Active 3D Segmentation through Fixation of Previously Unseen Objects
2010 (English)In: British Machine Vision Conference (BMVC), Aberystwyth, UK / [ed] Frédéric Labrosse, Reyer Zwiggelaar, Yonghuai Liu, and Bernie Tiddeman, BMVA Press , 2010, 119.1-119.11 p.Conference paper (Refereed)
We present an approach for active segmentation based on integration of several cues.It serves as a framework for generation of object hypotheses of previously unseen objectsin natural scenes. Using an approximate Expectation-Maximisation method, the appearance,3D shape and size of objects are modelled in an iterative manner, with fixation usedfor unsupervised initialisation. To better cope with situations where an object is hard tosegregate from the surface it is placed on, a flat surface model is added to the typical twohypotheses used in classical figure-ground segmentation. The framework is further extendedto include modelling over time, in order to exploit temporal consistency for bettersegmentation and to facilitate tracking.
Place, publisher, year, edition, pages
BMVA Press , 2010. 119.1-119.11 p.
Cpmputer Vision, Active Vision, Segmentation
IdentifiersURN: urn:nbn:se:kth:diva-51375DOI: 10.5244/C.24.119ScopusID: 2-s2.0-84898422381ISBN: 1-901725-40-5OAI: oai:DiVA.org:kth-51375DiVA: diva2:464053
British Machine Vision Conference (BMVC), Aberystwyth, UK
QC 201201112012-01-112011-12-122013-11-20Bibliographically approved