Learning Data Association for Multi-Object Tracking using Only Coordinates

arXiv:2403.08018v1 Announce Type: new
Abstract: We propose a novel Transformer-based module to address the data association problem for multi-object tracking. From detections obtained by a pretrained detector, this module uses only coordinates from bounding boxes to estimate an affinity score between pairs of tracks extracted from two distinct temporal windows. This module, named TWiX, is trained on sets of tracks with the objective of discriminating pairs of tracks coming from the same object from those which are not. Our module …

abstract arxiv association cs.cv data novel object temporal tracking transformer type windows