Audio-Visual Calibration with Polynomial Regression for 2-D Projection Using SVD-PHAT
Audio and Speech Processing
2020-02-13 v2 Sound
Signal Processing
Abstract
This paper proposes a straightforward 2-D method to spatially calibrate the visual field of a camera with the auditory field of an array microphone by generating and overlaying an acoustic image over an optical image. Using a low-cost microphone array and an off-the-shelf camera, we show that polynomial regression can deal efficiently with non-linear camera distortion, and that a recently proposed sound source localization method for real-time processing, SVD-PHAT, can be adapted for this task.
Cite
@article{arxiv.2002.01440,
title = {Audio-Visual Calibration with Polynomial Regression for 2-D Projection Using SVD-PHAT},
author = {Francois Grondin and Hao Tang and James Glass},
journal= {arXiv preprint arXiv:2002.01440},
year = {2020}
}