Improved Vehicle Sub-type Classification for Acoustic Traffic Monitoring

TL;DR

This paper presents an acoustic vehicle sub-type classification method using CNNs that outperforms previous approaches, especially in low-light and privacy-sensitive environments, achieving 98.95% accuracy on a traffic dataset.

Contribution

It introduces an optimized CNN approach with MFCC features for acoustic vehicle classification, surpassing state-of-the-art accuracy on the IDMT Traffic dataset.

Findings

Achieved 98.95% accuracy with MFCC features.

Outperformed existing state-of-the-art baseline.

Demonstrated effectiveness in low-light and privacy-sensitive scenarios.

Abstract

The detection and classification of vehicles on the road is a crucial task for traffic monitoring. Usually, Computer Vision (CV) algorithms dominate the task of vehicle classification on the road, but CV methodologies might suffer in poor lighting conditions and require greater amounts of computational power. Additionally, there is a privacy concern with installing cameras in sensitive and secure areas. In contrast, acoustic traffic monitoring is cost-effective, and can provide greater accuracy, particularly in low lighting conditions and in places where cameras cannot be installed. In this paper, we consider the task of acoustic vehicle sub-type classification, where we classify acoustic signals into 4 classes: car, truck, bike, and no vehicle. We experimented with Mel spectrograms, MFCC and GFCC as features and performed data pre-processing to train a simple, well optimized CNN that performs well at the task. When used with MFCC as features and careful data pre-processing, our proposed methodology improves upon the established state-of-the-art baseline on the IDMT Traffic dataset with an accuracy of 98.95%.