Community based approach for generating building layouts

Abstract

In this paper we propose the design and evaluation of an algorithm capable of inferring basic floor plans from motion paths generated from smartphone sensors. First we shortly discuss the applicability of modern smartphones equipped with various sensors to create motion paths through premises. Some dead reckoning approaches which are used to track and calculate the position of devices are mentioned. After that we present an algorithm which shall use motion paths for the creation of maps holding probabilistic information regarding the accessibility of specific areas within a confined structure such as a building. The algorithm thus differs from traditional SLAM and mapping approaches in that it explicitly focuses on map generation and path interpretation and does not implement any sort of sensorspecific processing. In the concluding evaluation it is shown that the presented algorithm while still prone to certain types of bad input data can calculate free space from the motion paths with a sufficient accuracy for basic mapping tasks, especially if more input samples are used. Finally, various possible improvements are discussed which may improve the algorithms processing quality and robustness.