A Local Geometry-Based Descriptor for 3D Data Applied to Object Pose Estimation
2010 (English)Manuscript (preprint) (Other academic)
A local descriptor for 3D data, the scene tensor, is presentedtogether with novel applications. It can describe multiple planarsegments in a local 3D region; for the case of up to three segments itis possible to recover the geometry of the local region in terms of thesize, position and orientation of each of the segments from thedescriptor. In the setting of range data, this property makes thedescriptor unique compared to other popular local descriptors, such asspin images or point signatures. The estimation of the descriptor canbe based on 3D orientation tensors that, for example, can be computeddirectly from surface normals but the representation itself does notdepend on a specific estimation method and can also be applied to othertypes of 3D data, such as motion stereo. A series of experiments onboth real and synthetic range data show that the proposedrepresentation can be used as a interest point detector with highrepeatability. Further, the experiments show that, at such detectedpoints, the local geometric structure can be robustly recovered, evenin the presence of noise. Last we expand a framework for object poseestimation, based on the scene tensor and previously appliedsuccessfully on 2D image data, to work also on range data. Poseestimation from real range data shows that there are advantages oversimilar descriptors in 2D and that use of range data gives superiorperformance.
Place, publisher, year, edition, pages
3D analysis, local descriptor, tensor, range data
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:liu:diva-57328ISRN: LiTH-ISY-R-2951OAI: oai:DiVA.org:liu-57328DiVA: diva2:324997
See also the addendum which is found at http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-573292010-06-162010-06-162014-09-22Bibliographically approved