Modular Decomposition and Analysis of Registration based Trackers
Abhineet Singh, Ankush Roy, Xi Zhang, Martin Jagersand

TL;DR
This paper introduces a modular framework to analyze and optimize registration-based trackers by decomposing them into appearance, state, and search modules, enabling better understanding and customization.
Contribution
It proposes a systematic decomposition of trackers into sub modules, allowing experimental optimization and clearer analysis of each component's contribution.
Findings
Decomposition reveals performance variations across different module combinations.
Default configurations are often suboptimal compared to alternative module combinations.
Open source system facilitates rapid testing and customization of tracker components.
Abstract
This paper presents a new way to study registration based trackers by decomposing them into three constituent sub modules: appearance model, state space model and search method. It is often the case that when a new tracker is introduced in literature, it only contributes to one or two of these sub modules while using existing methods for the rest. Since these are often selected arbitrarily by the authors, they may not be optimal for the new method. In such cases, our breakdown can help to experimentally find the best combination of methods for these sub modules while also providing a framework within which the contributions of the new tracker can be clearly demarcated and thus studied better. We show how existing trackers can be broken down using the suggested methodology and compare the performance of the default configuration chosen by the authors against other possible combinations…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
