Dynamic NSGA-III with KRR-ANOVA Kernel Predictor for In-Motion Sonar Image Segmentation

Side-scan sonar is a widely explored technology for underwater exploration. It has a variety of utilization in research and industry, which facilitates scientific understanding, resource management, and safety of maritime activities. These images can be used in underwater image communication but suffer due to the limited acoustic channel bandwidth. The segmented images may be used instead for communication purposes but the process of segmentation of these images is hindered by influence of a large noise along with low resolution, complicating the segmen-tation process. In this work, an evolutionary dynamic many-objective optimization algorithm, KRR-DNSGA-III is proposed. This algorithm is equipped with KRR-ANOVA predictor for predicting the new solutions closer to the reference points. A modified mutation technique is also introduced for achieving faster convergence. Performance of the proposed algorithm is verified on four benchmark JY problems along with another problem from DF test suite. The algorithm is then used to segment a set of images from Seabed objects KLSG- II dataset.