Performance comparison of point feature detectors and descriptors for visual navigation on Android platform

Consumer electronics mobile devices, such like smartphones and tablets, are quickly growing in computing power and become equipped with advanced sensors. This makes a modern mobile device a viable platform for many computation-intensive, real-time applications. In this paper we present a study on the performance and robustness of point features detection and description in images acquired by a mobile device in the context of visual navigation. This is an important step towards infrastructure-less indoor self-localization and user guidance using only a smartphone or tablet. We rigorously evaluate the performance of several interest point detector and descriptor pairs on three different Android devices, using image sequences from publicly available robotics-related data sets, as well as our own data set obtained using a smartphone.