Abstract
This paper proposes a robust template-based visual tracking algorithm. The proposed algorithm combines global optimization and local optimization. The global optimization is performed in translational matching, and the local optimization is implemented by gradient descent in homography-based matching. Translational matching is robust to large translation of the reference image, although it is not robust to rotation, or scaling. In contrast, homography-based matching is robust to rotation, and scaling, although it is not robust to large translation. The proposed algorithm is a feedback combination of the two matching algorithms. Translational matching modifies the initial value for gradient descent in homography-based matching. Homography-based matching updates the reference image for translational matching. The proposed feedback combination inherits advantages from both translational matching and homography-based matching. Robot experiments demonstrate the robustness of the proposed feedback combination to composite transformations of translation, rotation, and scaling.
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.
