An Indoor Localization Technique Based on Visible Light Communication

This paper proposes a technique for indoor localization based on a visible light positioning approach. The strategy relies on using lighting luminaires that modulate the luminous flux at different frequencies. A light sensor is then used to gather the illuminance signal used as input for a previously trained Artificial Neural Network (ANN) to estimate the position of the sensor. The work's main contribution is using an illuminance estimator based on the lighting distribution of the luminaires to perform the training procedure of the ANN. The lighting distribution is obtained through the .IES file provided by the manufacturer, i.e., the same file used for lighting designs. Therefore, by using characteristics of the environment and the .IES file, the proposed system can provide data to train accurately the ANN used in the positioning method. The results attested to the satisfactory performance of the proposed localization technique as it produced mean distance errors of 1.51cm and 0.79cm considering 0% and 70% walls' reflectance levels, respectively.