Tracktor++ CVPR 2019


Short name:

TracktorCV

Benchmark:

Description:

The problem of tracking multiple objects in a video sequence poses several challenging tasks. For tracking-by- detection these include object re-identification, motion pre- diction and dealing with occlusions. We present a tracker that accomplishes tracking without specifically targeting any of these tasks, in particular, we perform no training or optimization on tracking data. To this end, we exploit the bounding box regression of an object detector to predict the position of an object in the next frame, thereby converting a detector into a Tracktor. We demonstrate the extensibility of our Tracktor and provide a new state-of-the-art on three multi-object tracking benchmarks by extending it with a straightforward re-identification and camera motion compensation. This benchmark submission presents the results of our extended Tracktor++ multi-object tracker.

Hardware:

Titan X 12 GB

Detector:

Public

Processing:

Online

Last submitted:

June 12, 2019 (3 months ago)

Published:

September 23, 2019 at 10:51:39 CET

Submissions:

1

Open source:

Yes

Project page / code:

Reference:

P. Bergmann, T. Meinhardt, L. Leal-Taixé. Tracking without bells and whistles. In ICCV, 2019.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
51.376.73.624.9 % 26.0 % 16,263253,6802,5844,824Titan X 12 GBPublic
IDF1ID PrecisionID Recall
47.665.137.5

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
CVPR19-0468.057.378.31.569236.8 % 12.1 % 3,18597,6141,0381,753
CVPR19-0629.130.871.77.52637.6 % 43.7 % 7,58684,4978771,771
CVPR19-0751.346.877.20.611123.4 % 20.7 % 37915,545211377
CVPR19-0820.427.370.36.31906.3 % 54.7 % 5,11356,024458923

Raw data:

n/a


GH
TracktorCV