DA-SACOT: Domain adaptive-segmentation guided attention for correlation based object tracking

Object tracking relies on a recursive search technique around the previous target location, concurrently learning the target appearance in each frame. A failure in any frame causes a drift from its optimal target path. Thus, obtaining highly confident search regions is essential in each frame. Motivated by the strong localization property of segmented object masks, the proposed method introduces instance segmentation as an attention mechanism in object tracking framework. The core contribution of this paper is threefold: (i) a region proposal module (RPM) based on instance segmentation to focus on search proposals having a high probability of being the target, (ii) a target localization module (TLM) to localize the final target using a correlation filter and (iii) a domain adaptation technique in both RPM and TLM modules to incorporate target specific knowledge and strong discrimination ability. Extensive experimental evaluation on three benchmark datasets demonstrate a significant average gain of 2.47% in precision, 2.55% in AUC score and 2.15% in overlap score in comparison with recent competing trackers. (c) 2021 Elsevier B.V. All rights reserved.

Automated summary

This study introduces an approach that incorporates instance segmentation into object tracking framework, achieving more accurate target tracking through region proposal module and target localization module. Experimental evaluations on multiple benchmark datasets demonstrate a significant improvement in precision, AUC score, and overlap score compared to recent competing trackers.