A novel method for extracting roof edges of specular polyhedra

This paper introduces a new vision technique for extracting roof edges of polyhedra having specularly reflecting surjaces. There have been many previous works on object recognition using edge information. But they can not be applied to specular objects since it is hard to acquire reliable camera images of specular objects. If there is a method which can extract the edges of specular objects, it is possibr'e to apply edge-based recognition algorithms to specular objects. To acquire the reliable edge images of specular objects> scanned double pass retroreflection method is proposed, whose main physical characteristic is curvature-sensitive. This utiliv of the phpical characteristic is motivated by the idea that roof edges can be charwterized as local surfaces of high curvature. In this pgper, the optical characteristics of double pass retroreflection are discussed and a series of simulation studies art? performed to verijj and analyze the sensor characteristics. The results from a series of simulations show the effectiveness of the proposed method.