A Visual Global Positioning Method Based on Smartphone with High Usability in Large Indoor Spaces
-
摘要:
基于视觉的手机定位方法是室内定位中的研究热点,但面向机场、商场等大型室内环境时存在可靠性差、计算效率低等问题。针对该类场景,提出一种基于三维实景地图的粗定位-精定位二级定位方法,首先基于Wi-Fi指纹匹配粗定位结果约束匹配图像库范围,然后通过子区域分段式建立特征库以及利用深度学习的方法去除天花板图像。实验结果表明,大型室内场景下所提方法可以将视觉匹配定位精度由1.89 m提升至0.45 m,将定位计算效率提升5倍以上。所提方法能够有效降低定位时间,提升特征点云的精度,进而提升视觉匹配定位精度,同时能降低特征点匹配错误而造成定位错误的情况,可以实现高可用、亚米级精度的室内视觉全局定位。
Abstract:ObjectivesThe visual global positioning based on smartphone is a research hotspot in location community services. The existing methods suffer from the problems of poor reliability and low computing efficiency especially when they are used for large indoor environments such as airport and shopping mall.
MethodsThis paper proposes a two-level localization method including rough localization and accurate localization, which is based on 3D real map and applied to large indoor scenes such as shopping mall. To reduce the location computing time, this paper proposes a method to limit the scope of image database. Wi-Fi fingerprint matching algorithm is used to obtain the location results, and then limit the image database. In order to improve the positioning accuracy, a new method of constructing database is proposed. The whole scene is divided into multiple regions, and each region completes the database establishment independently and splices different databases. In order to reduce the location error, a scene recognition method is proposed. Deep learning method is used to remove the ceiling images and reduce the matching errors of feature points.
ResultsBy comparing the location computing time before and after limiting the scope of image database, the proposed method improves the positioning precision from 1.89 m to 0.45 m, and reduces the positioning time from 6.113 s to 0.827 s per image.
ConclusionsThe proposed method achieves sub-meter accuracy of indoor vision global positioning, while the feature points matching errors affect the positioning precision. In the future work, feature lines will be used to improve the positioning accuracy.
-
http://ch.whu.edu.cn/cn/article/doi/10.13203/j.whugis20210602
-
![]()
图 4 RANSAC算法剔除特征点云离群值
Figure 4. Results of Removing Outliers from Feature Point Cloud Using RANSAC Algorithm
![]()
图 10 同一手机站同一控制点不同光照下拍摄的图像
Figure 10. Images Taken by the Same Mobile Phone in Different Lights at the Same Control Point
表 1 数据集1的图像去除天花板前后精度对比
Table 1 Accuracy Comparison of Images Before and After Ceiling Removal in Dataset 1
项目 误差项 剔除前 剔除后 输入图像数量/张 157 157 有效图像数量/张 139 138 RMS 水平误差/m 1.46 0.74 垂直误差/m 1.21 0.42 ∆d/m 1.89 0.85 68%（1δ） 水平误差/m 0.79 0.74 垂直误差/m 0.58 0.39 ∆d/m 0.98 0.84 最大误差 水平误差/m 4.97 2.34 垂直误差/m 2.91 1.66 ∆d/m 5.76 2.87 
下载: 导出CSV
表 2 数据集1的精度评估
Table 2 Accuracy Assessment of Dataset 1
项目 误差项 三星S8 华为P30白天拍摄 华为P30灯光拍摄 输入图像数量/张 138 157 128 有效图像数量/张 116 138 94 RMS 水平误差/m 0.98 0.74 1.00 垂直误差/m 0.35 0.42 0.94 ∆d/m 1.04 0.85 1.37 68%（1δ） 水平误差/m 0.89 0.74 0.93 垂直误差/m 0.34 0.39 0.87 ∆d/m 0.85 0.84 1.27
下载: 导出CSV
表 3 两种建库方案精度对比
Table 3 Accuracy Comparison of Two Strategies
项目 误差项 整层建库 分段式建库后拼接 输入图像数量/张 32 32 有效图像数量/张 29 29 RMS 水平误差/m 0.72 0.46 垂直误差/m 0.26 0.19 ∆d/m 0.77 0.49 68%（1δ） 水平误差/m 0.73 0.40 垂直误差/m 0.37 0.21 ∆d/m 0.82 0.45
下载: 导出CSV
表 4 数据集2的精度评估
Table 4 Accuracy Evaluation of Dataset 2
项目 误差项 三星S8 华为P30白天拍摄 华为P30灯光拍摄 输入图像数量/张 33 32 26 有效图像数量/张 31 29 21 RMS 水平误差/m 0.64 0.46 0.69 垂直误差/m 0.21 0.19 0.42 ∆d/m 0.67 0.49 0.80 68%（1δ） 水平误差/m 0.57 0.40 0.59 垂直误差/m 0.27 0.21 0.41 ∆d/m 0.63 0.45 0.72
下载: 导出CSV
表 5 数据集1加入粗定位结果后的时间对比
Table 5 Computational Time in Dataset 1 After Adding Coarse Positioning Results
过程 全层图像库用时 5 m范围内图像库用时 特征提取/ms <1 <1 相似图像查询/s 2.051 0.473 特征匹配/s 3.742 0.756 位姿计算/s 0.310 0.340 总计/s 6.113 1.569
下载: 导出CSV
表 6 数据集2加入粗定位结果后的时间对比
Table 6 Computational Time in Dataset 2 After Adding Coarse Positioning Results
过程 接待室图像库用时 5 m范围内图像库用时 特征提取/ms <1 <1 相似图像查询/s 1.051 0.249 特征匹配/s 1.142 0.288 位姿计算/s 0.330 0.290 总计/s 2.523 0.827
下载: 导出CSV
-
[1] 陈锐志, 郭光毅, 陈亮, 等. 室内高精度定位技术研究应用现状与发展趋势[J]. 武汉大学学报（信息科学版）, 2023, 48（10）： 1591-1600. Chen Ruizhi, Guo Guangyi, Chen Liang, et al. Application Status, Development and Future Trend of High-Precision Indoor Navigation and Tracking[J]. Geomatics and Information Science of Wuhan University, 2023, 48（10）： 1591-1600.
[2] Huang B C, Liu J B, Sun W, et al. A Robust Indoor Positioning Method Based on Bluetooth Low Energy with Separate Channel Information[J]. Sensors, 2019, 19（16）： 3487.
[3] Anwar Q, Malik A W, Thörnberg B. Design of Coded Reference Labels for Indoor Optical Navigation Using Monocular Camera[C]//International Conference on Indoor Positioning and Indoor Navigation, Montbeliard, France, 2013.
[4] Pivato P, Palopoli L, Petri D. Accuracy of RSS-Based Centroid Localization Algorithms in an Indoor Environment[J]. IEEE Transactions on Instrumentation and Measurement, 2011, 60（10）： 3451-3460.
[5] Yang S, Liu J B, Gong X D, et al. A Robust Heading Estimation Solution for Smartphone Multisensor-Integrated Indoor Positioning[J]. IEEE Internet of Things Journal, 2021, 8（23）： 17186-17198.
[6] 王勋, 崔先强, 高天杭. 城市环境下数据缺失定位算法比较[J]. 导航定位学报, 2020, 8（2）： 43-48. Wang Xun, Cui Xianqiang, Gao Tianhang. Comparison of Data Missing Positioning Algorithms in Urban Environment[J]. Journal of Navigation and Positioning, 2020, 8（2）： 43-48.
[7] Schönberger J L, Frahm J M. Structure-from-Motion Revisited[C]// IEEE Conference on Computer Vision and Pattern Recognition （CVPR）, Las Vegas, USA, 2016.
[8] Wu C C. Towards Linear-Time Incremental Structure from Motion[C]// International Conference on 3D Vision-3DV, Seattle, USA, 2013.
[9] 王中宏. 基于SIFT的室内定位视觉图像匹配方法研究[D]. 哈尔滨： 黑龙江大学, 2021. Wang Zhonghong. Research on Indoor Positioning Visual Image Matching Method Based on SIFT[D].Harbin： Helongjiang University, 2021.
[10] Wang Z M, Zhang Q, Li J S, et al. A Computationally Efficient Semantic SLAM Solution for Dynamic Scenes[J]. Remote Sensing, 2019, 11（11）： 1363.
[11] Gong X D, Liu J B, Yang S, et al. A Usability-Enhanced Smartphone Indoor Positioning Solution Using Compressive Sensing[J]. IEEE Sensors Journal, 2022, 22（3）： 2823-2834.
[12] Huitl R, Schroth G, Hilsenbeck S, et al. TUMindoor： An Extensive Image and Point Cloud Dataset for Visual Indoor Localization and Mapping[C]//IEEE International Conference on Image Processing, Orlando, USA, 2012.
[13] Gao Q J, Yin D Y, Luo Q J, et al. Minimum Elastic Bounding Box Algorithm for Dimension Detection of 3D Objects： A Case of Airline Baggage Measurement[J]. IET Image Processing, 2018, 12（8）： 1313-1321.
[14] 刘肃艳, 王竞雪, 沈昭宇, 等. 结合线对几何特征及单线描述符约束的直线匹配算法[J]. 武汉大学学报（信息科学版）, 2023, 48（6）： 936-949. Liu Suyan, Wang Jingxue, Shen Zhaoyu, et al. Line Matching Algorithm Based on Pair-Wise Geometric Features and Individual Line Descriptor Constraints[J]. Geomatics and Information Science of Wuhan University, 2023, 48（6）： 936-949.
[15] Mikolajczyk K, Schmid C. A Performance Evaluation of Local Descriptors[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Madison, USA, 2003.
[16] Xu D, Liu J B, Hyyppä J, et al. A Heterogeneous 3D Map-Based Place Recognition Solution Using Virtual LiDAR and a Polar Grid Height Coding Image Descriptor[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 183： 1-18.
[17] Liu J B, Xu D, Hyyppä J, et al. A Survey of Applications with Combined BIM and 3D Laser Scanning in the Life Cycle of Buildings[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14： 5627-5637.
[18] Hafiz A M, Bhat G M. A Survey on Instance Segmentation： State of the Art[J]. International Journal of Multimedia Information Retrieval, 2020, 9（3）： 171-189.
[19] Kirillov A, He K M, Girshick R, et al. Panoptic Segmentation[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）, Long Beach, USA, 2019.
[20] Rai A, Chintalapudi K K, Padmanabhan V N, et al. Zee： Zero-Effort Crowdsourcing for Indoor Localization[C]//The 18th Annual International Conference on Mobile Computing and Networking, Istanbul, Turkey, 2012.
[21] Lin P, Li Q B, Fan Q X, et al. A Real-Time Location-Based Services System Using Wi-Fi Fingerprinting Algorithm for Safety Risk Assessment of Workers in Tunnels[J]. Mathematical Problems in Engineering, 2014, 371456.
[22] de Francisco R. Indoor Channel Measurements and Models at 2.4 GHz in a Hospital[C]//IEEE Global Telecommunications Conference, Miami, USA, 2010.
[23] Li Z, Liu J B, Yang F, et al. A Bayesian Density Model Based Radio Signal Fingerprinting Positioning Method for Enhanced Usability[J]. Sensors, 2018, 18（11）： 4063.
[24] Torres-Solis J, Tiago H, Chau T. A Review of Indoor Localization Technologies： Towards Navigational Assistance for Topographical Disorientation[M] Croatia： Intech Open Access Publisher, 2010.
[25] Liang X L, Jaakkola A, Wang Y S, et al. The Use of a Hand-Held Camera for Individual Tree 3D Mapping in Forest Sample Plots[J]. Remote Sensing, 2014, 6（7）： 6587-6603.
[26] 徐彦彦, 赵啸, 李子君. 一种基于四元数变换的彩色遥感影像检索方法[J]. 武汉大学学报（信息科学版）, 2019, 44（11）： 1633-1640. Xu Yanyan, Zhao Xiao, Li Zijun. A Remote Sensing Image Retrieval Method Based on Quaternion Transformation[J]. Geomatics and Information Science of Wuhan University, 2019, 44（11）： 1633-1640.
[27] 张恒才, 蔚保国, 秘金钟, 等. 综合PNT场景增强系统研究进展及发展趋势[J]. 武汉大学学报（信息科学版）, 2023, 48（4）： 491-505. Zhang Hengcai, Yu Baoguo, Bi Jinzhong, et al. A Survey of Scene-Based Augmentation Systems for Comprehensive PNT[J]. Geomatics and Information Science of Wuhan University, 2023, 48（4）： 491-505.
[28] 方志祥, 徐虹, 萧世伦, 等. 绝对空间定位到相对空间感知的行人导航研究趋势[J]. 武汉大学学报（信息科学版）, 2018, 43（12）： 2173-2182. Fang Zhixiang, Xu Hong, Xiao Shilun, et al. Pedestrian Navigation Research Trend： From Absolute Space to Relative Space-Based Approach[J]. Geomatics and Information Science of Wuhan University, 2018, 43（12）： 2173-2182.
[29] Mautz R, Tilch S. Survey of Optical Indoor Positioning Systems[C]//International Conference on Indoor Positioning and Indoor Navigation, Guimaraes, Portugal, 2011.
[30] Wu T, Liu J B, Li Z, et al. Accurate Smartphone Indoor Visual Positioning Based on a High-Precision 3D Photorealistic Map[J]. Sensors, 2018, 18（6）： 1974.
[31] 陈锐志, 叶锋. 基于Wi-Fi信道状态信息的室内定位技术现状综述[J]. 武汉大学学报（信息科学版）, 2018, 43（12）： 2064-2070. Chen Ruizhi, Ye Feng. An Overview of Indoor Positioning Technology Based on Wi-Fi Channel State Information[J]. Geomatics and Information Science of Wuhan University, 2018, 43（12）： 2064-2070.
[32] Liu J B, Chen R Z, Pei L, et al. A Hybrid Smartphone Indoor Positioning Solution for Mobile LBS[J]. Sensors, 2012, 12（12）： 17208-17233.
[33] Xu S, Chou W S, Dong H Y. A Robust Indoor Localization System Integrating Visual Localization Aided by CNN-Based Image Retrieval with Monte Carlo Localization[J]. Sensors, 2019, 19（2）： 249.
[34] Wu D W, Chen R Z, Chen L. Visual Positioning Indoors： Human Eyes Vs. Smartphone Cameras[J]. Sensors, 2017, 17（11）： 2645.
[35] Schatzberg U, Banin L, Amizur Y. Enhanced Wi-Fi ToF Indoor Positioning System with MEMS-Based INS and Pedometric Information[C]//IEEE/ION Position, Location and Navigation Symposium, Monterey, USA, 2014.
[36] Kilinc C, Al Mahmud Mostafa S, Islam R U, et al. Indoor Taxi-Cab： Real-Time Indoor Positioning and Location-Based Services with Ekahau and Android OS[C]//The 8th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing, Birmingham, UK, 2014.
[37] Liang J Z, Corso N, Turner E, et al. Image Based Localization in Indoor Environments[C]//The 4th International Conference on Computing for Geospatial Research and Application,Chicago,USA,2013.
[38] Zhang Z B, Liu J B, Wang L, et al. An Enhanced Smartphone Indoor Positioning Scheme with Out-lier Removal Using Machine Learning[J]. Remote Sensing, 2021, 13（6）： 1106.
计量
- 文章访问数: 803
- HTML全文浏览量: 98
- PDF下载量: 98
