CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
Fast Localization in Large-Scale Environments Using Supervised Indexing of Binary Features
Feng, Youji1,2; Fan, Lixin3; Wu, Yihong1
发表期刊IEEE TRANSACTIONS ON IMAGE PROCESSING
2016
卷号25期号:1页码:343-358
文章类型Article
摘要The essence of image-based localization lies in matching 2D key points in the query image and 3D points in the database. State-of-the-art methods mostly employ sophisticated key point detectors and feature descriptors, e.g., Difference of Gaussian (DoG) and Scale Invariant Feature Transform (SIFT), to ensure robust matching. While a high registration rate is attained, the registration speed is impeded by the expensive key point detection and the descriptor extraction. In this paper, we propose to use efficient key point detectors along with binary feature descriptors, since the extraction of such binary features is extremely fast. The naive usage of binary features, however, does not lend itself to significant speedup of localization, since existing indexing approaches, such as hierarchical clustering trees and locality sensitive hashing, are not efficient enough in indexing binary features and matching binary features turns out to be much slower than matching SIFT features. To overcome this, we propose a much more efficient indexing approach for approximate nearest neighbor search of binary features. This approach resorts to randomized trees that are constructed in a supervised training process by exploiting the label information derived from that multiple features correspond to a common 3D point. In the tree construction process, node tests are selected in a way such that trees have uniform leaf sizes and low error rates, which are two desired properties for efficient approximate nearest neighbor search. To further improve the search efficiency, a probabilistic priority search strategy is adopted. Apart from the label information, this strategy also uses non-binary pixel intensity differences available in descriptor extraction. By using the proposed indexing approach, matching binary features is no longer much slower but slightly faster than matching SIFT features. Consequently, the overall localization speed is significantly improved due to the much faster key point detection and descriptor extraction. It is empirically demonstrated that the localization speed is improved by an order of magnitude as compared with state-of-the-art methods, while comparable registration rate and localization accuracy are still maintained.
关键词Image Based Localization Binary Feature Approximate Nearest Neighbor Search
WOS标题词Science & Technology ; Technology
DOI10.1109/TIP.2015.2500030
关键词[WOS]NEAREST-NEIGHBOR SEARCH ; IMAGE ; RECOGNITION ; ALGORITHM
收录类别SCI
语种英语
项目资助者Nokia Research(LF14011659182) ; National Basic Research Program of China(2012CB316302) ; National Natural Science Foundation of China(61421004)
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000366558900006
引用统计
被引频次:33[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/10644
专题模式识别国家重点实验室_机器人视觉
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing 400714, Peoples R China
3.Nokia Technol, Tampere 33100, Finland
第一作者单位模式识别国家重点实验室
推荐引用方式
GB/T 7714
Feng, Youji,Fan, Lixin,Wu, Yihong. Fast Localization in Large-Scale Environments Using Supervised Indexing of Binary Features[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2016,25(1):343-358.
APA Feng, Youji,Fan, Lixin,&Wu, Yihong.(2016).Fast Localization in Large-Scale Environments Using Supervised Indexing of Binary Features.IEEE TRANSACTIONS ON IMAGE PROCESSING,25(1),343-358.
MLA Feng, Youji,et al."Fast Localization in Large-Scale Environments Using Supervised Indexing of Binary Features".IEEE TRANSACTIONS ON IMAGE PROCESSING 25.1(2016):343-358.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
IP2016_final.pdf(5024KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Feng, Youji]的文章
[Fan, Lixin]的文章
[Wu, Yihong]的文章
百度学术
百度学术中相似的文章
[Feng, Youji]的文章
[Fan, Lixin]的文章
[Wu, Yihong]的文章
必应学术
必应学术中相似的文章
[Feng, Youji]的文章
[Fan, Lixin]的文章
[Wu, Yihong]的文章
相关权益政策
暂无数据
收藏/分享
文件名: IP2016_final.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。