One-Stage Detector from Coarse to Fine for Rotating Object of Remote Sensing

Rotation detection has become a popular topic in the field of remote sensing in recent years. Although quite a few progress has been made, some challenges still exist in feature alignment and regression accuracy due to large aspect ratio and arbitrary orientations of remote sensing objects, especially for the one-stage detectors. To address these problems, we propose a novel one-stage detector from coarse to fine for rotating objects. To alleviate misalignment problem between regression features and classification features, we construct the Feature Alignment Block (FAB). It can flexibly extract the features of objects with different aspect ratios by the deformable convolution and align the regression features with the corresponding classification features. Moreover, to obtain a more accurate regression estimate, we design the refined regression head (RRH) that can effectively fine-tune the coarse regression position. Experiments on the public DOTA and HRSC2016 datasets demonstrate that our proposed method shows excellent detection performance for rotating objects.