A novel segmentation algorithm for side-scan sonar imagery with multi-object

Automatic detection of underwater objects using side-scan sonar imagery is complicated by the variability of objects, noises, and background signatures. In recent years, as the resolution of side-scan sonar is much higher than before, the sonar imagery can be generated from sonar signal for processing. The first step of underwater object detection is to segment the underwater objects from sonar imagery. In typical sonar imagery, the object contains two parts: high-light areas (echo) and the shadow behind the object. By analyzing the features of the side-scan sonar imagery, we propose a novel segmentation algorithm for multi-object side-scan sonar imagery. First we utilize a self-adaptive window to scan the imagery and calculate the variance of the window to segment the high-light areas in sonar imagery. Then the shadows of the objects are segmented by fractal dimension. At last, the final segmentation results are achieved by combining the results from the above two steps for further analysis. This segmentation algorithm is based on analyzing the structure of objects in sonar imagery and works well in the multi-object sonar imagery.