Abstract
This paper describes an application of the competitive associative net called CAN2 to plane extraction from range images measured by a laser range scanner (LRS). The CAN2 basically is a neural net for learning efficient piecewise linear approximation of nonlinear functions, and in this application it is utilized for learning piecewise planner (linear) surfaces from the range image. As a result of the learning, the obtained piecewise planner surfaces are more precise than the actual planner surfaces, so that we introduce a method to gather piecewise planner surfaces for reconstructing the actual planner surfaces. We apply this method to the real range image, and examine the effectiveness by means of comparing other methods, such as the USF (University of South Florida) method and a RHT (Randomized Hough Transform) based method.
