Search

The limited number and under-representation of side-scan sonar samples hinders the training of high-performance underwater object detection models. To address this issue, in this paper, we propose a diffusion model-based method to augment side-scan sonar image samples. First, the side-scan sonar image is transformed into Gaussian distributed random noise based on its a priori discriminant. Then, the Gaussian noise is modified step by step in the inverse process to reconstruct a new sample with the same distribution as the a priori data. To improve the sample generation speed, an accelerated encoder is introduced to reduce the model sampling time. Experiments show that our method can generate a large number of representative side-scan sonar images. The generated side-scan sonar shipwreck images are used to train an underwater shipwreck object detection model, which achieves a detection accuracy of 91.5% on a real side-scan sonar dataset. This exceeds the detection accuracy of real side-scan sonar data and validates the feasibility of the proposed method. [ABSTRACT FROM AUTHOR]

Sub-bottom profiler (SBP) measurements play a very important role in marine pipeline detection and checking. However, sometimes because of bad sea conditions and complex underwater environments, only poor SBP images can be obtained. Pipeline recognition based on a poor SBP image manually is tedious and has low accuracy. In this article, based on the specific hyperbola shapes caused by pipelines on SBP images, a novel method to detect the marine pipelines automatically and robustly is presented. Two main steps are used. First, a comprehensive edge extraction method is proposed, which includes line-like structure enhancement and preliminary edge extraction, local phase calculation and phase edge extraction, final edge extraction, as well as edge processing. By applying this method, interference such as reverberation can be eliminated, and fine hyperbola edges can be obtained. Second, by referencing the theoretical hyperbola and using a buffer zone and a hyperbola contour consistency (HCC) criterion, the location of the pipeline can be determined robustly. This method was implemented and verified using data collected under real conditions. The results show that the proposed method is practicable. [ABSTRACT FROM AUTHOR]

To overcome the shortcomings of the traditional manual detection of underwater targets in side-scan sonar (SSS) images, a real-time automatic target recognition (ATR) method is proposed in this paper. This method consists of image preprocessing, sampling, ATR by integration of the transformer module and YOLOv5s (that is, TR–YOLOv5s), and target localization. By considering the target-sparse and feature-barren characteristics of SSS images, a novel TR–YOLOv5s network and a down-sampling principle are put forward, and the attention mechanism is introduced in the method to meet the requirements of accuracy and efficiency for underwater target recognition. Experiments verified the proposed method achieved 85.6% mean average precision (mAP) and 87.8% macro-F2 score, and brought 12.5% and 10.6% gains compared with the YOLOv5s network trained from scratch, and had the real-time recognition speed of about 0.068 s per image. [ABSTRACT FROM AUTHOR]