TrctrD16: deepMOTTracktor16

MOT16-01


Benchmark:

MOT16 |

Short name:

TrctrD16

Detector:

Public

Description:

The recent trend in vision-based multi-object tracking (MOT) is heading towards leveraging the representational power of deep learning to jointly learn to detect and track objects. However, existing methods train only certain sub-modules using loss functions that often do not correlate with established tracking evaluation measures such as Multi-Object Tracking Accuracy (MOTA) and Precision (MOTP). As these measures are not differentiable, the choice of appropriate loss functions for end-to-end training of multi-object tracking methods is still an open research problem. In this paper, we bridge this gap by proposing a differentiable proxy of MOTA and MOTP, which we combine in a loss function suitable for end-to-end training of deep multi-object trackers. As a key ingredient, we propose a Deep Hungarian Net (DHN) module that approximates the Hungarian matching algorithm. DHN allows to estimate the correspondence between object tracks and ground truth objects to compute differentiable proxies of MOTA and MOTP, which are in turn used to optimize deep trackers directly. We experimentally demonstrate that the proposed differentiable framework improves the performance of existing multi-object trackers, and we establish a new state-of-the-art on the MOTChallenge benchmark.

Reference:

Y. Xu, A. Osep, Y. Ban, R. Horaud, L. Leal-Taixe, X. Alameda-Pineda. How To Train Your Deep Multi-Object Tracker. In , 2019.

Last submitted:

February 01, 2020 (7 months ago)

Published:

April 16, 2020 at 14:18:00 CET

Submissions:

1

Open source:

Yes

Hardware:

GTX TITAN XP

Runtime:

1.6 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT1654.853.477.5145 (19.1)281 (37.0)2,95578,76556.897.20.5645 (11.4)1,515 (26.7)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT16-0137.838.274.45111223,82140.395.50.33584
MOT16-0366.358.777.653191,19633,84067.698.30.8205387
MOT16-0653.756.679.746862585,01056.696.20.278187
MOT16-0743.147.675.27173928,81146.095.00.886304
MOT16-0834.637.380.382429710,55237.095.40.593146
MOT16-1248.256.780.916381134,15949.997.30.12870
MOT16-1428.237.771.9108657712,57232.091.10.8120337

Raw data: