光学精密工程2025，Vol.33Issue(8)：1289-1302,14.DOI:10.37188/OPE.20253308.1289
超融合残差行进几何感知的遥感目标检测
Remote sensing object detection algorithm based on ultra fusion residual marching geometric perception
摘要
Abstract
This paper proposed an ultra-fusion residual marching geometric perception algorithm,which aimed to solve the challenges of multi-scale,dense overlap,and uneven data distribution in remote sensing image object detection.The hyper-fusion residual marching module optimized the network structure,and its multi-level convolution operation used different scale receptive fields to capture the details of each scale of the object,enhance the model's perception of the object features,and achieve small-scale object feature extraction and large-scale object accurate positioning.The detection effect was accurately evaluated by cal-culating the geometric similarity between the detection and the real results,and the fit was carefully consid-ered in the dense overlapping scene of the object,so as to screen the final results,reduce missed detection and false detection,and improve the mAP of the algorithm.A multi-path feature fusion module was de-signed to fuse different levels of feature information,extract richer object features,enhance network repre-sentation and discrimination capabilities,and improve detection mAP and stability.The experimental re-sults on the NWPU-VHR-10 data set showed that mPrecision,mRecall,mAP and mF1 Score were in-creased by 0.041 9,0.104 0,0.045 5 and 0.085 0,respectively.The experimental results on the RSOD data set show that mPrecision,mRecall,mAP,and mF1 Score are increased by 0.022 1,0.103 4,0.061 9,and 0.087 5,respectively.The effectiveness and superiority of the proposed ultra-fusion residu-al marching geometric perception algorithm in the field of remote sensing image object detection are fully proved.关键词
遥感图像/目标检测/超融合残差行进模块/几何相似度/多路径特征融合Key words
remote sensing images/object detection/geometric similarity/multipath feature fusion/ul-tra-fusion residual marching module分类
计算机与自动化引用本文复制引用
白晨帅,白晓凤,邬开俊,王昊雯..超融合残差行进几何感知的遥感目标检测[J].光学精密工程,2025,33(8):1289-1302,14.基金项目
甘肃省自然科学基金项目(No.23JRRA913) （No.23JRRA913）
甘肃省重点研发项目(No.25YFGA047) （No.25YFGA047）
内蒙古自治区重点研发与成果转化计划项目(No.2023YFDZ0043,No.2023YFDZ0054,No.2023YFSH0043) （No.2023YFDZ0043,No.2023YFDZ0054,No.2023YFSH0043）
甘肃省教育厅:优秀研究生"创新之星"项目(No.2025CXZX-632) （No.2025CXZX-632）
