RTDETR-Refa: a real-time detection method for multi-breed classification of cattle

作者：Bingxuan Li, Jiandong Fang, Yvdong Zhao · 发表于：Journal of Real-Time Image Processing · 年份：2025 · DOI：10.1007/s11554-024-01613-7 · 被引用次数：13 · 研究领域：Computer Science

In the farming industry, to cope with problems such as complex pasture environments and dense targets, which lead to increased difficulty in recognising and thus quickly classifying and automatically identifying cattle breeds to improve accuracy. In this paper, an RTDETR-Refa (RepConv Efficient Faster Attention) algorithm based on ResNet18 backbone network is proposed for cattle breed classification and identification. First, new improvements are made to the ResNet18 backbone network: the Faster-Block module is introduced to improve the feature extraction network and increase the computational speed without sacrificing the accuracy; the 1×\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\times$$\end{document}1 convolution in the Faster-Block module is replaced by a 3×\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\times$$\end{document}3 convolution using the RepConv reparameterised with the RepVGG block, which makes the algorithm more lightweight and improves the inference speed. Second, in order to enhance the feature transformation and classification, the Efficient Multiscale Attention (EMA) module is added after the...