ADAPTIVE MULTISCALE FEATURE-EXTRACTION FROM RANGE DATA

作     者：PARVIN, B MEDIONI, G 

作者机构：Institute of Robotics and Intelligent Systems Department of Electrical Engineering Powel Hall 233 University of Southern California Los Angeles California 90089-0272 USA 

出 版 物：《COMPUTER VISION GRAPHICS AND IMAGE PROCESSING》 (Comput Vision Graphics Image Process)

年 卷 期：1989年第45卷第3期

页      面：346-356页

核心收录：

主　　题：Image Processing 

摘      要：We present a method to extract meaningful features from range images which introduces some novel ideas: Firstm our primitives are a richer set than the usual one, as we not only extract high frequences events, which correspond to jump boundaries and sharp creases, but also low frequency events such as smooth ridges and ravines. These last features are generally discarded as they tend to hide in noise; however, they provide a coarse descriotion of the shape, and we believe they may help in inferring volumetric description. The method works at multiple scales to improve reliability, and we have designed a control strategy to automatically select the most appropriate mask size. We present results on images of different levels of complexity from three different sensors.