Toward a General 3-D Matching Engine: Multiple Models, Complex Scenes, and Efficient Data Filtering
Abstract
We present a 3-D shape-based object recognition system for simultaneous recognition of multiple objects in scenes containing clutter and occlusion. Recognition is based on matching surfaces by matching points using the spin-image representation. The spin-image is a data level shape descriptor that is used to match surfaces represented as surface meshes. Starting with the general matching framework introduced earlier, we present a compression scheme for spin-images; this scheme results in efficient multiple object recognition which we verify with results showing the simultaneous recognition of multiple objects from a library of 20 models. In addition, we demonstrate the robust performance of recognition in the presence of clutter and occlusion through analysis of recognition trials on 100 scenes. We address efficiency and generality through two extensions to the basic matching scheme: fast filtering of scene points and processing of general data sets.
BibTeX
@workshop{Johnson-1998-14795,author = {Andrew Johnson and Owen Carmichael and Daniel Huber and Martial Hebert},
title = {Toward a General 3-D Matching Engine: Multiple Models, Complex Scenes, and Efficient Data Filtering},
booktitle = {Proceedings of DARPA Image Understanding Workshop (IUW '98)},
year = {1998},
month = {November},
pages = {1097 - 1107},
}