detector:

Public

Description:

https://github.com/yyc9268/Deep-TAMA

Reference:

Y. Yoon, A. Boragule, Y. Song, K. Yoon, M. Jeon. Online Multi-Object Tracking with Historical Appearance Matching and Scene Adaptive Detection Filtering. In IEEE AVSS, 2018.

Last submitted:

July 15, 2018 (1 year ago)

Published:

July 15, 2018 at 18:08:48 CET

Submissions:

1

Open source:

Yes

Hardware:

3.7 GHZ, 1 Core, TITAN X

Runtime:

18.7 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
2D MOT 201528.641.471.172 (10.0)317 (44.0)7,48535,91041.677.31.3460 (11.1)1,038 (25.0)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
ADL-Rundle-116.738.372.45131,9495,77038.064.53.93278
ADL-Rundle-335.539.373.53154426,07140.390.30.73956
AVG-TownCentre20.946.568.830741,7623,74947.665.93.9145301
ETH-Crossing29.046.374.02172868132.192.00.133
ETH-Jelmoli40.160.173.59152691,24051.182.80.61033
ETH-Linthescher19.830.673.691511896,95922.191.30.21745
KITTI-1639.551.672.60310390646.788.50.52042
KITTI-1920.743.666.54171,3112,87946.165.31.247193
PETS09-S2L246.040.969.4537044,38554.588.21.6121229
TUD-Crossing63.466.574.6432837066.496.30.1511
Venice-120.636.872.3167002,90036.470.41.62147

Raw data: