Reconstruction of HOT curves from Image Sequences

D.J. Kriegman, B. Vijayakumar and J. Ponce

Conference on Computer Vision and Pattern Recongnition, June 1993.


Recently, a novel shape representation of general curved objects, which is suitable for object recognition, has been proposed; it is based on a set of surface curves, named HOT curves, defined by the locus of points where a line has high order tangency with the surface. These curves determine the structure of an object's image contours and their catastrophic changes. A nat 2 ural correspondence between a point in an intensity image and some of these curves can be directly established. This correspondence can be used for pose estimation and indexing in recognition. It also permits their 3D reconstruction from feature points on the edges detected in a sequence of images under known observer motion. This paper presents an implemented reconstruction method and experimental results.