Advertisement

A Fast Vision-Based Indoor Localization Method Using BoVW-Based Image Retrieval

  • Lin Ma
  • Tong Jia
  • Xuezhi Tan
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 463)

Abstract

With the increasing demand for indoor localization service in our daily life, vision-based indoor localization has become a hot topic since image recording and application are very popular in the indoor environment. Based on the epipolar geometry algorithm, more images are required in the database to achieve better localization performance, which would inevitably lead to high time consuming for image retrieval. Therefore, in this paper we propose a vision-based indoor localization method by using the BoVW (Bag of Visual Word)-based image retrieval method, which could achieve less time consuming and good localization performance. The experiment results show that the localization error of the system by utilizing our proposed method could achieve an accuracy of less than 2 meters by a chance of 75%, while the time for localization sharply decreases by 60%. Compared with the traditional localization system, the proposed method could make a balance between the localization accuracy and efficiency in practice.

Keywords

Indoor localization Vision-based Image retrieval BoVW algorithm Epipolar geometry 

Notes

Acknowledgment

This paper is supported by National Natural Science Foundation of China (61571162), Natural Science Foundation of Hei Longjiang Province China (F2016019), Postdoctoral Science-Research Development Foundation of Hei Longjiang Province China (LBH-Q12080), Science and Technology Project of Ministry of China Public Security Foundation (2015GABJC38) and National Science and Technology Major Specific Projects of China (2015ZX03004002-004)

References

  1. 1.
    Liang, J., Corso, N., Turner, E.: Image based localization in indoor environments. In: IEEE Computing for Geospatial Research and Application, pp. 70–75 (2013)Google Scholar
  2. 2.
    Montero, A.S., Sekkati, J., Lang, H., Laganire, R., James, J.: Framework for natural landmark-based robot localization. In: IEEE Computer and Robot Vision, pp. 131–138 (2012)Google Scholar
  3. 3.
    Li, B., Li, H., Soderstrom, U.: Scale-invariant corner keypoints. In: IEEE International Conference on Image Processing, pp. 5741–5745 (2014)Google Scholar
  4. 4.
    Bay, H., Ess, A., Tuytelaars, T., Gool, L.V.: Speeded-up robust features (SURF). Comput. Vis. Image Underst. 110, 346–359 (2008)Google Scholar
  5. 5.
    Murillo, A.C., Singh, G., Kosecka, J., Guerrero, J.J.: Localization in urban environments using a panoramic gist descriptor. IEEE Trans. Robot. 29(1), pp. 146–160Google Scholar
  6. 6.
    Tsai, Y.H., Yang, M.: Locality preserving hashing. In: IEEE International Conference on Image Processing, pp. 2988–2992 (2014)Google Scholar
  7. 7.
    Li, F., Perona, P.: A Bayesian hierarchical model for learning natural scene categories. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 524–531 (2005)Google Scholar
  8. 8.
    Xue, H., Ma, L., Tan, X.: A fast visual map building method using video stream for visual-based indoor localization. In: IEEE International Wireless Communications and Mobile Computing Conference (2016)Google Scholar
  9. 9.
    Sadeghi, H., Valaee, S., Shirani, S.: A weighted knn epipolar geometry-based approach for vision-based indoor localization using smartphone cameras. In: IEEE 8th Sensor Array and Multichannel Signal Processing Workshop, pp. 37–40 (2014)Google Scholar
  10. 10.
    Ionescu, R.T., Popescu, M.N.: Objectness to improve the bag of visual words model. In: IEEE International Conference on Image Processing, pp. 3238–3242 (2014)Google Scholar
  11. 11.
    Durand, T., Thome, N., Cord, M.: MANTRA: minimum maximum latent structural svm for image classification and ranking. In: IEEE International Conference on Computer Vision, pp. 2713–2721 (2015)Google Scholar
  12. 12.
    Ma, A., Li, J., Yuen, P.: Cross-domain person reidentification using domain adaptation ranking SVMs. In: IEEE Trans. Image Process. 24(5), pp. 1599–1613 (2015)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Communication Research CenterHarbin Institute of TechnologyHarbinChina
  2. 2.Key Laboratory of Police Wireless Digital CommunicationChina Ministry of Public SecurityHarbinChina

Personalised recommendations