智能系统学报2025，Vol.20Issue(4)：813-821,9.DOI:10.11992/tis.202405001
基于高效特征提取和大感受野的无人机航拍图像目标检测
Uav aerial image target detection based on high-efficiency feature extraction and large receptive field
摘要
Abstract
Aiming at the problems of small targets,target occlusion and complex background in UAV aerial images,a target detection network based on high-efficiency feature extraction and large receptive field(EFLF-Net)was proposed.Firstly,the missed detection rate of small targets was reduced by optimizing the detection layer architecture.Then,the new building blocks were integrated in the backbone network to improve the efficiency of feature extraction.Then,a content-aware feature recombination module and a large selective kernel network were introduced to enhance the con-text-aware ability of the neck network for occluded targets.Finally,the Wise-IoU loss function was used to optimize the bounding box regression stability.Experimental results on the VisDrone2019 dataset show that EFLF-Net improves the average precision by 5.2％compared with the basic algorithm.Compared with the existing representative target detec-tion algorithms,the proposed method has better detection effects for UAV aerial images with small targets,mutual oc-clusion of targets and complex backgrounds.关键词
无人机航拍图像/小目标检测/特征提取/多尺度变化/YOLOv8/上下文信息/感受野/损失函数Key words
drone aerial images/small target detection/feature extraction/multi-scale variation/YOLOv8/context in-formation/receptive field/loss function分类
信息技术与安全科学引用本文复制引用
沈朕宇,朱凤华,王知学,沈震,熊刚..基于高效特征提取和大感受野的无人机航拍图像目标检测[J].智能系统学报,2025,20(4):813-821,9.基金项目
国家自然科学基金项目(U24A20277) （U24A20277）
北京市自然科学基项目(L241016) （L241016）
重庆市交通科技项目(CQJT-CZKJ2024-04). （CQJT-CZKJ2024-04）
