Neural network-based acoustic vehicle counting

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00351751" target="_blank" >RIV/68407700:21230/21:00351751 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.23919/EUSIPCO54536.2021.9615925" target="_blank" >https://doi.org/10.23919/EUSIPCO54536.2021.9615925</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.23919/EUSIPCO54536.2021.9615925" target="_blank" >10.23919/EUSIPCO54536.2021.9615925</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Neural network-based acoustic vehicle counting

Popis výsledku v původním jazyce

This paper addresses acoustic vehicle counting usingone-channel audio. We predict the pass-by instants of vehiclesfrom 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 regressionoutperforms by far the previously proposed support vectorregression. The95%confidence interval for the mean of vehiclecounting error is within[0.28%,-0.55%]. Besides the minima-based counting, we propose a deep learning counting that op-erates 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 notdepend on minima detection parameters. Results also show thatremoving low frequencies in features improves the countingperformance.

Název v anglickém jazyce

Neural network-based acoustic vehicle counting

Popis výsledku anglicky

This paper addresses acoustic vehicle counting usingone-channel audio. We predict the pass-by instants of vehiclesfrom 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 regressionoutperforms by far the previously proposed support vectorregression. The95%confidence interval for the mean of vehiclecounting error is within[0.28%,-0.55%]. Besides the minima-based counting, we propose a deep learning counting that op-erates 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 notdepend on minima detection parameters. Results also show thatremoving low frequencies in features improves the countingperformance.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

29th European Signal Processing Conference (EUSIPCO)

ISBN

9789082797060

ISSN

2219-5491

e-ISSN

2076-1465

Počet stran výsledku

5

Strana od-do

561-565

Název nakladatele

IEEE Signal Processing Society

Místo vydání

New Jersey

Místo konání akce

Dublin (virtual)

Datum konání akce

23. 8. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000764066600111