Abstract
Image-based localization is featured with low deployment cost and universal accessibility with smartphones, thus attracts great attentions from both academy and industry. The fingerprints from the image data, which mostly consists of the image features, are promising for indoor localization. However, constructing such fingerprint database is usually time-consuming and labor-intensive. Moreover the high computational and storage cost render this localization scheme highly relies on the cloud-based solution. Meanwhile, this solution suffers from the transmission delay and query contentions in the cloud. To this end, we propose a smartphone-based indoor localization method with enhanced image fingerprint extraction and edge computing paradigm. Basically, we extract image feature vectors with MobileNet and offload part of the database to the smartphone. Then, we query image through the second-level retrieval and verification of the smartphone orientation information to finds out six most similar images. After this, we obtain the most similar image by carrying out query expansion. In the phase of collecting image database, video and samrtphone sensors data are collaboratively used to build image database. We have implement the prototype system on the Android platform, and conduct real experiments to verify the feasibility of the positioning method. Experiment results show that our method has good accuracy (90% location error is within 1.5 m) and high real-time performance (average location delay is about 1.11 s) .
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, Y., Ruizhi, C., Mengyun, L., Aoran, X., Dewen, W., Shuheng, Z.: Indoor visual positioning aided by CNN-based image retrieval: training-free, 3D modeling-free. Sensors 18(8), 2692 (2018)
Chum, O., Philbin, J., Sivic, J., Isard, M., Zisserman, A.: Total recall: automatic query expansion with a generative feature model for object retrieval. In: 2007 IEEE 11th International Conference on Computer Vision (2007)
Guo, Y., Yang, L., Li, B., Liu, T., Liu, Y.: Rollcaller: user-friendly indoor navigation system using human-item spatial relation. In: IEEE INFOCOM 2014-IEEE Conference on Computer Communications (2014)
Han, X., Zheng, Y., Zhou, Z., Shangguan, L., Ke, Y., Liu, Y.: Indoor localization via multi-modal sensing on smartphones (2016)
Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: Squeezenet: Alexnet-level accuracy with 50x fewer parameters and \(<\)0.5mb model size (2016)
Jiang, W., Yin, Z.: Indoor localization with a signal tree. Multimed. Tools Appl. 76(19), 20317–20339 (2017). https://doi.org/10.1007/s11042-017-4779-6
Li, M., Liu, N., Niu, Q., Liu, C., Chan, S.G., Gao, C.: Sweeploc: automatic video-based indoor localization by camera sweeping. IMWUT 2(3), 120:1–120:25 (2018). https://doi.org/10.1145/3264930
Wang, L., Liu, H., Liu, W., Jing, N., Adnan, A., Wu, C.: Leveraging logical anchor into topology optimization for indoor wireless fingerprinting. Comput. Mater. Continua 58(2), 437–449 (2019). https://doi.org/10.32604/cmc.2019.03814. http://www.techscience.com/cmc/v58n2/23019
Liu, K., Liu, X., Xie, L., Li, X.: Towards accurate acoustic localization on a smartphone. In: 2013 Proceedings IEEE INFOCOM, pp. 495–499. IEEE (2013)
Wang, M., Niu, S., Gao, Z.: A novel scene text recognition method based on deep learning. Comput. Mater. Continua 60(2), 781–794 (2019). https://doi.org/10.32604/cmc.2019.05595. http://www.techscience.com/cmc/v60n2/23061
Noelia, H., Manuel, O., Jose, A., Euntai, K.: Continuous space estimation: increasing wifi-based indoor localization resolution without increasing the site-survey effort. Sensors 17(12), 147 (2017)
Sadeghi, H., Valaee, S., Shirani, S.: Ocrapose: an indoor positioning system using smartphone/tablet cameras and OCR-aided stereo feature matching (2015)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Inverted residuals and linear bottlenecks: mobile networks for classification, detection and segmentation. arXiv preprint arXiv:1801.04381 (2018)
Wang, J., Zha, H., Cipolla, R.: Coarse-to-fine vision-based localization by indexing scale-invariant features. IEEE Trans. Syst. Man Cybern. Part B 36(2), 413–422 (2006)
Wang, S., Fidler, S., Urtasun, R.: Lost shopping! monocular localization in large indoor spaces. In: 2015 IEEE International Conference on Computer Vision (ICCV) (2015)
Werner, M., Kessel, M.: Indoor positioning using smartphone camera (2011)
Wu, K., Jiang, X., Yi, Y., Chen, D., Ni, L.M.: Csi-based indoor localization. IEEE Trans. Parallel Distrib. Syst. 24(7), 1300–1309 (2013)
Xia, Y., Xiu, C., Yang, D.: Visual indoor positioning method using image database, pp. 1–8 (2018). https://doi.org/10.1109/UPINLBS.2018.8559714
Wei, Y., Wang, Z., Guo, D., Yu, F.R.: Deep q-learning based computation offloading strategy for mobile edge computing. Comput. Mater. Continua 59(1), 89–104 (2019). https://doi.org/10.32604/cmc.2019.04836. http://www.techscience.com/cmc/v59n1/27923
Zhang, G., Rao, S.V.: Position localization with impulse ultra wide band (2005)
Zhang, W., Liu, G., Tian, G.: A coarse to fine indoor visual localization method using environmental semantic information. IEEE Access 7, 21963–21970 (2019)
Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: an extremely efficient convolutional neural network for mobile devices (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Gao, R., Zhao, Y. (2020). A Lightweight Indoor Location Method Based on Image Fingerprint. In: Sun, X., Wang, J., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2020. Lecture Notes in Computer Science(), vol 12239. Springer, Cham. https://doi.org/10.1007/978-3-030-57884-8_67
Download citation
DOI: https://doi.org/10.1007/978-3-030-57884-8_67
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-57883-1
Online ISBN: 978-3-030-57884-8
eBook Packages: Computer ScienceComputer Science (R0)