Surfaces in Range Image Understanding (Springer Series in Perception Engineering)

Machine perception requires the digitization of physically-sensed signals. During the last ten years, digital range images have become available from a variety of sensors. This book is devoted to the problem of range image understanding with computers. Its aims are to develop a theoretical framework, devise appropriate algorithms, and demonstrate a software implementation of those algorithms that will confirm the usefulness of surfaces in range image understanding. It will be of interest to the researcher studying the theoretical concepts of image understanding, as well as the engineer who wants to implement these concepts in practical applications. Contents: Introduction Object Recognition and Segmentation Surface Curvature Characteristics From Surface Labels to Surface Primitives Description Combination and Region Merging Region Edges Experimental Results Conclusions and Future Directions Surface Curvature Invariance Theorems Discrete Intrinsic Properties Least Squares Surface Fitting Equal Angle Increment Sampling A Metric Space of Image Regions Software Implementation Iterative Region Growing Algorithm References. Front Matter....Pages i-xv Introduction....Pages 1-33 Object Recognition and Segmentation....Pages 34-62 Surface Curvature Characteristics....Pages 63-115 From Surface Labels to Surface Primitives....Pages 116-175 Description Combination and Region Merging....Pages 176-189 Region Edges....Pages 190-209 Experimental Results....Pages 210-287 Conclusions and Future Directions....Pages 289-297 Back Matter....Pages 298-340