Posterior Instance Injection Detector for Arbitrary-Oriented Object Detection From Optical Remote-Sensing Imagery

Arbitrary-oriented object detection (AOOD) from optical remote-sensing imagery has to correctly generate delicate oriented boundary box (OBB) and meanwhile identify their specific categories. However, how to make detectors learn the delicate parameters of OBBs, especially for the crucial orientation information, and identify object categories from complex backgrounds becomes a challenging task. Therefore, in this article, to explore a better way to guide the detector to learn specific categories and parametric information of OBBs, a novel one-stage anchor-free detector called posterior instance injection detector (PIIDet) is proposed for AOOD. First, as the anchor-free manner lacks prior information, an object-aware posterior guidance (OAPG) structure is proposed to generate specific-category instances used for conditioning on OBB prediction. This structure can assist the proposed PIIDet in better learning the relative parametric information of OBBs corresponding to their specific categories. Besides, to guarantee a high-quality injection of specific category instances, a new hierarchical feature fusion module (HFFM) is developed to establish a suitable multiscale feature mapping space. Second, considering the negative optimization of angle regression, which is caused by the boundary discontinuity of angular periods and sudden shifts of the relation between width and height in the training phase, a novel binary classification embedded angle regression space (BCE-RegSpace) is devised for providing continuous angle regression space and stable relation between the width and height. Finally, extensive experiments are executed on three AOOD benchmarks (e.g., DOTA, DIOR-R, and HRSC2016), and results proved that the proposed concise one-stage anchor-free PIIDet can reach the state-of-the-art (SOTA) performance and meanwhile have an impressive inference speed.