Application of Deep Convolutional Neural Networks and Smartphone Sensors for Indoor Localization

Abstract

Indoor localization systems are susceptible to higher errors and do not meet the current standards of indoor localization. Moreover, the performance of such approaches is limited by device dependence. The use of Wi-Fi makes the localization process vulnerable to dynamic factors and energy hungry. A multi-sensor fusion based indoor localization approach is proposed to overcome these issues. The proposed approach predicts pedestrians' current location with smartphone sensors data alone. The proposed approach aims at mitigating the impact of device dependency on the localization accuracy and lowering the localization error in the magnetic field based localization systems. We trained a deep learning based convolutional neural network to recognize the indoor scene which helps to lower the localization error. The recognized scene is used to identify a specific floor and narrow the search space. The database built of magnetic field patterns helps to lower the device dependence. A modified K nearest neighbor (mKNN) is presented to calculate the pedestrian's current location. The data from pedestrian dead reckoning further refines this location and an extended Kalman filter is implemented to this end. The performance of the proposed approach is tested with experiments on Galaxy S8 and LG G6 smartphones. The experimental results demonstrate that the proposed approach can achieve an accuracy of 1.04 m at 50 percent, regardless of the smartphone used for localization. The proposed mKNN outperforms K nearest neighbor approach, and mean, variance, and maximum errors are lower than those of KNN. Moreover, the proposed approach does not use Wi-Fi for localization and is more energy efficient than those of Wi-Fi based approaches. Experiments reveal that localization without scene recognition leads to higher errors.

LocSpeck: A Collaborative and Distributed Positioning System for Asymmetric Nodes Based on UWB Ad-Hoc Network and Wi-Fi Fingerprinting

“…Since these results depend mainly on Wi-Fi fingerprinting, the performance might be affected by the presence of high human mobility in the test area [56]. Additionally, the overall performance of the standalone positioning scenario can be improved by augmenting the solution with other techniques, such as the geomagnetic field anomalies or visual scene recognition [57][58][59][60]. However, the main objective of the standalone filter in this work is to form the performance baseline, to which the effect of collaboration between nodes is to be measured, as discussed later in Section 4.2.3.…”

Integration of Convolutional Neural Network and Error Correction for Indoor Positioning

“…There are also studies on positioning in combination with a variety of indoor positioning technologies. Ashraf et al [19] combined mobile phone sensor data with a CNN to predict the current position of pedestrians, with the purpose of reducing the dependence of devices in magnetic field positioning system. Firstly, a CNN model was trained to recognize indoor scenes, which helped to identify specific floors and reduce the search space.…”

DeepLocate: Smartphone Based Indoor Localization with a Deep Neural Network Ensemble Classifier

“…The reported localization error is 1.32 at 95%. In the same fashion, the research [50] proposes a multi-story localization approach based on smartphone sensors. The smartphone camera is utilized along with the magnetometer.…”