IDMT-Traffic: An Open Benchmark Dataset for Acoustic Traffic Monitoring Research

TL;DR

This paper introduces IDMT-Traffic, a comprehensive open dataset of stereo audio recordings for urban traffic monitoring, enabling evaluation of acoustic classification algorithms on various microphone qualities and hardware constraints.

Contribution

It provides a new benchmark dataset with diverse vehicle sounds and evaluates multiple CNN architectures for traffic classification and movement estimation.

Findings

Dataset includes 2.5 hours of stereo recordings of 4718 vehicle events.

Benchmark results show CNN architectures' effectiveness in vehicle type and direction estimation.

The dataset supports development of embedded audio traffic monitoring systems.

Abstract

In many urban areas, traffic load and noise pollution are constantly increasing. Automated systems for traffic monitoring are promising countermeasures, which allow to systematically quantify and predict local traffic flow in order to to support municipal traffic planning decisions. In this paper, we present a novel open benchmark dataset, containing 2.5 hours of stereo audio recordings of 4718 vehicle passing events captured with both high-quality sE8 and medium-quality MEMS microphones. This dataset is well suited to evaluate the use-case of deploying audio classification algorithms to embedded sensor devices with restricted microphone quality and hardware processing power. In addition, this paper provides a detailed review of recent acoustic traffic monitoring (ATM) algorithms as well as the results of two benchmark experiments on vehicle type classification and direction of movement estimation using four state-of-the-art convolutional neural network architectures.