Enhanced 3-D Modeling for Landmark Image Classification

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 > 图像与视频分析团队

	Enhanced 3-D Modeling for Landmark Image Classification
	Xiao, Xian 1,2; Xu, Changsheng1,2 ; Wang, Jinqiao1,2 ; Xu, Min1,2,3
刊名	IEEE TRANSACTIONS ON MULTIMEDIA
	2012-08-01
卷号	14 期号:4 页码:1246-1258
关键词	Attention analysis attention-based 3-D reconstruction landmark image classification 3-D model enhancement
英文摘要	Landmark image classification is a challenging task due to the various circumstances, e. g., illumination, viewpoint, zoom in/out and occlusion under which landmark images are taken. Most existing approaches utilize features extracted from the whole image including both landmark and non-landmark areas. However, non-landmark areas introduce redundant and noisy information. In this paper, we propose a novel approach to improve landmark image classification consisting of three steps. First, an attention-based 3-D reconstruction method is proposed to reconstruct sparse 3-D landmark models. Second, the sparse 3-D models are projected onto iconic images in order to identify images of the hot regions. For a landmark, hot regions are parts of a landmark which attract photographers' attention and are popularly captured in photos. These hot region images are later used to enhance reconstructed sparse 3-D models. Third, the landmark regions are obtained through mapping the enhanced 3-D models to landmark images. A k-dimensional tree (kd-tree) is then constructed for each landmark based on scale invariant feature transform (SIFT) features [5] extracted from the landmark area to classify unlabeled images into pre-defined landmark categories. The proposed method is evaluated using 291 661 images of 51 landmarks. Experiments of comparison indicate that our method outperforms bag-of-words (BoW) based approach [25] 18.5% and method of spatial-pyramid-matching using sparse-coding (ScSPM) [3] 8.4%.
WOS标题词	Science & Technology ; Technology
类目[WOS]	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
研究领域[WOS]	Computer Science ; Telecommunications
关键词[WOS]	VISUAL-ATTENTION ; SCENE ; COLLECTIONS ; FEATURES
收录类别	SCI
语种	英语
WOS记录号	WOS:000306599400011
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/3352]
专题	自动化研究所_模式识别国家重点实验室_图像与视频分析团队
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit NLPR, Beijing 100190, Peoples R China 2.China Singapore Inst Digital Media, Singapore, Singapore 3.Univ Technol Sydney, Fac Engn & Informat Technol, Sydney, NSW 2007, Australia
推荐引用方式 GB/T 7714	Xiao, Xian,Xu, Changsheng,Wang, Jinqiao,et al. Enhanced 3-D Modeling for Landmark Image Classification[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2012,14(4):1246-1258.
APA	Xiao, Xian,Xu, Changsheng,Wang, Jinqiao,&Xu, Min.(2012).Enhanced 3-D Modeling for Landmark Image Classification.IEEE TRANSACTIONS ON MULTIMEDIA,14(4),1246-1258.
MLA	Xiao, Xian,et al."Enhanced 3-D Modeling for Landmark Image Classification".IEEE TRANSACTIONS ON MULTIMEDIA 14.4(2012):1246-1258.