MDM-YOLO: Research on Object Detection Algorithm Based on Improved YOLOv4 for Marine Organisms

Abstract

Vision-based underwater object detection technology is a hot topic of current research. In order to address the issues of low accuracy and high missed rate of marine life detection, an object detection algorithm called MDM-YOLO (Marine Detection Model with YOLO) for marine organisms based on improved YOLOv4 is proposed. To improve the network's capacity for feature extraction, a multi-branch architecture CSBM is integrated into the backbone. Based on this, the feature fusion structure introduces shuffle attention to reinforce the focus on important information. The experimental results demonstrate that the MDM-YOLO algorithm increases the mean average precision (mAP) by 2.31 % compared to the YOLOv4 algorithm on the Underwater Robot Picking Contest (URPC) dataset. Moreover, on the RSOD dataset and PASCAL VOC dataset, MDM-YOLO obtained an mAP of 87.54 % and 86.87 %, respectively. According to these advancements, the MDM-YOLO model is more suitable for the identification of items on the seafloor.