Neural Network-Based Underwater Object Detection off the Coast of the Korean Peninsula

Abstract

Recently, neural network-based deep learning techniques have been actively applied to detect underwater objects in sonar (sound navigation and ranging) images. However, unlike optical images, acquiring sonar images is extremely time- and cost-intensive, and therefore securing sonar data and conducting related research can be rather challenging. Here, a side-scan sonar was used to obtain sonar images to detect underwater objects off the coast of the Korean Peninsula. For the detection experiments, we used an underwater mock-up model with a similar size, shape, material, and acoustic characteristics to the target object that we wished to detect. We acquired various side-scan sonar images of the mock-up object against the background of mud, sand, and rock to account for the different characteristics of the coastal and seafloor environments of the Korean Peninsula. To construct a detection network suitable for the obtained sonar images from the experiment, the performance of five types of feature extraction networks and two types of optimizers was analyzed. From the analysis results, it was confirmed that performance was achieved when DarkNet-19 was used as the feature extraction network, and ADAM was applied as the optimizer. However, it is possible that there are feature extraction network and optimizer that are more suitable for our sonar images. Therefore, further research is needed. In addition, it is expected that the performance of the modified detection network can be more improved if additional images are obtained.

Underwater small target detection based on dynamic convolution and attention mechanism

“…Extensive research has been undertaken in the domain of underwater acoustic image target detection (Lee et al, 2018;Zhang et al, 2021b;Kim et al, 2022;Tang et al, 2023). These endeavors encompass the design of specialized functional modules tailored to data characteristics or the adaptation and enhancement of networks originally well-suited for optical data to underwater acoustic data.…”

UTD-YOLO: underwater trash detection model based on improved YOLOv5

“…The use of optical cameras is the mainstream method of underwater target detection at present. 1,2 Intelligent submersibles can better understand their surroundings, because compared with sonar, 3 the camera can recognize underwater objects at a closer range. 4 However, poor image quality, small volume, high density, overlapping, and blurring of underwater targets often make underwater target detection difficult.…”

“…The use of optical cameras is the mainstream method of underwater target detection at present 1 , 2 . Intelligent submersibles can better understand their surroundings, because compared with sonar, 3 the camera can recognize underwater objects at a closer range 4 .…”