Tracktor++v2: Tracktor++ PyTorch 1.3


Video not available.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

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 28, 2022 (2 years ago)

Published:

March 28, 2022 at 17:25:50 CET

Submissions:

1

Open source:

Yes

Hardware:

Titan X

Runtime:

1.5 Hz

Benchmark performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOTSynth-MOT-CVPR2256.553.042.8205 (26.1)205 (26.1)10,89170,03262.891.639.746.543.873.150.173.179.41.8946 (0.0)1,594 (0.0)

Detailed performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT17-0143.740.232.0784883,10351.987.328.636.031.071.039.666.678.01.14066
MOT17-0366.158.547.458186,02529,23972.192.642.053.945.774.257.974.479.34.0269617
MOT17-0655.757.043.772441,1813,91666.886.941.646.254.062.052.067.778.51.0128234
MOT17-0759.249.740.61931,1985,57667.090.434.248.637.075.053.472.180.22.4126201
MOT17-0834.935.730.2152565312,97038.692.631.129.734.173.831.174.680.21.0138162
MOT17-1247.856.744.718313764,11152.692.449.340.755.074.743.175.880.90.43763
MOT17-1433.538.229.0167697011,11739.988.429.528.732.168.830.968.578.91.3208251

Raw data: