On Training Road Surface Classifiers by Data Augmentation
It is demonstrated that data augmentation is a promising approach to reduce the size of the captured dataset required for training automatic road surface classifiers. The context is on-board systems for autonomous or semi-autonomous driving assistance: automatic power-assisted steering. Evidence is...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-03-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/7/3423 |
_version_ | 1797440467218989056 |
---|---|
author | Addisson Salazar Alberto Rodríguez Nancy Vargas Luis Vergara |
author_facet | Addisson Salazar Alberto Rodríguez Nancy Vargas Luis Vergara |
author_sort | Addisson Salazar |
collection | DOAJ |
description | It is demonstrated that data augmentation is a promising approach to reduce the size of the captured dataset required for training automatic road surface classifiers. The context is on-board systems for autonomous or semi-autonomous driving assistance: automatic power-assisted steering. Evidence is obtained by extensive experiments involving multiple captures from a 10-channel multisensor deployment: three channels from the accelerometer (acceleration in the X, Y, and Z axes); three microphone channels; two speed channels; and the torque and position of the handwheel. These captures were made under different settings: three worm-gear interface configurations; hands on or off the wheel; vehicle speed (constant speed of 10, 15, 20, 30 km/h, or accelerating from 0 to 30 km/h); and road surface (smooth flat asphalt, stripes, or cobblestones). It has been demonstrated in the experiments that data augmentation allows a reduction by an approximate factor of 1.5 in the size of the captured training dataset. |
first_indexed | 2024-03-09T12:07:34Z |
format | Article |
id | doaj.art-51d7d2aa15a94182834ecc798596ff87 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T12:07:34Z |
publishDate | 2022-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-51d7d2aa15a94182834ecc798596ff872023-11-30T22:55:32ZengMDPI AGApplied Sciences2076-34172022-03-01127342310.3390/app12073423On Training Road Surface Classifiers by Data AugmentationAddisson Salazar0Alberto Rodríguez1Nancy Vargas2Luis Vergara3Instituto de Telecomunicaciones y Aplicaciones Multimedia, Universitat Politècnica de València, C/Camino de Vera s/n, 46022 València, SpainDepartamento de Ingeniería de Comunicación, Universidad Miguel Hernández, Avda. de la Universitat d’Elx s/n, 03202 Alicante, SpainInstituto de Telecomunicaciones y Aplicaciones Multimedia, Universitat Politècnica de València, C/Camino de Vera s/n, 46022 València, SpainInstituto de Telecomunicaciones y Aplicaciones Multimedia, Universitat Politècnica de València, C/Camino de Vera s/n, 46022 València, SpainIt is demonstrated that data augmentation is a promising approach to reduce the size of the captured dataset required for training automatic road surface classifiers. The context is on-board systems for autonomous or semi-autonomous driving assistance: automatic power-assisted steering. Evidence is obtained by extensive experiments involving multiple captures from a 10-channel multisensor deployment: three channels from the accelerometer (acceleration in the X, Y, and Z axes); three microphone channels; two speed channels; and the torque and position of the handwheel. These captures were made under different settings: three worm-gear interface configurations; hands on or off the wheel; vehicle speed (constant speed of 10, 15, 20, 30 km/h, or accelerating from 0 to 30 km/h); and road surface (smooth flat asphalt, stripes, or cobblestones). It has been demonstrated in the experiments that data augmentation allows a reduction by an approximate factor of 1.5 in the size of the captured training dataset.https://www.mdpi.com/2076-3417/12/7/3423driving assistanceroad surface classificationmachine learningdata augmentation |
spellingShingle | Addisson Salazar Alberto Rodríguez Nancy Vargas Luis Vergara On Training Road Surface Classifiers by Data Augmentation Applied Sciences driving assistance road surface classification machine learning data augmentation |
title | On Training Road Surface Classifiers by Data Augmentation |
title_full | On Training Road Surface Classifiers by Data Augmentation |
title_fullStr | On Training Road Surface Classifiers by Data Augmentation |
title_full_unstemmed | On Training Road Surface Classifiers by Data Augmentation |
title_short | On Training Road Surface Classifiers by Data Augmentation |
title_sort | on training road surface classifiers by data augmentation |
topic | driving assistance road surface classification machine learning data augmentation |
url | https://www.mdpi.com/2076-3417/12/7/3423 |
work_keys_str_mv | AT addissonsalazar ontrainingroadsurfaceclassifiersbydataaugmentation AT albertorodriguez ontrainingroadsurfaceclassifiersbydataaugmentation AT nancyvargas ontrainingroadsurfaceclassifiersbydataaugmentation AT luisvergara ontrainingroadsurfaceclassifiersbydataaugmentation |