{"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/tracking-using-numerous-anchor-points","title":"Tracking using Numerous Anchor points","arxiv_id":"1702.02012","date":"2017-02-07","proceeding":null,"authors":["Tanushri Chakravorty","Guillaume-Alexandre Bilodeau","Eric Granger"],"abstract":"In this paper, an online adaptive model-free tracker is proposed to track\nsingle objects in video sequences to deal with real-world tracking challenges\nlike low-resolution, object deformation, occlusion and motion blur. The novelty\nlies in the construction of a strong appearance model that captures features\nfrom the initialized bounding box and then are assembled into anchor-point\nfeatures. These features memorize the global pattern of the object and have an\ninternal star graph-like structure. These features are unique and flexible and\nhelps tracking generic and deformable objects with no limitation on specific\nobjects. In addition, the relevance of each feature is evaluated online using\nshort-term consistency and long-term consistency. These parameters are adapted\nto retain consistent features that vote for the object location and that deal\nwith outliers for long-term tracking scenarios. Additionally, voting in a\nGaussian manner helps in tackling inherent noise of the tracking system and in\naccurate object localization. Furthermore, the proposed tracker uses pairwise\ndistance measure to cope with scale variations and combines pixel-level binary\nfeatures and global weighted color features for model update. Finally,\nexperimental results on a visual tracking benchmark dataset are presented to\ndemonstrate the effectiveness and competitiveness of the proposed tracker.","url_abs":"http://arxiv.org/abs/1702.02012v2","url_pdf":"http://arxiv.org/pdf/1702.02012v2.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":"tracking-using-numerous-anchor-points","repo_url":"https://bitbucket.org/tanushri/tuna","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"tracking-using-numerous-anchor-points","repo_url":"https://github.com/sinbycos/TUNA","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-localization","task_name":"Object Localization"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}