Tracktor++: Tracktor++

CVPR19-04


Short name:

Tracktor++

Detector:

Public

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.

Reference:

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

Processing:

Online

Last submitted:

August 06, 2019 (10 months ago)

Published:

August 06, 2019 at 17:18:03 CET

Submissions:

1

Open source:

Yes

Hardware:

Titan X 12 GB

Runtime:

0.7 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
CVPR 2019 Tracking Challenge51.347.676.7313 (24.9)326 (26.0)16,263253,68054.795.03.62,584 (47.2)4,824 (88.2)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
CVPR19-0468.057.378.3255843,18597,61469.398.61.51,0381,753
CVPR19-0629.130.871.7201157,58684,49735.686.07.58771,771
CVPR19-0751.346.877.2262337915,54553.097.90.6211377
CVPR19-0820.427.370.3121045,11356,02427.680.76.3458923

Raw data: