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


Benchmark:

Short name:

HAM_INTP15

Detector:

Public

Description:

n/a

Project page / code:

n/a

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.

Processing:

Online

Last submitted:

July 15, 2018 (1 year ago)

Published:

July 15, 2018 at 18:08:48 CET

Submissions:

1

Open source:

No

Hardware:

3.7 GHZ, 1 Core, TITAN X

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 201528.641.471.172.0317.07,48535,910460

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-116.738.372.45.013.01,9495,77032
ADL-Rundle-335.539.373.53.015.04426,07139
AVG-TownCentre20.946.568.830.074.01,7623,749145
ETH-Crossing29.046.374.02.017.0286813
ETH-Jelmoli40.160.173.59.015.02691,24010
ETH-Linthescher19.830.673.69.0151.01896,95917
KITTI-1639.551.672.60.03.010390620
KITTI-1920.743.666.54.017.01,3112,87947
PETS09-S2L246.040.969.45.03.07044,385121
TUD-Crossing63.466.574.64.03.0283705
Venice-120.636.872.31.06.07002,90021

Raw data:


HAM_INTP15