Abstract
Correlation filter is a simple yet efficient method to deal with the visual tracking task. However, the unwanted boundary effects hinder further performance improvement. Spatially Regularized DCF (SRDCF) has been proposed to address this problem with a pre-computed spatial penalty matrix, which improves the tracking performance greatly. In this paper, aiming to achieve more accurate spatial regularization, we present our spatial adaptive regularized correlation filter (SARCF). A coarse-to-fine scale estimation approach is proposed to change the spatial penalty area, which can efficiently deal with large scale variation. Moreover, temporal regularization is introduced for long-term tracking. Experimental results show that the proposed algorithm outperforms most advanced algorithms in tracking accuracy and success rate.
Highlights
Visual tracking is a fundamental and challenging problem in computer vision with many applications, such as robotic service, video surveillance, human interaction, motion analysis, and autonomous driving, to name a few
The pioneering work is proposed by Galoogahi et al [14] who use a larger training area and a smaller filter size to learn correlation filter from cropped samples, which can significantly improve the number of samples that are not contaminated by boundary effects
Pu et al.: spatial adaptive regularized correlation filter (SARCF) for Robust Visual Tracking one hand, we introduce a rectangle-shaped spatial regularization component to address the unwanted boundary effects within the CF formulation
Summary
Visual tracking is a fundamental and challenging problem in computer vision with many applications, such as robotic service, video surveillance, human interaction, motion analysis, and autonomous driving, to name a few. The pioneering work is proposed by Galoogahi et al [14] who use a larger training area and a smaller filter size to learn correlation filter from cropped samples, which can significantly improve the number of samples that are not contaminated by boundary effects. Danelljan et al [7] propose the well-known SRDCF tracker to penalize the boundary of the filter coefficient with an inverse Gaussian-shaped spatial map. Both methods use the fixed rectangle or invariable weights to implement regularization and not changed during filter learning, which cares little to the target scale variation.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
