The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Articles | Volume XLVI-3/W1-2022
22 Apr 2022
 | 22 Apr 2022


X. Cao, G. Chen, Y. Zhuang, X. Wang, and X. Yang

Keywords: Wi-Fi fingerprint indoor positioning, morphology similarity distance, device heterogeneity, outlier detection, combined weight

Abstract. Wi-Fi fingerprint positioning is widely used because of its ready hardware and high accuracy. However, its application is considerably restricted by time-consuming and labor-intensive works of offline collection and irregular fluctuation of signals. To address the above problems, we proposed a novel method to deploy the Wi-Fi fingerprint database based on implicit crowdsourcing and improved the weighted k-nearest neighbor (WKNN) algorithm to eliminate the influence of neighbor mismatching and device heterogeneity. First, ordinary users continuously gather Wi-Fi information instead of collecting one point after another. Meanwhile, video surveillance cameras record users’ trajectories without any intervention and use monocular vision based on plane constraints to obtain users’ location at the moment of each scanning. At the localization phase, the morphology similarity distance instead of the Euclidean distance is used to measure the similarity of signals to solve the problem of device heterogeneity. Outlier detection is also utilized for a secondary selection of neighbor points. Finally, geometric and signal morphology similarity distances are used to determine the combined weight of all neighbors after the dimensionless treatment. Results of the experiments conducted in a real indoor environment show that the proposed strategy improves the efficiency of fingerprint collection and achieves higher positioning accuracy.