Real-time extraction of connected components in 3-D sonar range images

The´s paper describes an efficient algorithm for the segmentation of echo clusters within a dynamic 3-D sonar image. The sensor centered image is an echo management framework grouping sonar returns into spherical cells, and allowing real-time organisation of 3-D range data using inexpensive equipment. Each cell acts as a spatial key to the features related to this location. The spherical representation is effectively exploited for segmentation using an approach motivated from, connected components analysis in binary video images. A fast algorithm (linear in time complexity) based on cell connectivity between sonar beams is presented, including methods for coping with sparse data