Recognition of 3-D objects by forward checking constrained search

Abstract

An attempt to recognize 3-D objects from range images is described. Objects are represented by surface patches obtained by segmenting image at depth or orientation discontinuity. To find the best matching pairs between model surface patches (MSPs) and scene surface patches (SSPs), we use forward checking constrained tree search that is a sequential constrained tree search with a forward checking mechanism. It checks geometric constraints between current partial matching pairs and unexplored possible pairs and drastically reduces the number of candidate MSPs matchable to unexplored SSPs. Futhermore, it yields powerful search termination criteria. As an alternative to the sequential search method, we also applied the optimal search algorithm (A). To verify advantages of the forward checking, we evaluated the perfomance of the matching algorithms using real range images. The experimental results demonstrated significant gains in computation. Comparing with other methods, our approach is particularly advantageous for the difficult problems in that model objects are very much similar to each other. Our method detects part in difference in advance and so reduces time to discriminate the similar objects. It is confirmed by an evaluation. © 1993.