06109131

a

06109131 Pham, Minh-Tri Woodford, Oliver J. Perbet, Frank Maki, Atsuto, Gherardi Stenger, Bj\"orn Cipolla, Roberto Scale-invariant vote-based 3D recognition and registration from point clouds. Cipolla, Roberto (ed.) et al., Machine learning for computer vision. Selected papers based on the presentations at the international computer vision summer school (ICVSS 2012), Sicily, Italy, July 7--15, 2012. Berlin: Springer (ISBN 978-3-642-28660-5/hbk; 978-3-642-28661-2/ebook). Studies in Computational Intelligence 411, 137-162 (2013). 2013 Berlin: Springer EN 3D shape recognition registration SRT distance

doi:10.1007/978-3-642-28661-2_6

Summary: This chapter presents a method for vote-based 3D shape recognition and registration, in particular using mean shift on 3D pose votes in the space of direct similarity transformations for the first time. We introduce a new distance between poses in this space -- the SRT distance. It is left-invariant, unlike Euclidean distance, and has a unique, closed-form mean, in contrast to Riemannian distance, so is fast to compute. We demonstrate improved performance over the state of the art in both recognition and registration on a (real and) challenging dataset, by comparing our distance with others in a mean shift framework, as well as with the commonly used Hough voting approach.