华东交通大学学报2025，Vol.42Issue(6)：42-50,9.
ES-YOLO:基于细节特征增强与冗余特征抑制的小目标检测方法
ES-YOLO:Small Object Detection Method Based on Detail Feature Enhancement and Redundant Feature Suppression
摘要
Abstract
To address the problem of detail feature loss of low-altitude small objects during multi-layer down-sam-pling,a small object detection model ES-YOLO is proposed,based on detail feature enhancement and redundant feature suppression.The method is built upon the lightweight YOLOv5s framework and constructs a dual-feature optimization mechanism consisting of spatial detail enhancement(SDE)and redundant feature suppression(RFS)modules.SDE collaborates dynamic upsampling with transposed convolution upsampling to achieve scale-adap-tive fine recovery of spatial details and structural consistency reconstruction,enhancing small object texture and boundary information.RFS models feature dependencies across both channel and spatial dimensions to suppress background noise and redundant responses,improving feature purity and object saliency.Experimental results show that ES-YOLO achieves improvements of 12.97 percentage point and 9.22 percentage point in mAP@0.5 and mAP@[0.5:0.95],respectively,compared to YOLOv5s on the VisDrone2019 dataset.The proposed model requires only 38.59%of the GFLOPs of YOLOv8m,achieving a significant reduction in computational cost.关键词
小目标检测/细节特征增强/冗余特征抑制/YOLOKey words
small object detection/detail feature enhancement/redundant feature suppression/YOLO分类
信息技术与安全科学引用本文复制引用
朱志亮,黄欣荣,刘怡,罗文俊,朱碧堂,张小刚..ES-YOLO:基于细节特征增强与冗余特征抑制的小目标检测方法[J].华东交通大学学报,2025,42(6):42-50,9.基金项目
国家重点研发计划项目(2023YFB2603900) （2023YFB2603900）
中国铁路武汉局集团有限公司科技研究开发计划课题(24D03) （24D03）
