FloorTag: A Hybrid Indoor Localization System Based on Floor-Deployed Visual Markers and Pedometer Integration

Abstract

[EN]With the widespread adoption of smartphones and wearable devices, localization systems have become increasingly important in modern society. While Global Positioning System (GPS) technology is widely accepted as a standard outdoors, accurately determining user location indoors remains a significant challenge despite extensive research efforts. Indoor positioning systems (IPSs) play a critical role in various sectors, including retail, tourism, transportation, healthcare, and emergency services. However, existing solutions require costly infrastructure deployments, complex area mapping, or offer suboptimal user experiences without achieving satisfactory accuracy. This paper introduces FloorTag, a scalable, low-cost, and minimally invasive hybrid IPS designed specifically for smartphone platforms. FloorTag leverages a combination of 2D visual markers placed on floor surfaces at key locations, and inertial sensor data from mobile devices. Each marker is associated with a unique identifier and precise spatial coordinates, enabling an immediate reset of accumulated localization errors upon detection. Between markers, a pedometer-based dead reckoning module maintains continuous location tracking. The localization process is designed to be seamless and unobtrusive to the user. When activated by the app during navigation, the phone’s rear camera, naturally angled toward the floor during walking, captures markers. This solution avoids explicit user scans while preserving the performance benefits of visual positioning. To model the indoor environment, FloorTag introduces the concept of Path-Points, which discretize the walkable space, and Informative Layers, which add semantic context to the navigation experience. This paper details the proposed methodology and the client–server system architecture and presents experimental results obtained from a prototype deployed in an academic building at the University of Catania, Italy. The findings demonstrate reliable localization at approximately 2 m spatial granularity and near-real-time performance across varying lighting conditions, confirming the feasibility of the approach and the effectiveness of the system.