多元特征提取与表征优化的遥感多尺度目标检测

Remote sensing multi-scale object detection based on multivariate feature extraction and characterization optimization

遥感目标具有较大的尺度差异性,针对其在复杂背景干扰下易导致细粒度级别多尺度特征提取困难、预测部分有效表征较弱的问题,本文基于无锚框思想,提出一种多元特征提取与表征优化的遥感多尺度目标检测方法(Multivariate Feature extraction and Characterization optimization,MFC)。在特征提取部分,设计多元特征提取模块(Multivariate Fea⁃ture Extraction,MFE)挖掘细粒度级别的多尺度特征,通过分组操作及跨组连接的方式扩大感受野、增强多个特征尺度的组合效应,并联合上下文信息进一步加强对小目标的关注;采用深层聚合结构对深浅层特征进行充分融合,以获得更全面的特征表达。在预测部分,提出一种表征优化策略(Characterization Optimization Strategy,COS),利用椭圆型映射进行标签优化以适应具有较大纵横比的遥感目标,设计坐标像素注意力组合关注多尺度目标通道、位置及像素信息,减少复杂背景干扰,使有效信息得以突出表征。在DIOR,HRRSD,RSOD数据集上进行消融及对比实验,实验结果表明:MFC模型的mAP分别达到了70.9%,90.2%和96.9%,优于大多现有方法,有效改善了误检、漏检问题,适应性和鲁棒性较强。

Remote sensing objects have large scale differences.In order to solve the problems that they are prone to lead to difficulties in fine granularity multi-scale feature extraction and weak prediction part of effective representation under complex background interference,a multi-scale remote sensing object detec⁃tion method(MFC)for multivariate feature extraction and characterization optimization based on the idea of anchor-free is proposed.In the feature extraction part,a multivariate feature extraction module(MFE)is designed to mine multi-scale features at the fine granularity level,expand the receptive field through grouping operation and cross group connection,enhance the combination effect of multiple feature scales,and further strengthen the focus on small objects by combining context information;The deep and shallow features are fully integrated by the deep layer aggregation structure to obtain a more comprehensive feature expression.In the prediction part,a characterization optimization strategy(COS)is proposed,which uses elliptical mapping to optimize tags to adapt to remote sensing targets with large aspect ratio.And a Coordi⁃nate-Pixel attention is designed to focus on multi-scale object channels,positions and pixel information,re⁃duce complex background interference,and make effective information prominent.Ablation and contrast experiments were conducted on DIOR,HRRSD and RSOD datasets.The experimental results showed that the mAP of MFC model reached 70.9%,90.2%and 96.9%respectively,which was superior to most existing methods.It effectively improved the problems of false detection and missing detection,and had strong adaptability and robustness.