Document Type : Research Paper
Authors
1 University of Technology-Iraq, Computer Engineering Department, Baghdad, Iraq
2 Computer Engineering Department, University of Technology, Baghdad, Iraq.
Abstract
Robust and accurate indoor localization has been the goal of several research
efforts over the past decade. In the building where the GPS is not available, this project
can be utilized. Indoor localization based on image matching techniques related to deep
learning was achieved in a hard environment. So, if it wanted to raise the precision of
indoor classification, the number of image dataset of the indoor environment should be as
large as possible to satisfy and cover the underlying area. In this work, a smartphone
camera is used to build the image-based dataset of the investigated building. In addition,
captured images in real time are taken to be processed with the proposed model as a test
set. The proposed indoor localization includes two phases the first one is the offline
learning phase and the second phase is the online processing phase. In the offline learning
phase, here we propose a convolutional neural network (CNN) model that sequences the
features of image data from some classis's dataset composed with a smartphone camera.
In the online processing phase, an image is taken by the camera of a smartphone in real–
time to be tested by the proposed model. The obtained results of the prediction can appoint
the expected indoor location. The proposed system has been tested over various
experiments and the obtained experimental results show that the accuracy of the prediction
is almost 98.0%.
Keywords
)
