Abstract

This paper proposes an RGB-D sensor-aided ray-tracing simulation framework for indoor radio map construction that models indoor information, such as walls and obstacles, as a set of cuboids. Radio maps can accelerate indoor wireless systems, including resource optimization and fingerprint-based localization. We can construct an accurate radio map using a ray-tracing algorithm with precise information about indoor structures and obstacles. However, it is difficult to acquire this indoor information because manual observations, including the placement of obstacles, are expensive. To mitigate this critical drawback, we propose the acquisition of colored point clouds using an RGB-D sensor. After the point clouds are labeled via a three-dimensional semantic segmentation task, we model the indoor information as a set of cuboids that can be immediately used for the ray-tracing simulation. Indoor experiments using wireless LANs over 5180 and 2452 MHz clarified that the proposed method accurately automates the radio-map construction process from indoor information acquisition to radio propagation simulation.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call