Real-Time Visual Place Recognition Based on Analyzing Distribution of Multi-scale CNN Landmarks

doi:10.1007/s10846-018-0804-x

	Real-Time Visual Place Recognition Based on Analyzing Distribution of Multi-scale CNN Landmarks
	Xin, Zhe 1,2; Cui, Xiaoguang1 ; Zhang, Jixiang1 ; Yang, Yiping1 ; Wang, Yanqing1
刊名	JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
	2019-06-01
卷号	94 期号:3-4 页码:777-792
关键词	Visual place recognition Localization Convolutional neural networks Changing environments Landmark distribution 68T45 92B20
ISSN号	0921-0296
DOI	10.1007/s10846-018-0804-x
通讯作者	Xin, Zhe(xinzhe2015@ia.ac.cn)
英文摘要	What makes visual place recognition difficult to solve is the variation of the real-world places. In this work, an effective similarity measurement is proposed for visual place recognition in changing environments, based on Convolutional Neural Networks (CNNs) and content-based multi-scale landmarks. The image is firstly segmented into multi-scale landmarks with content information in order to adapt variations of viewpoint, then highly representative features of landmarks are derived from Convolutional Neural Networks (CNNs), which are robust against appearance variations. In the similarity measurement, the similarity between images is determined by analyzing both spatial and scale distributions of matched landmarks. Moreover, an efficient feature extraction and reduction strategy are proposed to generate all features of landmarks at one time. The efficiency of the proposed method makes it suitable for real-time applications. The proposed method is evaluated on two widespread datasets with varied viewpoint and appearance conditions and achieves superior performance against four other state-of-the-art methods, such as the bag-of-words model DBoW3 and the CNN-based Edge Boxes landmarks. Extensive experimentation demonstrates that integrating global and local information can provide more invariance in severe appearance changes, and considering the spatial distribution of landmarks can improve the robustness against viewpoint changes.
WOS关键词	FEATURES ; SCALE
WOS研究方向	Computer Science ; Robotics
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000468432500015
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/24212]
专题	中国科学院自动化研究所
通讯作者	Xin, Zhe
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Xin, Zhe,Cui, Xiaoguang,Zhang, Jixiang,et al. Real-Time Visual Place Recognition Based on Analyzing Distribution of Multi-scale CNN Landmarks[J]. JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS,2019,94(3-4):777-792.
APA	Xin, Zhe,Cui, Xiaoguang,Zhang, Jixiang,Yang, Yiping,&Wang, Yanqing.(2019).Real-Time Visual Place Recognition Based on Analyzing Distribution of Multi-scale CNN Landmarks.JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS,94(3-4),777-792.
MLA	Xin, Zhe,et al."Real-Time Visual Place Recognition Based on Analyzing Distribution of Multi-scale CNN Landmarks".JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS 94.3-4(2019):777-792.