Benchmark:

MOT17 |

Short name:

TADN

Detector:

Public

Description:

Data association is a crucial component for any multiple object tracking (MOT) method that follows the tracking-by-detection paradigm. To generate complete trajectories such methods employ a data association process to establish assignments between detections and existing targets during each timestep. Recent data association approaches try to solve a multi-dimensional linear assignment task or a network flow minimization problem or either tackle it via multiple hypotheses tracking. However, during inference an optimization step that computes optimal assignments is required for every sequence frame adding significant computational complexity in any given solution. To this end, in the context of this work we introduce Transformer-based Assignment Decision Network (TADN) that tackles data association without the need of any explicit optimization during inference. In particular, TADN can directly infer assignment pairs between detections and active targets in a single forward pass of the network. We have integrated TADN in a rather simple MOT framework, we designed a novel training strategy for efficient end-to-end training and demonstrate the high potential of our approach for online visual tracking-by-detection MOT on two popular benchmarks, i.e. MOT17 and UA-DETRAC. Our proposed approach outperforms the state-of-the-art in most evaluation metrics despite its simple nature as a tracker which lacks significant auxiliary components such as occlusion handling or re-identification.

Reference:

A. Psalta, V. Tsironis, K. Karantzalos. Transformer-based assignment decision network for multiple object tracking. In , 2022.

Last submitted:

June 23, 2022 (1 year ago)

Published:

October 13, 2022 at 10:18:31 CET

Submissions:

2

Project page / code:

https://github.com/psaltaath/tadn-mot

Open source:

Yes

Hardware:

GPU 2080ti

Runtime:

360.9 Hz

Benchmark performance:

Detailed performance:

Raw data:

download