Feature Extraction for Side Scan Sonar Image Based on Deep Learning

Abstract

There are some questions in sonar images features extract, such as strong speckle noise, low image resolution, poor image quality, and difficult target segmentation. In order to overcome the shortcomings of traditional algorithms in sonar image feature extraction, we apply Mask RCNN instance segmentation network to sonar image feature extraction. The effectiveness of the deep learning algorithm is verified by experiments. First of all, we use online and off-line data enhancement method to expand the data set. Then, we improve the residual network, and adding convolutional block attention module (CBAM), group normalization (GN) and atrous spatial pyramid pooling (ASPP) module to network. Finally, we choose the best network structure and add focal loss function to improve semantic segmentation. The final experimental results show that the Average Precision (AP) and Mean Intersection over Union (mIoU) of the proposed network are improved compared with the original network on the side scan sonar dataset.