Autonomous range image-based object detection and location, and parallel surface fitting for range data

A range image processing method was developed to allow an autonomous robot to detect and locate objects. The procedure consists of talcing a range image, filtering and preprocessing the image, calculating surface normals, obtaining edge maps from both range and surface normals, combining the edge maps into an initial scene segmentation map, and analyzing each object in the scene in order to detect and locate the desired objects. While this method is reasonably fast and robust, its surface characterization is fairly crude. More elaborate surface characterization on a serial computer would be considerably slower, which is not desirable for autonomous robot operation. Hence we developed parallel techniques for surface characterization in these images. Using parallel processing techniques, the complexity and accuracy of the characterization is increased without a prohibitive cost in processing time. The method explored is a parallel implementation of a least squares QR surface fitting technique using Givens transformations. Results for both synthetic and real range data are presented.