Real-time Jellyfish Classification and Detection Algorithm Based on Improved YOLOv4-Tiny and Improved Underwater Image Enhancement Algorithm

Abstract

Abstract Large-scale jellyfish outbreaks have caused a severe threat to both human life and marine ecology. Therefore, jellyfish-detecting technology has garnered a lot of interest. The paper investigates jellyfish detection and classification algorithms based on optical imagery and deep learning theory. First, an underwater image enhancement algorithm is proposed. In addition, the article creates a dataset of 11926 photos that contains seven jellyfish species and fish. An improved YOLOv4-tiny algorithm is suggested based on the Convolutional Block Attention Module and a better training approach. According to the results, the accuracy of the improved algorithm reaches 95.01%, which is 1.55% higher than the YOLOv4 algorithm and 2.55% higher than the YOLOv4-tiny algorithm. Additionally, the detection speed is 223 FPS, substantially faster than the YOLOv4 algorithm's 43.9 FPS. In conclusion, our method can detect the jellyfish accurately and quickly. The paper establishes the groundwork for developing a real-time submarine jellyfish monitoring system.