Man-made Object Detection Algorithm of Sonar Image Based on Texture Analysis

The detection of man-made object in sonar image is one of the crucial problems in the field of underwater detection. Conventional methods based on the intensity of a target echo signal will result in high false alarming rate if a mine-like object such as a rock lying on the seafloor. For the texture difference between man-made objects and natural backgrounds: natural backgrounds have always complicated texture and man-made objects have simple texture and regular shape. The multi-scale fractal theory and Zipf law were adopted to detect man-made objects in sonar image. Simulation results are presented and indicate that the detection performance of this algorithm is satisfied, which provides proper basis for underwater detection and recognition