Adaptive context-agnostic floor transition detection on smart mobile devices

We present a technique for detecting floor changes in an indoor environment and improving pedestrian indoor localization and navigation. Our technique relies on barometric pressure sensors commonly available on smartphones and tablets. We developed an algorithm running on smart mobile devices that can be integrated in any indoor localization system to improve accuracy and support 3D navigation. The main novelty of our technique is that it can work in any type of environment, without any prior knowledge of the building layout, it does not require calibration and it is adaptive. Experimental results show that our method can accurately detect floor changes in any condition without requiring any additional work.