LocaGen: Low-Overhead Indoor Localization Through Spatial Augmentation
This addresses the deployability issue for indoor localization systems by reducing data collection overhead, though it is incremental as it builds on existing fingerprinting and augmentation techniques.
The paper tackles the problem of high overhead in indoor localization systems by proposing LocaGen, a spatial augmentation framework that reduces fingerprinting effort; it achieves the same localization accuracy with 30% of locations unseen and up to 28% improvement over state-of-the-art methods.
Indoor localization systems commonly rely on fingerprinting, which requires extensive survey efforts to obtain location-tagged signal data, limiting their real-world deployability. Recent approaches that attempt to reduce this overhead either suffer from low representation ability, mode collapse issues, or require the effort of collecting data at all target locations. We present LocaGen, a novel spatial augmentation framework that significantly reduces fingerprinting overhead by generating high-quality synthetic data at completely unseen locations. LocaGen leverages a conditional diffusion model guided by a novel spatially aware optimization strategy to synthesize realistic fingerprints at unseen locations using only a subset of seen locations. To further improve our diffusion model performance, LocaGen augments seen location data based on domain-specific heuristics and strategically selects the seen and unseen locations using a novel density-based approach that ensures robust coverage. Our extensive evaluation on a real-world WiFi fingerprinting dataset shows that LocaGen maintains the same localization accuracy even with 30% of the locations unseen and achieves up to 28% improvement in accuracy over state-of-the-art augmentation methods.