Rotated Object Detection with Circular Gaussian Distribution

doi:10.3390/electronics12153265

	Rotated Object Detection with Circular Gaussian Distribution
	Xu, Hang 1; Liu, Xinyuan 2; Ma, Yike 2; Zhu, Zunjie 1,3; Wang, Shuai 1,3; Yan, Chenggang 1,3; Dai, Feng 2
	2023-08-01
发表期刊	ELECTRONICS
卷号	12 期号:15 页码:12
摘要	Rotated object detection is a challenging task due to the difficulties of locating the rotated objects and separating them effectively from the background. For rotated object prediction, researchers have explored numerous regression-based and classification-based approaches to predict a rotation angle. However, both paradigms are constrained by some flaws that make it difficult to accurately predict angles, such as multi-solution and boundary issues, which limits the performance upper bound of detectors. To address these issues, we propose a circular Gaussian distribution (CGD)-based method for angular prediction. We convert the labeled angle into a discrete circular Gaussian distribution spanning a single minimal positive period, and let the model predict the distribution parameters instead of directly regressing or classifying the angle. To improve the overall efficiency of the detection model, we also design a rotated object detector based on CenterNet. Experimental results on various public datasets demonstrated the effectiveness and superior performances of our method. In particular, our approach achieves better results than state-of-the-art competitors, with improvements of 1.92% and 1.04% in terms of AP points on the HRSC2016 and DOTA datasets, respectively.
关键词	rotated object detection circular Gaussian CenterNet CGD
DOI	10.3390/electronics12153265
收录类别	SCI
语种	英语
资助项目	National Key Ramp;D Program of China[2022YFD2001601] ; National Nature Science Foundation of China[62072438] ; National Nature Science Foundation of China[U21B2024] ; National Nature Science Foundation of China[61931008] ; National Nature Science Foundation of China[62071415] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDA28040000] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDA28120000] ; Natural Science Foundation of Shandong Province[ZR2021MF094] ; Key Ramp;D Plan of Shandong Province[2020CXGC010804] ; Central Leading Local Science and Technology Development Special Fund Project[YDZX2021122] ; Science amp; Technology Specific Projects in Agricultural High-Tech Industrial Demonstration Area of the Yellow River Delta[2022SZX11]
WOS研究方向	Computer Science ; Engineering ; Physics
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Physics, Applied
WOS记录号	WOS:001046145400001
出版者	MDPI
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/21338
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Dai, Feng
作者单位	1.Hangzhou Dianzi Univ, Sch Automat, Hangzhou 310018, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100086, Peoples R China 3.Hangzhou Dianzi Univ, Lishui Inst, Lishui 323000, Peoples R China
推荐引用方式 GB/T 7714	Xu, Hang,Liu, Xinyuan,Ma, Yike,et al. Rotated Object Detection with Circular Gaussian Distribution[J]. ELECTRONICS,2023,12(15):12.
APA	Xu, Hang.,Liu, Xinyuan.,Ma, Yike.,Zhu, Zunjie.,Wang, Shuai.,...&Dai, Feng.(2023).Rotated Object Detection with Circular Gaussian Distribution.ELECTRONICS,12(15),12.
MLA	Xu, Hang,et al."Rotated Object Detection with Circular Gaussian Distribution".ELECTRONICS 12.15(2023):12.