Sistema de localização por luz visível para ambientes interiores baseado em um estimador de Iluminâncias

Abstract

This work proposes a technique for indoor localization based on Visible Light Communication (VLC). The strategy relies on using lighting LED luminaires whose luminous flux is modulated 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 that the training procedure of the ANN is performed by using an illuminance estimator based on the lighting distribution of the luminaires, which is obtained through the .IES file provided by the luminaire manufacturer, which is the same file used for lighting designs. Therefore, by using the environment’s characteristics and the .IES file, the proposed system can provide data to train accurately the ANN used in the positioning method without the need to collect data from the environment. The results attested to the satisfactory performance of the proposed localization technique as it produced a mean distance error inferior to 1.16cm in a 3m × 3m × 3m environment and inferior to 3.83cm in a 3m × 1m × 3m environment, considering 0%, 30% and 70% walls reflectance levels.