SAR: Single-Stage Anchor-Free Rotating Object Detection

doi:10.1109/access.2020.3037350

CIOMP OpenIR

	SAR: Single-Stage Anchor-Free Rotating Object Detection
	J. Y. Lu,T. Li,J. Y. Ma,Z. Q. Li and H. G. Jia
	2020
发表期刊	Ieee Access
ISSN	2169-3536
卷号	8 页码:205902-205912
摘要	As object detection is widely adopted in aerial images, scene texts and other fields, rotating object detection plays an important role and draws attention since it can provide highly accurate orientation and scale information. In this article, we propose a novel and simple baseline to effectively conduct rotating object detection. First, we design a brand-new representation for rotating objects by using a circle cut horizontal rectangle (CCH). The CCH ensures that the regression parameters will not exceed the defined domain and avoids vertex sorting, thus solving some problems in current common representations, including the boundary problem and order problem, and improving the robustness. Second, we design a lightweight head based on the CCH to add the rotating regression to classic benchmark in an almost cost-free manner and propose a single-stage anchor-free rotating (SAR) object detection convolutional neural network. Finally, we demonstrate the details of our method by applying it to data sets with different scenarios. The experiments confirm that our method achieves competitive accuracy and state-of-the-art speed in aerial image and scene text detection.
DOI	10.1109/access.2020.3037350
URL	查看原文
收录类别	SCI
语种	英语
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/64868
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	J. Y. Lu,T. Li,J. Y. Ma,Z. Q. Li and H. G. Jia. SAR: Single-Stage Anchor-Free Rotating Object Detection[J]. Ieee Access,2020,8:205902-205912.
APA	J. Y. Lu,T. Li,J. Y. Ma,Z. Q. Li and H. G. Jia.(2020).SAR: Single-Stage Anchor-Free Rotating Object Detection.Ieee Access,8,205902-205912.
MLA	J. Y. Lu,T. Li,J. Y. Ma,Z. Q. Li and H. G. Jia."SAR: Single-Stage Anchor-Free Rotating Object Detection".Ieee Access 8(2020):205902-205912.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Lu-2020-SAR_ Single-（3281KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载