{"id":306,"date":"2013-07-30T12:19:03","date_gmt":"2013-07-30T10:19:03","guid":{"rendered":"http:\/\/www.mpateraki.org\/?p=306"},"modified":"2015-03-03T09:33:53","modified_gmt":"2015-03-03T07:33:53","slug":"robust-multi-hypothesis-3d-object-pose-tracking","status":"publish","type":"post","link":"https:\/\/mpateraki.org\/?p=306","title":{"rendered":"Robust multi-hypothesis 3D object pose tracking"},"content":{"rendered":"

Chliveros G., Pateraki M.<\/strong>, Trahanias P., 2013. Robust multi-hypothesis 3D object pose tracking. In Proc. of the 9th Intl. Conference on Computer Vision Systems (ICVS), LNCS 7963, pp. 234-243, Springer-Verlag, St. Petersburg, Russia, July 16-18, 2013. [doi<\/a>] [pdf<\/a>] [bib<\/a>]<\/p>\n

Abstract:<\/p>\n

This paper tackles the problem of 3D object pose tracking\u00a0from monocular cameras. Data association is performed via a variant of\u00a0the Iterative Closest Point algorithm, thus making it robust to noise and\u00a0other artifacts. We re-initialise the hypothesis space based on the resulting\u00a0re-projection error between hypothesized models and observed image\u00a0objects. This is performed through a non-linear minimisation step after\u00a0correspondences are found. The use of multi-hypotheses and correspondences\u00a0refinement, lead to a robust framework. Experimental results with\u00a0benchmark image sequences indicate the effectiveness of our framework.<\/p>\n\n\n\n
\"\"<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n