Point RCNN: An Angle-Free Framework for Rotated Object Detection
This addresses the challenge of detecting arbitrarily oriented objects in aerial images, which is crucial for applications like remote sensing, but it is incremental as it builds on existing methods like RepPoints.
The paper tackles the boundary problem in rotated object detection for aerial images by proposing an angle-free framework, Point RCNN, which achieves state-of-the-art performance on datasets like DOTA-v1.0, DOTA-v1.5, and 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.