Can Synthetic Data Boost the Training of Deep Acoustic Vehicle Counting Networks?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Damiano, Stefano, Bondi, Luca, Ghaffarzadegan, Shabnam, Guntoro, Andre, van Waterschoot, Toon
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916095017877504
author Damiano, Stefano
Bondi, Luca
Ghaffarzadegan, Shabnam
Guntoro, Andre
van Waterschoot, Toon
author_facet Damiano, Stefano
Bondi, Luca
Ghaffarzadegan, Shabnam
Guntoro, Andre
van Waterschoot, Toon
contents In the design of traffic monitoring solutions for optimizing the urban mobility infrastructure, acoustic vehicle counting models have received attention due to their cost effectiveness and energy efficiency. Although deep learning has proven effective for visual traffic monitoring, its use has not been thoroughly investigated in the audio domain, likely due to real-world data scarcity. In this work, we propose a novel approach to acoustic vehicle counting by developing: i) a traffic noise simulation framework to synthesize realistic vehicle pass-by events; ii) a strategy to mix synthetic and real data to train a deep-learning model for traffic counting. The proposed system is capable of simultaneously counting cars and commercial vehicles driving on a two-lane road, and identifying their direction of travel under moderate traffic density conditions. With only 24 hours of labeled real-world traffic noise, we are able to improve counting accuracy on real-world data from $63\%$ to $88\%$ for cars and from $86\%$ to $94\%$ for commercial vehicles.
format Preprint
id arxiv_https___arxiv_org_abs_2401_09308
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Can Synthetic Data Boost the Training of Deep Acoustic Vehicle Counting Networks?
Damiano, Stefano
Bondi, Luca
Ghaffarzadegan, Shabnam
Guntoro, Andre
van Waterschoot, Toon
Audio and Speech Processing
Sound
In the design of traffic monitoring solutions for optimizing the urban mobility infrastructure, acoustic vehicle counting models have received attention due to their cost effectiveness and energy efficiency. Although deep learning has proven effective for visual traffic monitoring, its use has not been thoroughly investigated in the audio domain, likely due to real-world data scarcity. In this work, we propose a novel approach to acoustic vehicle counting by developing: i) a traffic noise simulation framework to synthesize realistic vehicle pass-by events; ii) a strategy to mix synthetic and real data to train a deep-learning model for traffic counting. The proposed system is capable of simultaneously counting cars and commercial vehicles driving on a two-lane road, and identifying their direction of travel under moderate traffic density conditions. With only 24 hours of labeled real-world traffic noise, we are able to improve counting accuracy on real-world data from $63\%$ to $88\%$ for cars and from $86\%$ to $94\%$ for commercial vehicles.
title Can Synthetic Data Boost the Training of Deep Acoustic Vehicle Counting Networks?
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2401.09308