文献类型：期刊文献

英文题名：Continuous Indoor Visual Localization Using a Spatial Model and Constraint

作者：Zhang, Xing[1,2,3,4];Lin, Jing[1,2,3,4];Li, Qingquan[1,2,3,4];Liu, Tao[5];Fang, Zhixiang[6]

第一作者：Zhang, Xing

通讯作者：Zhang, X[1];Zhang, X[2];Zhang, X[3];Zhang, X[4]

机构：[1]Shenzhen Univ, Sch Architecture & Urban Planning, Guangdong Key Lab Urban Informat, Shenzhen 518060, Peoples R China;[2]Shenzhen Univ, MNR Key Lab Geoenvironm Monitoring Great Bay Area, Shenzhen 518060, Peoples R China;[3]Shenzhen Univ, Guangdong Lab Artificial Intelligence & Digital E, Shenzhen 518060, Peoples R China;[4]Shenzhen Univ, Shenzhen Key Lab Spatial Smart Sensing & Serv, Shenzhen 518060, Peoples R China;[5]Henan Univ Econ & Law, Coll Resources & Environm, Zhengzhou 450002, Peoples R China;[6]Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan 430072, Peoples R China

第一机构：Shenzhen Univ, Sch Architecture & Urban Planning, Guangdong Key Lab Urban Informat, Shenzhen 518060, Peoples R China

通讯机构：[1]corresponding author), Shenzhen Univ, Sch Architecture & Urban Planning, Guangdong Key Lab Urban Informat, Shenzhen 518060, Peoples R China;[2]corresponding author), Shenzhen Univ, MNR Key Lab Geoenvironm Monitoring Great Bay Area, Shenzhen 518060, Peoples R China;[3]corresponding author), Shenzhen Univ, Guangdong Lab Artificial Intelligence & Digital E, Shenzhen 518060, Peoples R China;[4]corresponding author), Shenzhen Univ, Shenzhen Key Lab Spatial Smart Sensing & Serv, Shenzhen 518060, Peoples R China.

年份：2020

卷号：8

起止页码：69800-69815

外文期刊名：IEEE ACCESS

收录：;EI(收录号：20201908610970);Scopus(收录号：2-s2.0-85084110614);WOS:【SCI-EXPANDED(收录号:WOS:000549827900010)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 41301511, Grant 41801376, and Grant 41771473, in part by the National Key Research Development Program of China under Grant 2016YFB0502203, in part by the Natural Science Foundation of Guangdong Province under Grant 2018A030313289, in part by the Shenzhen Scienti~c Research and Development Funding Program under Grant JCYJ20170818144544900 and Grant JCYJ20180305125033478, in part by the Open Research Fund of State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, under Grant 18S03, and in part by the Key Research Projects of Henan Higher Education Institutions under Grant 19A420004.

语种：英文

外文关键词：Visualization; Cameras; Image matching; Indoor environments; Smart phones; Computational modeling; Trajectory; Indoor positioning; visual localization; image matching; spatial model

摘要：Visual localization is an accurate and low-cost indoor localization solution. A bottleneck for visual localization is the computation efficiency of continuous image searching and matching. In this paper, an indoor visual localization method is proposed to realize continuous and accurate indoor localization based on image matching. This method uses smartphones to collect multi-sensor data, including video frames and inertial readings. To improve the computation efficiency of the proposed visual localization method, a spatial model is developed to optimize the spatial organization of geo-tagged images in a dataset. Several spatial constraint-based image searching strategies are also designed to further reduce the computation time. Based on the spatial model and spatial constraint-based strategies, a visual localization algorithm is proposed. The experimental results show that the localization errors of the image querying, continuous offline localization and online localization of this method are approximately 0.4 m, 0.7 m and 0.9 m, respectively. This method can achieve an accuracy of 1.3 m, even under a random camera opening condition. The average computation time (i.e.. the average time needed to provide a location estimation result) is approximately 0.59 s. The results indicate that the proposed method can realize efficient and continuous indoor localization with high localization accuracy.