HyRise

Abstract

Floor localization is an integral part of indoor localization systems that are deployed in any typical high-rise building. Nevertheless, while many efforts have been made to detect floor change events leveraging phone-embedded sensors, there are still a number of pitfalls that need to be overcome to provide robust and accurate localization in the 3D space. In this paper, we present HyRise: a robust and ubiquitous probabilistic crowdsourcing-based floor determination system. HyRise is a hybrid system that combines the barometer sensor and the ubiquitous Wi-Fi access points installed in the building into a probabilistic framework to identify the user's floor. In particular, HyRise incorporates a discrete Markov localization algorithm where the motion model is based on the vertical transitions detected from the sampled pressure readings and the observation model is based on the overheard Wi-Fi access points (APs) to find the most probable floor of the user. HyRise also has provisions to handle practical deployment issues including handling the inherent drift in the barometer readings, the noisy wireless environment, heterogeneous devices, among others. HyRise is implemented on Android phones and evaluated using three different testbeds: a campus building, a shopping mall, and a residential building with different floorplan layouts and APs densities. The results show that HyRise can identify the exact user's floor correctly in 93%, 92% and 77% of the cases for the campus building, the shopping mall, and the more challenging residential building; respectively. In addition, it can identify the floor with at most 1-floor error in 100% of the cases for all three testbeds. Moreover, the floor localization accuracy outperforms that achieved by other state-of-the-art techniques by at least 79% and up to 278%. This accuracy is achieved with no training overhead, is robust to the different user devices, and is consistent in buildings with different structures and APs densities.