{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/robust-estimation-of-similarity","title":"Robust Estimation of Similarity Transformation for Visual Object Tracking","arxiv_id":"1712.05231","date":"2017-12-14","proceeding":null,"authors":["Yang Li","Jianke Zhu","Steven C. H. Hoi","Wenjie Song","Zhefeng Wang","Hantang Liu"],"abstract":"Most of existing correlation filter-based tracking approaches only estimate\nsimple axis-aligned bounding boxes, and very few of them is capable of\nrecovering the underlying similarity transformation. To tackle this challenging\nproblem, in this paper, we propose a new correlation filter-based tracker with\na novel robust estimation of similarity transformation on the large\ndisplacements. In order to efficiently search in such a large 4-DoF space in\nreal-time, we formulate the problem into two 2-DoF sub-problems and apply an\nefficient Block Coordinates Descent solver to optimize the estimation result.\nSpecifically, we employ an efficient phase correlation scheme to deal with both\nscale and rotation changes simultaneously in log-polar coordinates. Moreover, a\nvariant of correlation filter is used to predict the translational motion\nindividually. Our experimental results demonstrate that the proposed tracker\nachieves very promising prediction performance compared with the\nstate-of-the-art visual object tracking methods while still retaining the\nadvantages of high efficiency and simplicity in conventional correlation\nfilter-based tracking methods.","url_abs":"http://arxiv.org/abs/1712.05231v2","url_pdf":"http://arxiv.org/pdf/1712.05231v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"robust-estimation-of-similarity","repo_url":"https://github.com/ihpdep/LDES","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"robust-estimation-of-similarity","repo_url":"https://github.com/fengyang95/pyCFTrackers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"video-object-tracking","task_name":"Video Object Tracking"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-object-tracking-on-nv-vot211","task":"Video Object Tracking","dataset":"NT-VOT211","model":"LDES","rank_in_archive_order":36,"of":43,"metrics":{"AUC":"27.72","Precision":"35.19"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}