A fast indoor tracking algorithm based on particle filter and improved fingerprinting

Wi-Fi based indoor tracking has attracted considerable attention due to the growing need for location based service (LBS) and the rapid development of mobile phones. Most existing Wi-Fi based indoor tracking systems suffer from the low accuracy, due to the complexity of indoor environment, and the high time-delay, caused by the time consumption of positioning algorithm. In this paper, we propose a new tracking scheme based on particle filter and an improved k-nearest neighbor (KNN) algorithm. The particle filter is used to add motion constrains to the tracking model and reduce the measurement error. The improved KNN algorithm is used to provide the position in a fast and precise way. A series of experiments were implemented on a mobile phone and the results show that our scheme achieves superior performance than other existing algorithms.