Multi-Scale Graph Channel Attention Detectors for Sonar Images in Smart Ocean

Abstract

Object detection in sonar images is challenging since the performance based on generic object detectors is generally not well on sonar datasets and the prior for the scale distribution of the objects is usually ignored. To overcome these issues, in this article, multi-scale graph channel attention (MGCA) detectors are proposed, in which multi-scale box copy-paste is designed for data augmentation and graph transformer channel attention (GTCA) based on ConvNeXt is introduced to learn powerful visual representations for sonar images. GTCA contains three basic modules: graph structure transformation module for feature maps, graph convolution module for aggregating and updating information, and feedforward network module for feature transformation. With multi-scale box copy-paste to balance scale distribution and channel attention network in a graph form to recalibrate feature maps, MGCA detectors can effectively detect multi-scale objects in sonar images through transfer learning. The MGCA detector with Cascade R-CNN (CR) detection head achieves detection accuracies of 95.6 mAP and 72.7 mmAP on the sonar common target detection (SCTD) dataset, outperforming the previous best detector with an increase of 2.8 mAP and 11.8 mmAP. Extensive experimental results and ablation studies on two sonar datasets demonstrate the superiority of the proposed method compared with state-of-the-art methods.