Fish Target Detection in Underwater Blurred Scenes Based on Improved YOLOv5

In recent years, human beings have paid more and more attention to the exploration of the underwater world. As an important part of underwater resources, fish can be detected by using the fish image data collected by underwater imaging systems, which can help us better understand fish species richness and assess fish populations. In this paper, we proposed a fish target detection algorithm YOLOv5-fish for underwater blurred scenes. For underwater blurred scenes, the algorithm first uses the auto-MSRCR algorithm to enhance the acquired low-quality underwater blurred image data and obtains the enhanced fish images as the dataset for model training. Then the YOLOv5s algorithm is improved through the following methods. First, replacing the original activation function with Meta-ACON to realize the model autonomously control the nonlinearity degree of the activation function; Second, adding the Shuffle Attention mechanism to enhance the model's attention to the detection object; Third, introducing RepVGG structure to the backbone network to accelerate the model's inference speed. The experimental results show that the improved YOLOv5-fish algorithm achieves an mAP of 97.6% and a detection speed of 84 FPS, which can achieve accurate and fast detection for fish targets in underwater blurred scenes.