Side Scan Sonar Image Alignment for Complex Terrain

Underwater object detection is a typical problem in underwater exploration, widely used in fields such as underwater archaeology, underwater rescue, and underwater facility maintenance. Due to the particularity of water media, underwater object detection has brought challenges compared to land object detection. In order to overcome the limitations of water media, sonar is a commonly used tool. Ships are equipped with side scan sonar (SSS) to conduct large-scale surveys of underwater topography. Object detection is achieved by observing terrain changes. With the development of machine learning technology, the use of autonomous underwater vehicles (AUVs) equipped with side scan sonar for autonomous underwater object detection has become a trend. Usually, training machine learning algorithms requires extensive training samples. For situations where the object shape is unknown in advance, general autonomous object detection methods are difficult to be effective. It needs to develop unsupervised object detection algorithms to solve this problem, and we attempt to apply image change detection algorithms to SSS images. Therefore, in this paper, we investigate the alignment problem of SSS images. Specifically, we adopt three alignment algorithms, including RANSAC, GLU-Net and UDIS++, for underwater object detection in SSS images. To verify the feasibility and timeliness of these algorithms, we conduct extensive experiments on common multi beam SSS images and synthetic aperture sonar images.