Indoor corner recognition from crowdsourced trajectories using smartphone sensors

Recently, fingerprint crowdsourcing from pedestrian movement trajectories has been promoted to alleviate the site survey burden for radio map construction in fingerprinting-based indoor localization. Indoor corners, as one of the most common indoor landmarks, play an important role in movement trajectory analysis. This paper studies the problem of indoor corner recognition in crowdsourced movement trajectories. In a movement trajectory, smartphone internal sensor measurements experience some signal changes when passing by a corner. However, the state-of-the-art solutions based on signal change detection cannot well deal with the fake corner problem and pose diversity problem in most practical movement trajectories. In this paper, we study the corner recognition problem from an expert system viewpoint by applying machine learning techniques. In particular, we extract recognition features from both the time and frequency domain and propose a hierarchical corner recognition scheme consisting of three classifiers. The first pose classifier is to classify various poses into only two groups according to whether or not a smartphone is kept in a fixed position relative to a user upper body when collecting sensor measurements. Feature selection is then applied to train two corner classifiers each for one pose group. Field experiments are conducted to compare our proposed scheme with three state-of-the-art algorithms. In all cases, our scheme outperforms the best of these algorithms in terms of much higher F1-measure and precision for corner recognition. The results also provide insights on the potentials of using more advanced techniques from expert systems in indoor localization.