YES - YEt another object Segmentation: exploiting camera movement
2012 (English)In: Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on, IEEE , 2012, 2116-2121 p.Conference paper (Refereed)
We address the problem of object segmentation in image sequences where no a-priori knowledge of objects is assumed. We take advantage of robots' ability to move, gathering multiple images of the scene. Our approach starts by extracting edges, uses a polar domain representation and performs integration over time based on a simple dilation operation. The proposed system can be used for providing reliable initial segmentation of unknown objects in scenes of varying complexity, allowing for recognition, categorization or physical interaction with the objects. The experimental evaluation on both self-captured and a publicly available dataset shows the efficiency and stability of the proposed method.
Place, publisher, year, edition, pages
IEEE , 2012. 2116-2121 p.
, IEEE International Conference on Intelligent Robots and Systems, ISSN 2153-0858
Camera movement, Data sets, Dilation operation, Domain representations, Experimental evaluation, Image sequence, Initial segmentation, Multiple image, Object segmentation, Physical interactions, Unknown objects
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:kth:diva-123455DOI: 10.1109/IROS.2012.6385890ISI: 000317042702103ISBN: 978-1-4673-1736-8OAI: oai:DiVA.org:kth-123455DiVA: diva2:630065
25th IEEE\RSJ International Conference on Intelligent Robots and Systems (IROS), OCT 07-12, 2012, Algarve, PORTUGAL
QC 201306182013-06-182013-06-102013-06-18Bibliographically approved