SiameseCNN: SiameseCNN based tracker

TUD-Crossing


Benchmark:

Short name:

SiameseCNN

Detector:

Public

Description:

n/a

Reference:

Laura Leal-Taixé, Cristian Canton-Ferrer, Konrad Schindler. Learning by Tracking: Siamese CNN for Robust Target Association. DeepVision Workshop (CVPR), Las Vegas (Nevada, USA), June 2016.

Last submitted:

November 06, 2015 (4 years ago)

Published:

July 05, 2016 at 16:47:42 CET

Submissions:

1

Project page / code:

n/a

Open source:

No

Hardware:

3 Ghz 24 cores

Runtime:

52.8 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
2D MOT 201529.034.371.261 (8.5)349 (48.4)5,16037,79838.582.10.9639 (16.6)1,316 (34.2)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
ADL-Rundle-125.641.671.6991,9994,89647.468.84.033104
ADL-Rundle-339.744.072.95151915,90641.995.70.33342
AVG-TownCentre19.39.169.0101016984,92731.176.11.6142289
ETH-Crossing27.532.874.11172070329.993.80.146
ETH-Jelmoli42.350.472.811143151,11955.981.80.73061
ETH-Linthescher16.723.274.29155937,33317.994.50.1927
KITTI-1636.937.772.6036898142.391.40.32453
KITTI-1926.738.666.24186973,15141.075.90.770276
PETS09-S2L234.527.069.7386725,36444.486.41.5282424
TUD-Crossing73.767.473.0928519782.191.40.4810
Venice-122.340.473.0073223,22129.480.60.7424

Raw data: