Image Sensor-based Visible Light Positioning Dataset

This dataset was acquired during the dissertation entitled "Optical Camera Communications and Machine Learning for Indoor Visible Light Positioning". This work was carried out in the academic year 2020/2021 at the Instituto de Telecomunicações in Aveiro in the scope of the Integrated Master in Electronics and Telecommunications Engineering at the Department of Electronics, Telecommunication and Informatics of the University of Aveiro. The dataset was designed for Visible Light Positioning (VLP) and it consists of photographs of the ceiling with the camera facing up, with varying roll angles. The setup consists of eight emitters (Tridonic DLA G2 luminaires) modulated with OOK with frequencies ranging from 1 kHz to 4.5 kHz with a 500 Hz interval. With its distinctive feature, each LED luminaire presents a different pattern in the image acquired by the rolling shutter CMOS sensor. The images that constitute this dataset were acquired over a grid with 15 regularly spaced reference points on the floor surface.