Recognizing Rigid Objects by Aligning Them with an Image

摘要

This paper presents an approach to recognition where an object is first aligned with an image using a small number of pairs of model and image features, and then the aligned model is compared directly against the image. For instance, the position, orientation, and scale of an object in three-space can be determined from three pairs of corresponding model and image points. By using a small fixed number of features to determine position and orientation, the alignment method avoids structuring the recognition process as an exponential search. To demonstrate the method, we present some examples of recognizing flat rigid objects with arbitrary three-dimensional position, orientation, and scale, from a single two-dimensional image. The recognition system chooses features for alignment using a scale-space segmentation of edge contours. Segments are described in terms of both their shape and the structure of the scale-space hierarchy at the next finer level, producing distinctive features for use in finding possible alignments. Finally, the method is extended to the domain of non-flat objects as well.