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

KITTI-16


Benchmark:

MOT15 |

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 (3 years 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 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT1528.641.430.472 (10.0)317 (44.0)7,48535,91041.677.333.028.336.269.031.859.175.21.3460 (11.1)1,038 (25.0)

Detailed performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
ADL-Rundle-116.738.328.95131,9495,77038.064.535.024.237.972.229.449.876.33.93278
ADL-Rundle-335.539.328.13154426,07140.390.327.429.029.571.730.768.777.20.73956
AVG-TownCentre20.946.534.330741,7623,74947.665.938.530.944.262.837.351.772.73.9145301
ETH-Crossing29.046.331.02172868132.192.040.623.744.473.924.770.878.10.133
ETH-Jelmoli40.160.139.49152691,24051.182.843.735.749.268.839.864.477.30.61033
ETH-Linthescher19.830.625.091511896,95922.191.337.916.641.373.117.170.677.30.21745
KITTI-1639.551.631.70310390646.788.530.732.833.364.835.467.177.10.52042
KITTI-1920.743.631.34171,3112,87946.165.333.929.538.263.135.550.271.61.247193
PETS09-S2L246.040.929.4537044,38554.588.223.237.725.164.840.465.473.91.6121229
TUD-Crossing63.466.547.0432837066.496.347.846.350.372.649.671.978.20.1511
Venice-120.636.828.2167002,90036.470.433.124.234.773.628.154.276.21.62147

Raw data:


HAM_INTP15