渔业现代化2024，Vol.51Issue(6)：80-90,11.DOI:10.3969/j.issn.1007-9580.2024.06.009
基于Segformer与特征融合的水下养殖鱼类图像分割方法
Image segmentation method for underwater aquaculture fish based on segformer and feature fusion
摘要
Abstract
In aquaculture,precise fish image segmentation is crucial for growth management.However,the intricate underwater environment,plagued by image blurriness and low quality,poses significant challenges to existing segmentation methods,often leading to reduced accuracy and limited generalization capabilities.We propose an underwater fish image segmentation approach based on an improved Segformer model designated as FT-Segformer(SegFT for brevity)to address these issues.Our methodology meticulously extracts multi-scale features,spanning from fine-grained high resolutions to coarse-grained low resolutions,utilizing a sophisticated four-layered transformer block structure.Within the decoder,a feature pyramid fusion mechanism seamlessly integrates these features,bolstering contextual understanding.Subsequently,transposed convolutions refine the feature maps,restoring their dimensions and amplifying feature learning capabilities.To evaluate the model,we constructed the UAGF(Underwater Aquaculture Goldfish Fishes)dataset,a genuine underwater aquaculture environment dataset featuring ornamental goldfish,and conducted extensive validation experiments thereon.The experimental results demonstrate that SegFT outperforms existing methods across evaluation metrics such as mIoU,mPA,and mRecall,achieving improvements of 1.76%,0.39%and 0.19%,respectively.Notably,in terms of mIoU,SegFT surpasses UNet,PSPNet,HRNet,and Deeplabv3+by impressive margins of 1.92%,3.73%,3.07%and 3.58%,respectively.This study underscores our proposed method's remarkable effectiveness and robustness in complex underwater settings,outperforming existing supervised image segmentation techniques in terms of segmentation performance.关键词
智慧水产养殖/图像分割/特征融合/转置卷积/深度学习Key words
smart aquaculture/image segmentation/feature fusion/transpose convolution/deep learning分类
农业科技引用本文复制引用
苏碧仪,梅海彬,袁红春..基于Segformer与特征融合的水下养殖鱼类图像分割方法[J].渔业现代化,2024,51(6):80-90,11.基金项目
国家自然科学基金"基于海洋大数据深度学习的渔情预测模型研究(4177614)" （4177614）
