Smartphone indoor localization by photo-taking of the environment

Existing mainstream indoor localization technologies mainly rely on RF signatures and thus incur significant and recurring labor cost to measure the time-varying signature map. We have proposed a smartphone localization system using the embedded gyroscope for triangulation from nearby physical features (e.g., store logos) recognized from photo-taking. It requires a much reduced and one-time measurement, while incurs uncertain localization errors. In this paper, we propose two methods to systematically address image matching errors that cause unrecognized physical features and large errors in our system. We formulate the optimal benchmark image selection problem and propose a heuristic algorithm that finds the best benchmark images for high matching accuracy. We propose a couple of geographical constraints to further infer unknown physical features based on the observation that the features chosen by the user are close together. Experiments in a 150 × 75m shopping mall, 300 × 200m train station show that dramatically we cut down both maximum and general localization errors, and achieve 2-8m accuracy at 80-percentile even with only one benchmark image on the phone.