Cargando…

High-Resolution Neural Network for Driver Visual Attention Prediction

Driving is a task that puts heavy demands on visual information, thereby the human visual system plays a critical role in making proper decisions for safe driving. Understanding a driver’s visual attention and relevant behavior information is a challenging but essential task in advanced driver-assis...

Descripción completa

Detalles Bibliográficos
Autores principales: Kang, Byeongkeun, Lee, Yeejin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7181285/
https://www.ncbi.nlm.nih.gov/pubmed/32260397
http://dx.doi.org/10.3390/s20072030
_version_ 1783526015221366784
author Kang, Byeongkeun
Lee, Yeejin
author_facet Kang, Byeongkeun
Lee, Yeejin
author_sort Kang, Byeongkeun
collection PubMed
description Driving is a task that puts heavy demands on visual information, thereby the human visual system plays a critical role in making proper decisions for safe driving. Understanding a driver’s visual attention and relevant behavior information is a challenging but essential task in advanced driver-assistance systems (ADAS) and efficient autonomous vehicles (AV). Specifically, robust prediction of a driver’s attention from images could be a crucial key to assist intelligent vehicle systems where a self-driving car is required to move safely interacting with the surrounding environment. Thus, in this paper, we investigate a human driver’s visual behavior in terms of computer vision to estimate the driver’s attention locations in images. First, we show that feature representations at high resolution improves visual attention prediction accuracy and localization performance when being fused with features at low-resolution. To demonstrate this, we employ a deep convolutional neural network framework that learns and extracts feature representations at multiple resolutions. In particular, the network maintains the feature representation with the highest resolution at the original image resolution. Second, attention prediction tends to be biased toward centers of images when neural networks are trained using typical visual attention datasets. To avoid overfitting to the center-biased solution, the network is trained using diverse regions of images. Finally, the experimental results verify that our proposed framework improves the prediction accuracy of a driver’s attention locations.
format Online
Article
Text
id pubmed-7181285
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-71812852020-04-28 High-Resolution Neural Network for Driver Visual Attention Prediction Kang, Byeongkeun Lee, Yeejin Sensors (Basel) Article Driving is a task that puts heavy demands on visual information, thereby the human visual system plays a critical role in making proper decisions for safe driving. Understanding a driver’s visual attention and relevant behavior information is a challenging but essential task in advanced driver-assistance systems (ADAS) and efficient autonomous vehicles (AV). Specifically, robust prediction of a driver’s attention from images could be a crucial key to assist intelligent vehicle systems where a self-driving car is required to move safely interacting with the surrounding environment. Thus, in this paper, we investigate a human driver’s visual behavior in terms of computer vision to estimate the driver’s attention locations in images. First, we show that feature representations at high resolution improves visual attention prediction accuracy and localization performance when being fused with features at low-resolution. To demonstrate this, we employ a deep convolutional neural network framework that learns and extracts feature representations at multiple resolutions. In particular, the network maintains the feature representation with the highest resolution at the original image resolution. Second, attention prediction tends to be biased toward centers of images when neural networks are trained using typical visual attention datasets. To avoid overfitting to the center-biased solution, the network is trained using diverse regions of images. Finally, the experimental results verify that our proposed framework improves the prediction accuracy of a driver’s attention locations. MDPI 2020-04-04 /pmc/articles/PMC7181285/ /pubmed/32260397 http://dx.doi.org/10.3390/s20072030 Text en © 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kang, Byeongkeun
Lee, Yeejin
High-Resolution Neural Network for Driver Visual Attention Prediction
title High-Resolution Neural Network for Driver Visual Attention Prediction
title_full High-Resolution Neural Network for Driver Visual Attention Prediction
title_fullStr High-Resolution Neural Network for Driver Visual Attention Prediction
title_full_unstemmed High-Resolution Neural Network for Driver Visual Attention Prediction
title_short High-Resolution Neural Network for Driver Visual Attention Prediction
title_sort high-resolution neural network for driver visual attention prediction
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7181285/
https://www.ncbi.nlm.nih.gov/pubmed/32260397
http://dx.doi.org/10.3390/s20072030
work_keys_str_mv AT kangbyeongkeun highresolutionneuralnetworkfordrivervisualattentionprediction
AT leeyeejin highresolutionneuralnetworkfordrivervisualattentionprediction