Scholarlink

<p>The continuous decrease in global fishery resources has increased the importance of precise and efficient underwater fish monitoring technology. First, this study proposes an improved underwater target detection framework based on YOLOv8, with the aim of enhancing detection accuracy and the ability to recognize multi-scale targets in blurry and complex underwater environments. A streamlined Vision Transformer (ViT) model is used as the feature extraction backbone, which retains global self-attention feature extraction and accelerates training efficiency. In addition, a detection head named Dynamic Head (DyHead) is introduced, which enhances the efficiency of processing various target sizes through multi-scale feature fusion and adaptive attention modules. Furthermore, a dynamic loss function adjustment method called SlideLoss is employed. This method utilizes sliding window technology to adaptively adjust parameters, which optimizes the detection of challenging targets. The experimental results on the RUOD dataset show that the proposed improved model not only significantly enhances the accuracy of target detection but also increases the efficiency of target detection.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An Efficient and Dynamic Framework for Multi-Scale Target Detection of Underwater Organisms

  • 期刊论文

  • 发表日期：

    2025年12月8日

查看全文
  • Zhuang Li,
  • Guixiang Li,
  • Xiangyang Song,
  • Xinhua Wang

摘要

The continuous decrease in global fishery resources has increased the importance of precise and efficient underwater fish monitoring technology. First, this study proposes an improved underwater target detection framework based on YOLOv8, with the aim of enhancing detection accuracy and the ability to recognize multi-scale targets in blurry and complex underwater environments. A streamlined Vision Transformer (ViT) model is used as the feature extraction backbone, which retains global self-attention feature extraction and accelerates training efficiency. In addition, a detection head named Dynamic Head (DyHead) is introduced, which enhances the efficiency of processing various target sizes through multi-scale feature fusion and adaptive attention modules. Furthermore, a dynamic loss function adjustment method called SlideLoss is employed. This method utilizes sliding window technology to adaptively adjust parameters, which optimizes the detection of challenging targets. The experimental results on the RUOD dataset show that the proposed improved model not only significantly enhances the accuracy of target detection but also increases the efficiency of target detection.