TC_SIAMESE: Tracker with selective siamese calculation

TUD-Crossing


Benchmark:

Short name:

TC_SIAMESE

Detector:

Public

Description:

n/a

Reference:

Y. Yoon, Y. Song, K. Yoon, M. Jeon. Online Multiple-Object Tracking using Selective Deep Appearance Matching. In IEEE/IEIE The International Conference on Consumer Electronics (ICCE) Asia, 2018.

Last submitted:

April 09, 2018 (2 years ago)

Published:

April 02, 2018 at 04:17:21 CET

Submissions:

4

Project page / code:

n/a

Open source:

No

Hardware:

3.7 GHZ, 4 Core

Runtime:

13.0 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
2D MOT 201520.232.671.119 (2.6)487 (67.5)6,12742,59630.775.51.1294 (9.6)825 (26.9)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
ADL-Rundle-114.638.671.2682,5495,35742.460.85.142149
ADL-Rundle-334.940.172.83146995,86642.386.01.14975
AVG-TownCentre3.612.969.011952936,5937.865.40.7732
ETH-Crossing16.027.371.70185678621.679.50.3112
ETH-Jelmoli30.950.572.43221941,55138.983.60.4741
ETH-Linthescher9.016.272.311721977,92511.383.60.2739
KITTI-1629.241.873.205911,09835.486.90.41536
KITTI-1918.932.667.01286833,60532.571.80.646154
PETS09-S2L228.931.069.10146626,08636.984.31.5104218
TUD-Crossing49.361.773.5338247057.488.50.4715
Venice-114.833.072.6186213,25928.667.71.4954

Raw data: