火力与指挥控制2026，Vol.51Issue(3)：50-58,9.DOI:10.3969/j.issn.1002-0640.2026.03.007
基于多阶段特征交互的目标检测方法
Object Detection Method Based on Multi-stage Feature Interaction
摘要
Abstract
To address the challenges of small object density and occlusion in object detection in complex combat environments,an object detection method based on multi-stage feature interaction is proposed.First,a super-span multi-convolution module is constructed in the backbone network to enhance the feature representation capability of the model.Second,Efficient RepGFPN is introduced in the neck network to extract more discriminative fine-grained features.Finally,the EIoU loss function is used to reduce the deviation between the object box and the predicted box.Experiments on public datasets show that the mAP performance is improved by 4.4%and 4.1%respectively compared with the original YOLOv5s model,with an average processing speed of 75FPS.关键词
作战环境/目标检测/特征交互/特征表达/目标细节Key words
combat environment/object detection/feature interaction/feature representation/fine-grained features分类
信息技术与安全科学引用本文复制引用
杨潞霞,崔耀文,张红瑞,马永杰..基于多阶段特征交互的目标检测方法[J].火力与指挥控制,2026,51(3):50-58,9.基金项目
国家自然科学基金(62066041) （62066041）
山西省重点研发计划(202102010101008) （202102010101008）
太原师范学院研究生创新基金资助项目(SYYJSYC-2392) （SYYJSYC-2392）
