Historical Appearance Matching and Scene Adaptive Detection Filtering (VisBest)

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

Short name:

HAM_INTP15

Benchmark:

Description:

n/a

Hardware:

3.7 GHZ, 1 Core, TITAN X

Detector:

Public

Processing:

Online

Last submitted:

July 15, 2018 (5 months ago)

Published:

July 15, 2018 at 18:08:48 CET

Submissions:

1

Open source:

No

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.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
28.671.11.310.0 % 44.0 % 7,48535,9104601,0383.7 GHZ, 1 Core, TITAN XPublic
IDF1ID PrecisionID Recall
41.459.331.9

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing63.466.574.60.11330.8 % 23.1 % 28370511
PETS09-S2L246.040.969.41.64211.9 % 7.1 % 7044,385121229
ETH-Jelmoli40.160.173.50.64520.0 % 33.3 % 2691,2401033
ETH-Linthescher19.830.673.60.21974.6 % 76.6 % 1896,9591745
ETH-Crossing29.046.374.00.1267.7 % 65.4 % 2868133
AVG-TownCentre20.946.568.83.922613.3 % 32.7 % 1,7623,749145301
ADL-Rundle-116.738.372.43.93215.6 % 40.6 % 1,9495,7703278
ADL-Rundle-335.539.373.50.7446.8 % 34.1 % 4426,0713956
KITTI-1639.551.672.60.5170.0 % 17.6 % 1039062042
KITTI-1920.743.666.51.2626.5 % 27.4 % 1,3112,87947193
Venice-120.636.872.31.6175.9 % 35.3 % 7002,9002147

Raw data:


HAM_INTP15