FANet: An Arbitrary Direction Remote Sensing Object Detection Network Based on Feature Fusion and Angle Classification

High-precision remote sensing image object detection has broad application prospects in military defense, disaster emergency, urban planning, and other fields. The arbitrary orientation, dense arrangement, and small size of objects in remote sensing images, however, lead to poor detection accuracy of existing methods. To achieve accurate detection, this article proposes an arbitrary directional remote sensing object detection method, called 'FANet,' based on feature fusion and angle classification. Initially, the angle prediction branch is introduced, and the circular smooth label (CSL) method is used to transform the angle regression problem into a classification problem, which solves the difficult problem of abrupt changes in the boundaries of the rotating frame while realizing the object frame rotation. Subsequently, to extract robust remote sensing objects, innovatively introduced a pure convolutional model as a backbone network, while Conv is replaced by GSConv to reduce the number of parameters in the model along with ensuring detection accuracy. Finally, the strengthen connection feature pyramid network (SC-FPN) is proposed to redesign the lateral connection part for deep and shallow layer feature fusion and add jump connections between the input and output of the same level feature map to enrich the feature semantic information. In addition, add a variable parameter to the original localization loss function to satisfy the bounding box regression accuracy under different intersection over union (IoU) thresholds, and thus obtain more accurate object detection. The comprehensive experimental results on two public datasets for rotated object detection, a large-scale dataset for object detection in aerial images (DOTA) and HRSC2016, demonstrate the effectiveness of our method.