Sparse motion segmentation using multiple six-point consistencies.
2010 (English)In: The 2nd International Workshop on Video Event Categorization, Tagging and Retrieval (VECTaR 2010), 2010, 338-348 p.Conference paper (Refereed)
We present a method for segmenting an arbitrary number of moving objects in image sequences using the geometry of 6 points in 2D to infer motion consistency. The method has been evaluated on the Hopkins155 database and surpasses current state-of-the-art methods such as SSC, both in terms of overall performance on two and three motions butalso in terms of maximum errors. The method works by nding initialclusters in the spatial domain, and then classifying each remaining pointas belonging to the cluster that minimizes a motion consistency score. In contrast to most other motion segmentation methods that are basedon an affine camera model, the proposed method is fully projective.
Place, publisher, year, edition, pages
2010. 338-348 p.
Lecture Notes in Computer Science, ISSN 0302-9743 (print), 1611-3349 (online) ; 6468
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-63170DOI: 10.1007/978-3-642-22822-3_34ISBN: 978-3-642-22821-6 (print)ISBN: 978-3-642-22822-3 (online)OAI: oai:DiVA.org:liu-63170DiVA: diva2:376722
International Workshops on Computer Vision, ACCV 2010; Queenstown; New Zealand