Objects In Side Scan Sonar Images Research Articles

Detection of Small Objects in Side-Scan Sonar Images Using an Enhanced YOLOv7-Based Approach

Deep learning-based object detection methods have demonstrated remarkable effectiveness across various domains. Recently, there has been growing interest in applying these techniques to underwater environments. Conventional optical imaging methods face severe limitations when operating in underwater conditions, restricting their ability to identify objects with good visibility and at close distances. Consequently, side-scan sonar (SSS) has emerged as a common equipment choice for underwater detection due to its compatibility with the characteristics of sound waves in water. This paper introduces a novel method, termed the Enhanced YOLOv7-Based Approach, for detecting small objects in SSS images. Building upon the widely-adopted YOLOv7 method, the proposed approach incorporates several enhancements aimed at improving detection accuracy. First, a dedicated detection layer tailored for small objects is added to the original network architecture. Additionally, two attention mechanisms are integrated within the backbone and neck components of the network, respectively, to strengthen the network’s focus on object features. Finally, the network features are recombined based on the BiFPN structure. Experimental results demonstrate that the proposed method outperforms mainstream object detection algorithms. In comparison to the original YOLOv7 network, it achieves a Precision of 95.5%, indicating a significant improvement of 4.8%. Moreover, its Recall reaches 87.0%, representing an enhancement of 5.1%, while the mean Average Precision (mAP) at an IoU threshold of 0.5 (mAP@.5) reaches 86.9%, reflecting a 6.7% improvement. Furthermore, the mAP@.5:.95 reaches 55.1%, a 4.8% enhancement. Therefore, the method presented in this paper enhances the performance of YOLOv7 for object detection in SSS images, providing a fresh perspective on small object detection based on SSS images and contributing to the advancement of underwater detection techniques.

Detection of small objects in sidescan sonar images based on POHMT and Tsallis entropy

SideScan Sonar (SSS) systems are able to provide near-photographic high-resolution images of underwater areas. However, automatic object detection, especially for small objects detection in such images is still difficult because of the inherent speckle noise as well as the various shapes of small objects. In this paper, by using both the Percentage Occupancy Hit-or-Miss Transform (POHMT) and the Tsallis entropy, a novel method for detecting small objects in SSS images is proposed. On one hand, the proposed method adopts the morphological POHMT to enhance faint small objects. On the other hand, the Tsallis entropy which considers the long-range interactions among particles in a system is employed to determine the optimal threshold of the POHMT. The proposed method has been evaluated on two groups of SSS images. For the first group, the average detection rate and false alarm rate of the proposed method are about 86.42% and 10.58%, respectively. For the second group, the average detection rate is 100% while the average false alarm rate is 6.25%. These results show that the proposed method performs better than the existing techniques such as the traditional hit-or-miss transform, the multilevel Tsallis entropy, and the accumulated cell average-constant false alarm rate.

Robust Object Classification in Underwater Sidescan Sonar Images by Using Reliability-Aware Fusion of Shadow Features

Detecting and classifying objects in sidescan sonar images is an important underwater application with relevance to naval transportation and defense. Properties of the imaging modality, in this case, often introduce large intraclass variabilities reducing the discriminative power of any classification algorithm and limiting the possibilities of improving classification accuracy by advances in pattern recognition only. In this work, we investigate the role of an ancillary feature set computed on object shadows and propose a scheme for exploiting this useful, but variedly reliable information for object classification. A mean-shift-clustering-based segmentation technique is used for isolating highlight and shadow segments from the images. We show the results of reliability-aware fusion of features computed on highlight and shadows on three different data sets of sidescan sonar images, to illustrate under what conditions such information might be useful.

Superellipse Fitting for the Recovery and Classification of Mine-Like Shapes in Sidescan Sonar Images

Mine-like object classification from sidescan sonar images is of great interest for mine counter measure (MCM) operations. Because the shadow cast by an object is often the most distinct feature of a sidescan image, a standard procedure is to perform classification based on features extracted from the shadow. The classification can then be performed by extracting features from the shadow and comparing this to training data to determine the object. In this paper, a superellipse fitting approach to classifying mine-like objects in sidescan sonar images is presented. Superellipses provide a compact and efficient way of representing different mine-like shapes. Through variation of a simple parameter of the superellipse function different shapes such as ellipses, rhomboids, and rectangles can be easily generated. This paper proposes a classification of the shape based directly on a parameter of the superellipse known as the squareness parameter. The first step in this procedure extracts the contour of the shadow given by an unsupervised Markovian segmentation algorithm. Afterwards, a superellipse is fitted by minimizing the Euclidean distance between points on the shadow contour and the superellipse. As the term being minimized is nonlinear, a closed-form solution is not available. Hence, the parameters of the superellipse are estimated by the Nelder-Mead simplex technique. The method was then applied to sidescan data to assess its ability to recover and classify objects. This resulted in a recovery rate of 70% (34 of the 48 mine-like objects) and a classification rate of better than 80% (39 of the 48 mine-like objects).