MRDet: A Multi-Head Network for Accurate Oriented Object Detection in Aerial Images
This paper offers an incremental improvement for object detection in aerial images, which is relevant for applications like surveillance and mapping.
The paper addresses the challenge of detecting arbitrarily oriented and densely packed objects in aerial images by proposing a multi-head network called MRDet. It introduces an efficient arbitrary-oriented region proposal network (AO-RPN) and decouples the detection task into multiple subtasks, achieving promising results on DOTA and HRSC2016 benchmarks.
Objects in aerial images usually have arbitrary orientations and are densely located over the ground, making them extremely challenge to be detected. Many recently developed methods attempt to solve these issues by estimating an extra orientation parameter and placing dense anchors, which will result in high model complexity and computational costs. In this paper, we propose an arbitrary-oriented region proposal network (AO-RPN) to generate oriented proposals transformed from horizontal anchors. The AO-RPN is very efficient with only a few amounts of parameters increase than the original RPN. Furthermore, to obtain accurate bounding boxes, we decouple the detection task into multiple subtasks and propose a multi-head network to accomplish them. Each head is specially designed to learn the features optimal for the corresponding task, which allows our network to detect objects accurately. We name it MRDet short for Multi-head Rotated object Detector for convenience. We test the proposed MRDet on two challenging benchmarks, i.e., DOTA and HRSC2016, and compare it with several state-of-the-art methods. Our method achieves very promising results which clearly demonstrate its effectiveness.