Answers are grounded in this paper and cite their sources.
Considering that small targets in underwater images in complex environment become difficult to be distinguished and recognized due to the problems such as light refraction and water flow, a method of underwater target detection based on YOLOv5 is proposed. It employs a convolutional attention module to enhance focus on small target regions, improving feature extraction. Additionally, a progressive feature pyramid integrates low-level to high-level features, enhancing discrimination and semantic information. Lastly, incorporating the C3ConvNeXtv2 neural network enhances the model's understanding of complex underwater scenes. Experimental results demonstrate a detection accuracy of 94.2% for underwater small targets, outperforming original YOLOv5 and other deep neural networks by significant mar.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2024) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: