Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2018 Jun 20;18(6):1974.
doi: 10.3390/s18061974.

Accurate Smartphone Indoor Visual Positioning Based on a High-Precision 3D Photorealistic Map

Teng Wu  1 , Jingbin Liu  2   3   4 , Zheng Li  5 , Keke Liu  6 , Beini Xu  7
Affiliations

Accurate Smartphone Indoor Visual Positioning Based on a High-Precision 3D Photorealistic Map

Teng Wu et al. Sensors (Basel). .

Abstract

Indoor positioning is in high demand in a variety of applications, and indoor environment is a challenging scene for visual positioning. This paper proposes an accurate visual positioning method for smartphones. The proposed method includes three procedures. First, an indoor high-precision 3D photorealistic map is produced using a mobile mapping system, and the intrinsic and extrinsic parameters of the images are obtained from the mapping result. A point cloud is calculated using feature matching and multi-view forward intersection. Second, top-K similar images are queried using hamming embedding with SIFT feature description. Feature matching and pose voting are used to select correctly matched image, and the relationship between image points and 3D points is obtained. Finally, outlier points are removed using P3P with the coarse focal length. Perspective-four-point with unknown focal length and random sample consensus are used to calculate the intrinsic and extrinsic parameters of the query image and then to obtain the positioning of the smartphone. Compared with established baseline methods, the proposed method is more accurate and reliable. The experiment results show that 70 percent of the images achieve location error smaller than 0.9 m in a 10 m × 15.8 m room, and the prospect of improvement is discussed.

Keywords: image feature matching; indoor visual positioning; photogrammetric vision; place recognition; smartphone positioning.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Workflow of database Image processing.
Figure 2
Figure 2
Comparison between the F matrix and E matrix in geometry check. (a) RANSAC and fundamental matrix as geometry check, 123 points; (b) Calculate essential matrix from extrinsic parameters as geometry check, 219 points.
Figure 3
Figure 3
Point cloud from multi-view forward intersection.
Figure 4
Figure 4
Workflow of smartphone image positioning.
Figure 5
Figure 5
Comparison between Hessian affine and DoG detectors. (a) mAP (b) average number of correct images in the top-K queries.
Figure 6
Figure 6
Matches after geometry check. (a) Most matched image with 390 matches. (b) A uniform distribution with 339 matches.
Figure 7
Figure 7
Euler angle vote plot.
Figure 8
Figure 8
Bad match image with 182 matches after geometry check.
Figure 9
Figure 9
(a) The total station; (b) The mark on the smartphone; (c) The control point measured using the total station.
Figure 10
Figure 10
Data description in experiment one. (a) Panorama image of the room. (b) Database image data description. (c) The smartphone positions in the experiment room.
Figure 11
Figure 11
The location error distribution diagram of dataset 1. (a) Samsung dataset result. (b) iPhone dataset result.
Figure 12
Figure 12
Data description in a challenging scene. (a) Panorama image of the room. (b) Database image data description. (c) The smartphone positions in the experiment room.
Figure 13
Figure 13
The location error distribution diagram of dataset 2. (a) Samsung dataset result. (b) iPhone dataset result.
Figure 14
Figure 14
Noise points in the feature 3D points.
Figure 15
Figure 15
Distribution of feature points before PnP estimator. (a) Good distribution and enough feature points. (b) Bad distribution of feature points.
Figure 16
Figure 16
Images are collected along a line.
Figure 17
Figure 17
Change of the environment, in the red rectangle. (a) Image captured on 4 December 2016. (b) Image captured on 16 October 2017.
See this image and copyright information in PMC

References

    1. Davidson P., Piche R. A survey of selected indoor positioning methods for smartphones. IEEE Commun. Surv. Tutor. 2016;19:1347–1370. doi: 10.1109/COMST.2016.2637663. - DOI
    1. Foxlin E. Pedestrian tracking with shoe-mounted inertial sensors. IEEE Comput. Graph. Appl. 2005;25:38–46. doi: 10.1109/MCG.2005.140. - DOI - PubMed
    1. Xia S., Liu Y., Yuan G., Zhu M., Wang Z. Indoor fingerprint positioning based on wi-fi: An overview. ISPRS Int. J. Geo-Inf. 2017;6:135. doi: 10.3390/ijgi6050135. - DOI
    1. Pei L., Liu J., Guinness R., Chen Y., Kuusniemi H., Chen R. Using ls-svm based motion recognition for smartphone indoor wireless positioning. Sensors. 2012;12:6155–6175. doi: 10.3390/s120506155. - DOI - PMC - PubMed
    1. Liang J.Z., Corso N., Turner E., Zakhor A. Image based localization in indoor environments; Proceedings of the 2013 Fourth International Conference on Computing for Geospatial Research and Application; San Jose, CA, USA. 22–24 July 2013; Piscataway, NJ, USA: IEEE; 2013. pp. 70–75.