No abstract

No abstract

The recent interest in using visible light as a means of communication has opened up possibilities for using visible light for other applications as well, such as indoor positioning. Visible light offers higher bandwidth, immunity from electromagnetic radiation, and most importantly it can be seamlessly integrated into the existing lighting infrastructure. This paper proposes a visible light based positioning model for estimating an object's three-dimensional (3-D) parameters such as height and radius in addition to location in an indoor environment. The model is built using neural networks (NN), trained by simulating numerous multiple object scenarios in an indoor environment. It also takes into account the shadowing effects so it can be implemented in a multiple obstacle environment. The proposed algorithm has numerous applications, such as positioning assisted communication, suspicious object monitoring and surveillance in an indoor environment. The proposed model achieves a location accuracy of 5.4 cm, which could be further improved to 4 cm at the expense of extra hardware. The accuracy in measuring the height and radius of the objects using the proposed framework is observed to be 4.39 cm and 1.27 cm, respectively. In addition, we also propose a methodology to optimize the power distribution to the light-emitting-diodes (LED's) in order to get the optimum location accuracy while maintaining the total power constraint on the system. This method could be utilized to update the power allocated to the LEDs by exploiting the current location of the objects in the room to improve communication uplink by employing visible access points (VAP's).