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

  title={IDMT-Traffic: An Open Benchmark Dataset for Acoustic Traffic Monitoring Research},
  author={Jakob Abe{\ss}er and Saichand Gourishetti and Andr'as K'atai and Tobias Clauss and Prachi Sharma and Judith Liebetrau},
  journal={2021 29th European Signal Processing Conference (EUSIPCO)},
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 15,706 2-second long stereo audio clips, which were extracted from 4718 vehicle passing events captured with both high-quality sE8 and medium… 
1 Citations

Figures and Tables from this paper

EGMM video surveillance for monitoring urban traffic scenario

The Enhanced Gaussian Mixture Model is proposed to overcome the addressed issue, efficiently detecting vehicles in complex traffic scenarios, resolving the contamination problem that occurred by slow-moving or momentarily stopped vehicles.



An Acoustic Traffic Monitoring System: Design and Implementation

  • Yueyue NaYanmeng GuoQ. FuYonghong Yan
  • Computer Science
    2015 IEEE 12th Intl Conf on Ubiquitous Intelligence and Computing and 2015 IEEE 12th Intl Conf on Autonomic and Trusted Computing and 2015 IEEE 15th Intl Conf on Scalable Computing and Communications and Its Associated Workshops (UIC-ATC-ScalCom)
  • 2015
An acoustic based traffic monitoring system is designed and implemented that utilizes a cross microphone array to collect road-side acoustic signals and is expected to have lower hardware cost, and become a good complement to the existing traffic monitoring techniques.

Audio-Based Machine Learning Model for Traffic Congestion Detection

  • R. GattoC. Forster
  • Computer Science
    IEEE Transactions on Intelligent Transportation Systems
  • 2021
The present work provides a solution that copes with the time, the cost and the constraints inherent to the activity of traffic monitoring, and uses the produced audio as a source of data for learning the traffic audio patterns.

Road Traffic Condition Estimation Based on Road Acoustics

A simple approach based on road acoustics is proposed to estimate the traffic density and to classify it into three categories as free, medium and jammed.

Robust Audio-Based Vehicle Counting in Low-to-Moderate Traffic Flow

The paper proposes to set the minima detection threshold at a point where the probabilities of false positives and false negatives coincide so they statistically cancel each other in total vehicle number, and introduces a novel high-frequency power feature to improve the regression accuracy in noisy environments.

Anomalous Sound Detection Using Deep Audio Representation and a BLSTM Network for Audio Surveillance of Roads

A framework based on multiple-stage deep autoencoder network (DAN) to extract the deep audio representation (DAR), which fuses complementary information from several input features and thus can be more discriminative and robust than those input features.

A multi-device dataset for urban acoustic scene classification

The acoustic scene classification task of DCASE 2018 Challenge and the TUT Urban Acoustic Scenes 2018 dataset provided for the task are introduced, and the performance of a baseline system in the task is evaluated.

Acoustic signal based traffic density state estimation using adaptive Neuro-Fuzzy classifier

  • P. BorkarL. Malik
  • Computer Science
    2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
  • 2013
This paper considers the problem of vehicular traffic density state estimation, based on the information present in cumulative acoustic signal acquired from a roadside-installed single microphone, using MFCC (Mel-Frequency Cepstral Coefficients) using the SCG algorithm.

Audio Surveillance of Roads: A System for Detecting Anomalous Sounds

A novel method for detecting road accidents by analyzing audio streams to identify hazardous situations such as tire skidding and car crashes is proposed and the obtained results confirm the effectiveness of the proposed approach.

Design of Acoustic Vehicle Count System using DTW

A vehicle counter using sidewalk microphones is presented and a vehicle count algorithm using a sound map based on DTW (dynamic time warping) is developed, which successfully counted vehicles with a precision of 0.92.

MAVD: A Dataset for Sound Event Detection in Urban Environments

We describe the public release of a dataset for sound event detection in urban environments, namely MAVD, which is the first of a series of datasets planned within an ongoing research project for