论文标题
点RCNN：无角框架旋转对象检测
Point RCNN: An Angle-Free Framework for Rotated Object Detection
论文作者
论文摘要
由于任意方向，大规模和纵横比变化以及物体的极端密度，航行图像中的旋转对象检测仍然具有挑战性。现有的最新旋转对象检测方法主要依赖于基于角度的检测器。但是，角度回归很容易遭受长期的边界问题。为了解决这个问题，我们提出了一个纯粹的无角框架，用于旋转对象检测，称为Point RCNN，该框架主要由Pointrpn和Pointreg组成。特别是，Pointrpn通过以粗到精细的方式转换学到的代表点来生成准确的旋转ROI（RROI），这是由重置的动机。基于学习的RROI，Pointreg执行角点完善，以更准确地检测。此外，航空图像通常在类别中严重不平衡，现有方法几乎忽略了这个问题。在本文中，我们还实验验证了重新采样罕见类别的图像将稳定训练并进一步改善检测性能。实验表明，我们的点RCNN在常用的空中数据集上实现了新的最先进的检测性能，包括DOTA-V1.0，DOTA-V1.5和HRSC2016。
Rotated object detection in aerial images is still challenging due to arbitrary orientations, large scale and aspect ratio variations, and extreme density of objects. Existing state-of-the-art rotated object detection methods mainly rely on angle-based detectors. However, angle regression can easily suffer from the long-standing boundary problem. To tackle this problem, we propose a purely angle-free framework for rotated object detection, called Point RCNN, which mainly consists of PointRPN and PointReg. In particular, PointRPN generates accurate rotated RoIs (RRoIs) by converting the learned representative points with a coarse-to-fine manner, which is motivated by RepPoints. Based on the learned RRoIs, PointReg performs corner points refinement for more accurate detection. In addition, aerial images are often severely unbalanced in categories, and existing methods almost ignore this issue. In this paper, we also experimentally verify that re-sampling the images of the rare categories will stabilize training and further improve the detection performance. Experiments demonstrate that our Point RCNN achieves the new state-of-the-art detection performance on commonly used aerial datasets, including DOTA-v1.0, DOTA-v1.5, and HRSC2016.
