Projectable Classifiers for Multi-View Object Class Recognition
2011 (English)In: 3rd International IEEE Workshop on 3D Representation and Recognition, 2011Conference paper (Refereed)
We propose a multi-view object class modeling framework based on a simplified camera model and surfels (defined by a location and normal direction in a normalized 3D coordinate system) that mediate coarse correspondences between different views. Weak classifiers are learnt relative to the reference frames provided by the surfels. We describe a weak classifier that uses contour information when its corresponding surfel projects to a contour element in the image and color information when the face of the surfel is visible in the image. We emphasize that these weak classifiers can possibly take many different forms and use many different image features. Weak classifiers are combined using AdaBoost. We evaluate the method on a public dataset , showing promising results on categorization, recognition/detection, pose estimation and image synthesis.
Place, publisher, year, edition, pages
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:kth:diva-49913DOI: 10.1109/ICCVW.2011.6130295ISI: 000300056700080ScopusID: 2-s2.0-84856685061ISBN: 978-1-4673-0063-6OAI: oai:DiVA.org:kth-49913DiVA: diva2:460615
3rd International IEEE Workshop on 3D Representation and Recognition (3dRR-11). Barcellona, Spain. November 07, 2011 - November 07, 2011
QC 201112052011-11-302011-11-302012-08-29Bibliographically approved