Improving Yolo5 for Real-Time Detection of Small Targets in Side Scan Sonar Images

作     者：WANG Jianjun WANG Qi GAO Guocheng QIN Ping HE Bo WANG Jianjun;WANG Qi;GAO Guocheng;QIN Ping;HE Bo

作者机构：Faculty of Information Science and EngineeringOcean University of ChinaQingdao 266100China 

出 版 物：《Journal of Ocean University of China》 (中国海洋大学学报（英文版）)

年 卷 期：2023年第22卷第6期

页      面：1551-1562页

核心收录：

学科分类：082403[工学-水声工程] 08[工学] 0824[工学-船舶与海洋工程] 

基　　金：supported by the National Key Research and Development Program of China(No.2016YFC0301400) 

主　　题：side scan sonar images autonomous underwater vehicle multisize parallel convolution module attention mechanism 

摘      要：Side scan sonar(SSS)is an important means to detect and locate seafloor *** underwater vehicles(AUVs)carrying SSS stay near the seafloor to obtain high-resolution images and provide the outline of the target for *** target feature information of an SSS image is similar to the background information,and a small target has less pixel information;therefore,accu-rately identifying and locating small targets in SSS images is *** collect the SSS images of iron metal balls(with a diameter of 1m)and rocks to solve the problem of target ***,the dataset contains two types of targets,namely,‘ball’and‘rock’.With the aim to enable AUVs to accurately and automatically identify small underwater targets in SSS images,this study designs a multisize parallel convolution module embedded in state-of-the-art *** attention mechanism transformer and a convolutional block attention module are also introduced to compare their contributions to small target detection *** performance of the proposed method is further evaluated by taking the lightweight networks Mobilenet3 and Shufflenet2 as the backbone network of *** study focuses on the performance of convolutional neural networks for the detection of small targets in SSS images,while another comparison experiment is carried out using traditional HOG+SVM to highlight the neural network’s *** study aims to improve the detection accuracy while ensuring the model efficiency to meet the real-time working requirements of AUV target detection.