# Neural Network-based Acoustic Vehicle Counting

arXiv: https://arxiv.org/abs/2010.11659 · HTML: https://mlsanity.com/paper/2010.11659/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2020.

## Built on by (most cited first, 2 of 2)

- [An approach to improving sound-based vehicle speed estimation](https://mlsanity.com/paper/2204.05082/) (2022)
- [Mel-spectrogram features for acoustic vehicle detection and speed estimation](https://mlsanity.com/paper/2204.04013/) (2022)

## Abstract (arXiv)

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%  confidence interval for the mean of vehicle counting error is within [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.