Objects detection for remote sensing images based on polar coordinates

Oriented and horizontal bounding box are two typical output forms in the field of remote sensing object detection. In this filed, most present state-of-the-art detectors belong to anchor-based method and perform regression tasks in Cartesian coordinates, which cause the design of oriented detectors is much more complicated than the horizontal ones, because the former usually needs to devise more complex rotated anchors, rotated Intersection-over-Union (IOU) and rotated Non Maximum Supression (NMS). In this paper, we propose a novel anchor-free detector modeled in polar coordinates to detect objects for remote sensing images, which makes the acquisition of oriented output form be as simple as the horizontal one. Our model, named Polar Remote Sensing Object Detector (P-RSDet), takes the center point of each object as the pole point and the horizontal positive direction as the polar axis to establish the polar coordinate system. The detection of one object can be regarded as predictions of one polar radius and two polar angles for both horizontal and oriented bounding box by our model. P-RSDet realizes the combination of two output forms with minimum cost. Experiments show that our P-RSDet achieves competitive performances on DOTA, UCAS-AOD and NWPU VHR-10 datasets on both horizontal and oreinted detection fileds.