OBJECT RECOGNITION USING HOUGH PYRAMIDS.

Abstract

A multiresolution modeling technique is described for coarse-to-fine model-based object recognition. Each two-dimensional object is modeled as a directed acyclic graph. Each node in the graph stores a boundary segment of the object model at a selected level of spatial resolution. The root node of the graph contains the coarsest resolution representation of the boundary of the complete object; leaf nodes contain sections of the boundary at the highest resolution, and intermediate nodes contain features at intermediate levels of resolution. Arcs are directed from boundary segments at one level of resolution to spatially-related boundary segments at finer levels of resolution. A generalized Hough transform is used to match the model nodes with regions in the corresponding level of resolution in a given input image pyramid. Advantages of this approach include the use of multiresolution descriptions to model different parts of an object at different scales, the ability to detect partially occluded objects, the ability to control dynamically over the coarse-to-fine matching process, and the increase in recognition speed over conventional model-based recognition algorithms.