A Local Single-Patch Feature for Pose Estimation Using the Log-Polar Transform: Revised Version
(English)Manuscript (preprint) (Other academic)
This paper presents a local image feature, based on the log-polartransform which together with the Fourier transform enables feature matching invariant to orientation and scalechanges. It is shown that this feature can be used for poseestimation of 3D objects with unknown pose, with clutteredbackground and with occlusion. The proposed method is compared to apreviously published one and the new feature is found to be about asgood or better as the old one for this task.
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:liu:diva-57326OAI: oai:DiVA.org:liu-57326DiVA: diva2:324993
This is a revised version of http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-482002010-06-162010-06-162010-06-23Bibliographically approved