Proceedings of the 2018 International Conference on Mechanical, Electronic, Control and Automation Engineering (MECAE 2018)

An Indoor Localization Method of Image Matching Based on Deep Learning

Authors
Guihua Yang, Yu Liang
Corresponding Author
Guihua Yang
Available Online March 2018.
DOI
https://doi.org/10.2991/mecae-18.2018.21How to use a DOI?
Keywords
indoor localization, deep learning, location algorithm, image matching
Abstract
To overcome the problems of low accuracy and poor stability brought by the complexity of scenarios, an indoor localization method of image matching based on Deep Learning is proposed. The method includes taking images of indoor surroundings with cameras of mobile devices, setting up a dataset of images containing information on position and direction, and training a Convolutional Neural Network (CNN) with the image data. Then use the trained CNN to match the current images taken by the cameras of mobile devices to estimate precise location. The results of experiments show that the accuracy rate of CNN can reach up to 99.2%, positioning accuracy rate is up to 90%, and positioning precision is within 2 metres of diameter. This algorithm can achieve sound robustness, and fairly excellent generalization capabilities.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Proceedings
2018 International Conference on Mechanical, Electronic, Control and Automation Engineering (MECAE 2018)
Publication Date
March 2018
ISBN
978-94-6252-493-4
DOI
https://doi.org/10.2991/mecae-18.2018.21How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Guihua Yang
AU  - Yu Liang
PY  - 2018/03
DA  - 2018/03
TI  - An Indoor Localization Method of Image Matching Based on Deep Learning
BT  - 2018 International Conference on Mechanical, Electronic, Control and Automation Engineering (MECAE 2018)
PB  - Atlantis Press
UR  - https://doi.org/10.2991/mecae-18.2018.21
DO  - https://doi.org/10.2991/mecae-18.2018.21
ID  - Yang2018/03
ER  -