Real-time 3-D Mapping with Estimating Acoustic Materials

TL;DR

This paper presents a real-time system that estimates acoustic materials from visual cues and integrates them into a 3D map for improved sound-related robotic applications, using semantic segmentation and an update policy.

Contribution

It introduces a novel real-time method combining visual-based acoustic material estimation with 3D mapping for robotics.

Findings

Successful integration of acoustic material estimation into 3D maps

Enhanced environment understanding for sound source localization

Real-time performance demonstrated in indoor scenes

Abstract

This paper proposes a real-time system integrating an acoustic material estimation from visual appearance and an on-the-fly mapping in the 3-dimension. The proposed method estimates the acoustic materials of surroundings in indoor scenes and incorporates them to a 3-D occupancy map, as a robot moves around the environment. To estimate the acoustic material from the visual cue, we apply the state-of-the-art semantic segmentation CNN network based on the assumption that the visual appearance and the acoustic materials have a strong association. Furthermore, we introduce an update policy to handle the material estimations during the online mapping process. As a result, our environment map with acoustic material can be used for sound-related robotics applications, such as sound source localization taking into account various acoustic propagation (e.g., reflection).