Hough-transfonn detection of lines in 3-D space

Detecting straight lines in 3-D space using a Hough transform approach involves a 4-D parameter space, which is cumbersome. In this paper, we show how to detect families of parallel lines in 3-D space at a moderate computational cost by using a (2 + 2)-D Hough space. We first find peaks in the 2-D slope parameter space; for each of these peaks, we then find peaks in the intercept parameter space. Our experimental results on range images of boxes and blocks indicate that the method works quite well. (C) 2000 Elsevier Science B.V. All rights reserved.