Showing papers by "Stan Z. Li published in 1992"
••
TL;DR: Experiments are shown to illustrate the matching algorithm and to demonstrate that the approach is truly invariant to arbitrary translations, rotations, and scale changes under noise.
140 citations
••
19 May 1992TL;DR: A method of matching and recognizing aerial road network images based on road network models based on attributed relational graphs is developed using a relaxation labelling algorithm, which optimises a criterion of similarity.
Abstract: In this paper, we develop a method of matching and recognizing aerial road network images based on road network models. We use attributed relational graphs to describe images and models. The correspondences are found using a relaxation labelling algorithm, which optimises a criterion of similarity.
31 citations
••
TL;DR: An unconventional approach to range image understanding is proposed, unconventional in the sense that object matching and recognition is performed before the image is segmented, and the problem of finding the optimal point-wise mapping is formulated as one of constrained optimization.
16 citations