<XML><RECORDS><RECORD><REFERENCE_TYPE>0</REFERENCE_TYPE><REFNUM>9207</REFNUM><AUTHORS><AUTHOR>Lo,T.W.R.</AUTHOR><AUTHOR>Siebert,J.P.</AUTHOR></AUTHORS><YEAR>2009</YEAR><TITLE>Local Feature Extraction and Matching on Range Images: 2.5D SIFT</TITLE><PLACE_PUBLISHED>Computer Vision and Image Understanding (2009), doi: 10.1016/j.cviu.2009.06.005</PLACE_PUBLISHED><PUBLISHER>Elsevier Science</PUBLISHER><LABEL>Lo:2009:9207</LABEL><KEYWORDS><KEYWORD>Range images</KEYWORD></KEYWORDS<ABSTRACT>This paper presents an algorithm that extracts robust feature descriptors from 2.5D range images, in order to provide accurate point-based correspondences between compared range surfaces. The algorithm is inspired by the two-dimensional (2D) Scale Invariant Feature Transform (SIFT) in which descriptors comprising the local distribution function of the image gradient orientations, are extracted at each sam- pling keypoint location over a local measurement aperture. We adapt this concept into the 2.5D domain by concatenating the histogram of the range surface topology types, derived using the bounded [-1,1] shape index, and the histogram of the range gradient orientations to form a feature descriptor. These histograms are sampled within a measurement window centred over each mathematically derived keypoint location. Furthermore, the local slant and tilt at each keypoint location are esti- mated by extracting range surface normals, allowing the three-dimensional (3D) pose of each keypoint to be recovered and used to adapt the descriptor sampling window to provide a more reliable match under out-of-plane viewpoint rotation.</ABSTRACT><NOTES>in press</NOTES><URL>http://www.elsevier.com/wps/find/journaldescription.cws_home/622809/description#description</URL></RECORD></RECORDS></XML>