Journal · 2025
Reference-Free 3D WiFi AP Localization by Outdoor-to-Indoor Bridging
Abstract
WiFi access point (AP) localization is essential for wireless infrastructure management and location-based services. While deep learning approaches have shown promising accuracy improvements, they require extensive training data with precise coordinates, making large-scale deployment impractical. Traditional localization techniques also rely heavily on indoor reference points (RPs), resulting in costly and labor-intensive deployments. We present WiSight, a novel framework that eliminates the need for indoor RPs by leveraging GPS-tagged outdoor RSS measurements and 3D building geometry, anchoring the indoor reference frame to the global coordinate system using GPS-tagged exterior points. WiSight first identifies virtual anchor positions on building exteriors through outdoor signal propagation modeling, then reconstructs indoor AP configurations using unlabeled RSS measurement pairs and multidimensional scaling. Extensive evaluation across multiple buildings demonstrates that WiSight achieves an average 3D AP localization error of 7.1 m (median: 6.8 m), reducing error by 59% compared to an opportunistic GPS-based approach. In office environments, WiSight attains 9.6 m error (median: 8.5 m)—22% lower than the state-of-the-art deep learning-based method, while achieving 82% floor-level accuracy without requiring any indoor RPs or training data.
Research Note
Knowing where WiFi access points are physically installed matters both for managing wireless infrastructure and for location-based services, yet accurate records frequently do not exist. Estimating their positions from radio signals has been studied extensively, and deep learning improves accuracy, but it requires large amounts of training data annotated with precise coordinates, which is impractical to gather building by building. Conventional localization techniques instead depend on numerous indoor reference points, which is costly and labour-intensive.
WiSight removes the need for indoor reference points entirely. It works from GPS-tagged outdoor signal strength measurements together with 3D building geometry. Outdoors, GPS is available, so measurement points taken around the exterior serve as the link to the global coordinate system, and the indoor frame can be anchored to it through them. The idea is to bridge from outdoors to indoors.
Concretely, outdoor propagation modelling first identifies virtual anchor positions on the building exterior. Indoor access point configurations are then reconstructed from unlabelled pairs of signal strength measurements using multidimensional scaling, a technique that recovers coordinates from the relations between distances alone, so that a layout can be assembled even when no absolute position is known.
Across multiple buildings the method achieved an average 3D localization error of 7.1 m with a median of 6.8 m, a 59% reduction relative to an opportunistic GPS-based approach. In office environments the error was 9.6 m with a median of 8.5 m, which is 22% lower than the state-of-the-art deep learning method, and floor-level accuracy reached 82% without any indoor reference points or training data.
Related Projects
