High-precision indoor positioning algorithm based on visible light communication using complementary metal–oxide–semiconductor image sensor

Visible light positioning (VLP) is widely believed to be a cost-effective answer to the growing demand for indoor positioning. There are two critical elements in VLP: positioning accuracy and real-time ability. Nevertheless, because of the nonlinear and highly complicated relationship between three-dimensional world coordinate and two-dimensional image coordinate, developing an effective VLP location algorithm to locate the positioning facility using complementary metal–oxide–semiconductor image sensor is of great need. Additionally, due to the high computational cost of image processing, most existing VLP systems fail to deliver satisfactory performance regarding real-time ability and positioning accuracy, both of which are crucial for the performance of an indoor positioning algorithm. Therefore, we propose a positioning algorithm: the triple-light positioning algorithm based on a situation with three light-emitting diodes (LEDs). The proposed positioning algorithm takes positioning accuracy into consideration. As there are merely binary linear equations to solve, real-time ability is also reflected in the proposed algorithm, which is very worth mentioning because most current positioning algorithms fail to deliver the efficiency. In addition, we treated the LED-ID detection and recognition problem, which is an essential part of the algorithm, as a classification problem in machine learning field and machine learning algorithm into consideration. Experiment results show that the proposed algorithm provides an accuracy of 4.38 cm and the computational time is 65.50 ms, suggesting that the proposed algorithm has a good performance in accuracy as well as real-time ability.