ORENet: Oriented Rotation Equivariant Network for Remote Sensing Object Detection

Current state-of-the-art methods use oriented bounding boxes (OBBs) instead of horizontal bounding boxes (HBBs) for oriented object detection in remote sensing images (RSIs). However, this introduces several challenges, such as imprecise rotated feature extraction, inefficient oriented region proposal generation, unstable rotated bounding box representation, and inconsistency between loss functions and evaluation metrics. To address these challenges, we propose an oriented rotation equivariant network (ORENet) called ORENet. First, to achieve accurate feature extraction, an equivariant steerable module (ESM) is designed to guide feature learning for arbitrarily oriented objects. Second, an oriented efficient region proposal network (OERPN) is developed to improve the efficiency of proposal generation. Third, a center-offset six-parameter (COSP) representation is adopted for robust bounding box modeling. Finally, a Gaussian distance loss module (GDLM) is introduced to tackle the inconsistency issue. Compared with existing state-of-the-art approaches, our method achieves substantially reduced computational complexity while maintaining superior performance. The source code is publicly available at: https://github.com/WangXin81/ORENet2.0/