Frequency Feature Pyramid Network With Global-Local Consistency Loss for Crowd-and-Vehicle Counting in Congested Scenes

doi:10.1109/TITS.2022.3178848

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 生物识别与安全技术研究中心

	Frequency Feature Pyramid Network With Global-Local Consistency Loss for Crowd-and-Vehicle Counting in Congested Scenes
	Yu, Xiaoyuan 5; Liang, Yanyan 5; Lin, Xuxin 5; Wan, Jun 1; Wang, Tian 2,3; Dai, Hong-Ning 4
刊名	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
	2022-07-01
卷号	23 期号:7 页码:9654-9664
关键词	Context prediction frequency feature pyramid discrete cosine transformation global-local consistency loss
ISSN号	1524-9050
DOI	10.1109/TITS.2022.3178848
通讯作者	Liang, Yanyan(yyliang@must.edu.mo)
英文摘要	Context prediction plays a crucial role in implementing autonomous driving applications. As one of important context-prediction tasks, crowd-and-vehicle counting is critical for achieving real-time traffic and crowd analysis, consequently facilitating decision-making processes for autonomous vehicles. However, the completion of crowd-and-vehicle counting also faces challenges, such as large-scale variations, imbalanced data distribution, and insufficient local patterns. To tackle these challenges, we put forth a novel frequency feature pyramid network (FFPNet) in this paper. Our proposed FFPNet extracts the multi-scale information by frequency feature pyramid module, which can tackle the issue of large-scale variations. Meanwhile, the frequency feature pyramid module uses different frequency branches to obtain different scale information. We also adopt the attention mechanism to strength the extraction of different scale information. Moreover, we devise a novel loss function, namely global-local consistency loss, to address the existing problems of imbalanced data distribution and insufficient local patterns. Furthermore, we conduct extensive experiments on six datasets to evaluate our proposed FFPNet. It is worth mentioning that we also construct a novel crowd-and-vehicle dataset (CROVEH), which is the only dataset that contains both crowd-and-vehicle annotations. The experimental results show that FFPNet achieves the best performance on different backbones, e.g., 52.69 mean absolute error (MAE) on P2PNet with FFP module. The codes are available at: https://github.com/MUST-AI-Lab/FFPNet.
资助项目	National Key Research and Development Plan[2021YFE0205700] ; External Cooperation Key Project of Chinese Academy Sciences[173211KYSB20200002] ; Chinese National Natural Science Foundation[61876179] ; Chinese National Natural Science Foundation[61961160704] ; Science and Technology Development Fund of Macau[0008/2019/A1] ; Science and Technology Development Fund of Macau[0010/2019/AFJ] ; Science and Technology Development Fund of Macau[0025/2019/AKP] ; Science and Technology Development Fund of Macau[0004/2020/A1] ; Science and Technology Development Fund of Macau[0070/2021/AMJ] ; Guangdong Provincial Key Research and Development Programme[2019B010148001] ; National Natural Science Foundation of China (NSFC)[62172046] ; Special Project of Guangdong Provincial Department of Education in Key Fields of Colleges and Universities[2021ZDZX1063]
WOS研究方向	Engineering ; Transportation
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000838694400302
资助机构	National Key Research and Development Plan ; External Cooperation Key Project of Chinese Academy Sciences ; Chinese National Natural Science Foundation ; Science and Technology Development Fund of Macau ; Guangdong Provincial Key Research and Development Programme ; National Natural Science Foundation of China (NSFC) ; Special Project of Guangdong Provincial Department of Education in Key Fields of Colleges and Universities
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/50379]
专题	自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心
通讯作者	Liang, Yanyan
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Beijing Normal Univ BNU Zhuhai, BNU HKBU United Int Coll, Guangdong Key Lab AI & Multimodal Data Proc, Zhuhai 519088, Guangdong, Peoples R China 3.Beijing Normal Univ BNU Zhuhai, BNU UIC Inst Artificial Intelligence & Future Net, Zhuhai 519088, Guangdong, Peoples R China 4.Lingnan Univ, Dept Comp & Decis Sci, Hong Kong, Peoples R China 5.Macau Univ Sci & Technol, Sch Comp Sci & Engn, Fac Innovat Engn, Macau, Peoples R China
推荐引用方式 GB/T 7714	Yu, Xiaoyuan,Liang, Yanyan,Lin, Xuxin,et al. Frequency Feature Pyramid Network With Global-Local Consistency Loss for Crowd-and-Vehicle Counting in Congested Scenes[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2022,23(7):9654-9664.
APA	Yu, Xiaoyuan,Liang, Yanyan,Lin, Xuxin,Wan, Jun,Wang, Tian,&Dai, Hong-Ning.(2022).Frequency Feature Pyramid Network With Global-Local Consistency Loss for Crowd-and-Vehicle Counting in Congested Scenes.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,23(7),9654-9664.
MLA	Yu, Xiaoyuan,et al."Frequency Feature Pyramid Network With Global-Local Consistency Loss for Crowd-and-Vehicle Counting in Congested Scenes".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 23.7(2022):9654-9664.