吉林大学学报（理学版）2025，Vol.63Issue(6)：1655-1662,8.DOI:10.13413/j.cnki.jdxblxb.2024514
基于改进ResNet50模型的体育图像分类
Sports Image Classification Based on Improved ResNet50 Model
摘要
Abstract
Aiming at the problem of complex image content,diverse action postures,and significant background interference in the task of sports image classification,we proposed a sports image classification algorithm based on an improved ResNet50 model.Firstly,a squeeze-and-excitation module was embedded within the residual structure to adaptively enhance key channel features and improve feature expression capability.Secondly,on this basis,a feature pyramid network was introduced to achieve effective fusion of multi-scale features,and enhance the model's perception ability of objects at different scales.Finally,classification prediction was performed through global average pooling and fully connected layers.Experimental results show that the classification accuracy of the proposed method is about 5％higher than that of the conventional ResNet50 model,fully demonstrating its robustness and superiority in handling complex actions and diverse backgrounds.The experimental results not only validate the effectiveness and feasibility of the proposed method,but also provide more reliable technical support and practical reference for applications in sports video analysis,intelligent sports training and other related fields.关键词
深度残差网络/体育图像分类/ResNet50模型/注意力机制/多尺度特征融合Key words
deep residual network/sports image classification/ResNet50 model/attention mechanism/multi-scale feature fusion分类
计算机与自动化引用本文复制引用
王立宁,蔡旭东..基于改进ResNet50模型的体育图像分类[J].吉林大学学报（理学版）,2025,63(6):1655-1662,8.基金项目
吉林省教育科学规划"十四五"课题项目(批准号:GH24045). （批准号:GH24045）
