English

Neural Network-based Acoustic Vehicle Counting

Sound 2021-03-30 v2 Machine Learning Audio and Speech Processing

Abstract

This paper addresses acoustic vehicle counting using one-channel audio. We predict the pass-by instants of vehicles from local minima of clipped vehicle-to-microphone distance. This distance is predicted from audio using a two-stage (coarse-fine) regression, with both stages realised via neural networks (NNs). Experiments show that the NN-based distance regression outperforms by far the previously proposed support vector regression. The 95% 95\% confidence interval for the mean of vehicle counting error is within [0.28%,0.55%][0.28\%, -0.55\%]. Besides the minima-based counting, we propose a deep learning counting that operates on the predicted distance without detecting local minima. Although outperformed in accuracy by the former approach, deep counting has a significant advantage in that it does not depend on minima detection parameters. Results also show that removing low frequencies in features improves the counting performance.

Keywords

Cite

@article{arxiv.2010.11659,
  title  = {Neural Network-based Acoustic Vehicle Counting},
  author = {Slobodan Djukanović and Yash Patel and Jiři Matas and Tuomas Virtanen},
  journal= {arXiv preprint arXiv:2010.11659},
  year   = {2021}
}
R2 v1 2026-06-23T19:33:13.745Z