基于深度学习的遥感图像旋转目标检测研究综述  

Overview of oriented object detection based on deep learning in remote sensing

作　　者：陈天鹏 胡建文[1] Chen Tianpeng;Hu Jianwen(School of Electrical&Information Engineering,Changsha University of Science&Technology,Changsha 410114,China)

机构地区：[1]长沙理工大学电气与信息工程学院,长沙410114

出　　处：《计算机应用研究》2024年第2期329-340,共12页Application Research of Computers

基　　金：国家自然科学基金面上项目(62271087);湖南省自然科学基金资助项目(2021JJ40609);湖南省教育厅科研项目(21B0330);长沙市自然科学基金资助项目(kq2208403)。

摘　　要：由于遥感图像中的目标具有方向任意、分布密集和尺度差异大等特点,使得遥感图像目标检测成为一个颇具挑战性的难题。针对该难题,系统梳理了近三年来深度学习遥感图像旋转目标检测的相关工作。首先介绍旋转框的表示方法及其特点;然后按照特征提取网络、旋转锚框和候选框生成、标签分配及采样策略、损失函数四个方面对当前遥感图像旋转目标检测的现有方法进行分析;再对常用的遥感图像旋转目标数据集进行介绍,对比分析不同算法的性能;最后对遥感图像旋转目标检测进行了展望。Since the objects in remote sensing images have the characteristics of arbitrary direction,dense distribution and large scale differences,object detection in remote sensing images has become a challenging problem.Aiming at this problem,this paper systematically reviewed the work related to rotating object detection in deep learning remote sensing images in recent three years.Firstly,this paper introduced the representation method and characteristics of rotated bounding box.Then,it analyzed the existing methods of rotating object detection in remote sensing images from four aspects:the feature extraction network,the generation of rotating anchor and candidate bounding box,the label allocation and sampling strategy,and the loss function.Next,it introduced the commonly used remote sensing image datasets for rotated object detection,and compared the performance of different algorithms.Finally,this paper prospected rotating object detection in remote sensing images.

关 键 词：卷积神经网络 深度学习 遥感图像 旋转目标检测 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]