Abstract

This paper presents a method for vote-based 3D shape recognition and registration, in particular using mean shift on 3D pose votes in the direct similarity transformations space for the first time (i.e. the space of all 3D Cartersian coordinate systems). 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.

Paper

A New Distance for Scale-Invariant 3D Shape Recognition and Registration Minh-Tri Pham, Oliver J. Woodford, Frank Perbet, Atsuto Maki, Björn Stenger, Roberto Cipolla Cambridge Research Laboratory and University of Cambridge Published in ICCV 2011 [paper, 3.3MB]

Video

Dataset

The distance has been tested using the Toshiba CAD model point clouds dataset.

BibTeX

@INPROCEEDINGS{Pham2011, author = {Pham, M.-T. and Woodford, O.~J. and Perbet, F. and Maki, A. and Stenger, B. and Cipolla, R.}, title = {A New Distance for Scale-Invariant 3{D} Shape Recognition and Registration}, booktitle = {13th International Conference on Computer Vision}, year = {2011} }

Contacts

• Minh-Tri Pham
• Frank Perbet
• Atsuto Maki
• Björn Stenger