Title :
Application of CAN2 to plane extraction from 3D range images
Author :
Kurogi, Shuichi ; Wakeyama, Daisuke ; Koya, Hideaki ; Okada, Shota ; Inoue, Shingo ; Nishida, Takeshi
Author_Institution :
Dept. of Control Eng., Kyushu Inst. of Technol., Kitakyushu
Abstract :
An application of CAN2 (competitive associative net 2) to plane extraction from 3D range images obtained by a LRF (laser range finder) is presented. The CAN2 basically is a neural net which learns efficient piecewise linear approximation of nonlinear functions, and in this application it is utilized for learning piecewise planner surfaces from the range image. As a result of the learning, the obtained piecewise planner surfaces are much smaller and much more 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 real range images, and examine the performance and the comparative advantage to other methods.
Keywords :
approximation theory; feature extraction; laser ranging; neural nets; piecewise linear techniques; 3D range images; CAN2; competitive associative net 2; laser range finder; neural net; nonlinear functions; piecewise linear approximation; piecewise planner surfaces; plane extraction; Data mining; Function approximation; Image reconstruction; Image resolution; Mobile robots; Neural networks; Noise reduction; Piecewise linear approximation; Surface reconstruction; Uncertainty;
Conference_Titel :
Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-1820-6
Electronic_ISBN :
1098-7576
DOI :
10.1109/IJCNN.2008.4634120