Fusion of Radio and Camera Sensor Data for Accurate Indoor Positioning

TL;DR

This paper introduces RAVEL, a novel indoor positioning system that fuses camera visual detections with WiFi radio data to achieve sub-meter accuracy in complex environments, overcoming occlusion and ambiguity issues.

Contribution

The paper presents a new sensor fusion approach combining visual and radio data for indoor positioning, enhancing accuracy and robustness over existing lightweight solutions.

Findings

Achieved sub-meter positioning accuracy in a museum environment.

Effectively resolved visual ambiguities using radio measurements.

Demonstrated robustness in cluttered, dimly lit indoor spaces.

Abstract

Indoor positioning systems have received a lot of attention recently due to their importance for many location-based services, e.g. indoor navigation and smart buildings. Lightweight solutions based on WiFi and inertial sensing have gained popularity, but are not fit for demanding applications, such as expert museum guides and industrial settings, which typically require sub-meter location information. In this paper, we propose a novel positioning system, RAVEL (Radio And Vision Enhanced Localization), which fuses anonymous visual detections captured by widely available camera infrastructure, with radio readings (e.g. WiFi radio data). Although visual trackers can provide excellent positioning accuracy, they are plagued by issues such as occlusions and people entering/exiting the scene, preventing their use as a robust tracking solution. By incorporating radio measurements, visually ambiguous or missing data can be resolved through multi-hypothesis tracking. We evaluate our system in a complex museum environment with dim lighting and multiple people moving around in a space cluttered with exhibit stands. Our experiments show that although the WiFi measurements are not by themselves sufficiently accurate, when they are fused with camera data, they become a catalyst for pulling together ambiguous, fragmented, and anonymous visual tracklets into accurate and continuous paths, yielding typical errors below 1 meter.