Tracktor++v2: Tracktor++ PyTorch 1.3

MOT16-01


Benchmark:

Short name:

Tracktor++v2

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 prediction 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.

Last submitted:

March 17, 2020 (6 months ago)

Published:

March 17, 2020 at 17:34:00 CET

Submissions:

1

Open source:

Yes

Hardware:

Titan X

Runtime:

1.6 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT1656.254.979.2157 (20.7)272 (35.8)2,39476,84457.997.80.4617 (10.7)1,068 (18.5)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT16-0142.236.578.1610233,64643.099.20.12535
MOT16-0367.761.378.960181,74331,90469.597.71.2168273
MOT16-0654.856.880.549821794,95157.197.40.182158
MOT16-0743.645.578.96161159,00544.898.50.291210
MOT16-0833.435.583.082610410,96634.598.20.278106
MOT16-1248.256.782.31739394,22949.099.00.02951
MOT16-1432.540.077.1118119112,14334.397.10.3144235

Raw data:


Tracktor++v2