EyeLoc: Smartphone Vision Enabled Plug-n-play Indoor Localization in Large Shopping Malls

Indoor localization is an emerging demand in many large shopping malls. Existing indoor localization systems, however, require exhausted system bootstrap and calibration phases. The huge sunk cost usually hinders practical deployment of the indoor localization systems in large shopping malls. In contrast, we observe that floor-plan images of large shopping malls, which highlight the positions of many shops, are widely available in Google Maps, Gaode Maps, Baidu Maps etc. According to several observed shops, people can localize themselves (self-localization). However, due to the requirements of geometric sense and space transformation, not all people get used to this way. In this paper, we propose EyeLoc, which uses smartphone vision to enable accurate self-localization on floor-plan images. EyeLoc addresses several challenges which include developing ubiquitous smartphone vision system, efficient vision clue extraction and robust measurement error mitigation. We implement EyeLoc in Android and evaluate its performance in emulated environment and four large shopping malls. The 90-percentile errors of localization and heading direction are 4m and 20○ in the two large shopping malls.