MSGSA: Multi-Scale Guided Self-Attention Network for Crowd Counting

doi:10.3390/electronics12122631

CORC > 自动化研究所 > 中国科学院自动化研究所 > 精密感知与控制研究中心 > 人工智能与机器学习

	MSGSA: Multi-Scale Guided Self-Attention Network for Crowd Counting
	Sun, Yange 1,2; Li, Meng 2; Guo, Huaping 1,2; Zhang, Li 2
刊名	ELECTRONICS
	2023-06-01
卷号	12 期号:12 页码:14
关键词	crowd counting self-attention convolutional neural networks multi-scale feature
DOI	10.3390/electronics12122631
通讯作者	Sun, Yange(yangesun@xynu.edu.cn) ; Guo, Huaping(hpguo@xynu.edu.cn)
英文摘要	The use of convolutional neural networks (CNN) for crowd counting has made significant progress in recent years; however, effectively addressing the scale variation and complex backgrounds remain challenging tasks. To address these challenges, we propose a novel Multi-Scale Guided Self-Attention (MSGSA) network that utilizes self-attention mechanisms to capture multi-scale contextual information for crowd counting. The MSGSA network consists of three key modules: a Feature Pyramid Module (FPM), a Scale Self-Attention Module (SSAM), and a Scale-aware Feature Fusion (SFA). By integrating self-attention mechanisms at multiple scales, our proposed method captures both global and local contextual information, leading to an improvement in the accuracy of crowd counting. We conducted extensive experiments on multiple benchmark datasets, and the results demonstrate that our method outperforms most existing methods in terms of counting accuracy and the quality of the generated density map. Our proposed MSGSA network provides a promising direction for efficient and accurate crowd counting in complex backgrounds.
资助项目	National Natural Science Foundation of China[62062004] ; Natural Science Foundation of Henan Province[222300420274] ; Natural Science Foundation of Henan Province[222300420275] ; Natural Science Foundation of Henan Province[232300421167] ; Key Scientific Research Projects of Henan Province[22A520008] ; Key Scientific Research Projects of Henan Province[22A220002] ; Academic Degrees amp; Graduate Education Reform Project of Henan Province[22A520008] ; Academic Degrees amp; Graduate Education Reform Project of Henan Province[22A220002] ; Postgraduate Education Reform and Quality Improvement Project of Henan Province[YJS2023SZ23] ; Nanhu Scholars Program for Young Scholars of XYNU
WOS研究方向	Computer Science ; Engineering ; Physics
语种	英语
出版者	MDPI
WOS记录号	WOS:001014369700001
资助机构	National Natural Science Foundation of China ; Natural Science Foundation of Henan Province ; Key Scientific Research Projects of Henan Province ; Academic Degrees amp; Graduate Education Reform Project of Henan Province ; Postgraduate Education Reform and Quality Improvement Project of Henan Province ; Nanhu Scholars Program for Young Scholars of XYNU
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53516]
专题	精密感知与控制研究中心_人工智能与机器学习
通讯作者	Sun, Yange; Guo, Huaping
作者单位	1.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing 100190, Peoples R China 2.Xinyang Normal Univ, Sch Comp & Informat Technol, Xinyang 464000, Peoples R China
推荐引用方式 GB/T 7714	Sun, Yange,Li, Meng,Guo, Huaping,et al. MSGSA: Multi-Scale Guided Self-Attention Network for Crowd Counting[J]. ELECTRONICS,2023,12(12):14.
APA	Sun, Yange,Li, Meng,Guo, Huaping,&Zhang, Li.(2023).MSGSA: Multi-Scale Guided Self-Attention Network for Crowd Counting.ELECTRONICS,12(12),14.
MLA	Sun, Yange,et al."MSGSA: Multi-Scale Guided Self-Attention Network for Crowd Counting".ELECTRONICS 12.12(2023):14.