Image Based Localization in Indoor Environments

Image based localization is an important problem with many applications. In our previous work, we presented a two step pipeline for performing image based localization of mobile devices in outdoor environments. In the first step, a query image is matched against a georeferenced 3D image database to retrieve the "closest" image. In the second step, the pose of the query image is recovered with respect to the "closest" image using cell phone sensors. As such, a key ingredient of our outdoor image based localization is a 3D georeferenced image database. In this paper, we extend this approach to indoors by utilizing a 3D locally referenced image database generated by an ambulatory depth acquisition backpack that is originally developed for 3D modeling of indoor environments. We demonstrate retrieval rate of 94% over a set of 83 query images taken in an indoor shopping center and characterize pose recovery accuracy of the same set.