Indoor localization via multi-modal sensing on smartphones

Abstract

Indoor localization is of great importance to a wide range of applications in shopping malls, office buildings and public places. The maturity of computer vision (CV) techniques and the ubiquity of smartphone cameras hold promise for offering sub-meter accuracy localization services. However, pure CV-based solutions usually involve hundreds of photos and pre-calibration to construct image database, a labor-intensive overhead for practical deployment. We present ClickLoc, an accurate, easy-to-deploy, sensor-enriched, image-based indoor localization system. With core techniques rooted in semantic information extraction and optimization-based sensor data fusion, ClickLoc is able to bootstrap with few images. Leveraging sensor-enriched photos, ClickLoc also enables user localization with a single photo of the surrounding place of interest (POI) with high accuracy and short delay. Incorporating multi-modal localization with Manifold Alignment and Trapezoid Representation, ClickLoc not only localizes efficiently, but also provides image-assisted navigation. Extensive experiments in various environments show that the 80-percentile error is within 0.26m for POIs on the floor plan, which sheds light on sub-meter level indoor localization.