Show simple item record

dc.contributor.authorBaumann, D
dc.contributor.authorMahmoud, M
dc.contributor.authorRobinson, Peter
dc.contributor.authorDias, E
dc.contributor.authorSkrypchuk, Lee
dc.date.accessioned2018-09-20T12:08:21Z
dc.date.available2018-09-20T12:08:21Z
dc.date.issued2017
dc.identifier.isbn9781538605639
dc.identifier.issn2156-8103
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/280586
dc.description.abstract—This paper presents a multimodal approach to invehicle classification of driver glances. Driver glance is a strong predictor of cognitive load and is a useful input to many applications in the automotive domain. Six descriptive glance regions are defined and a classifier is trained on video recordings of drivers from a single low-cost camera. Visual features such as head orientation, eye gaze and confidence ratings are extracted, then statistical methods are used to perform failure analysis and calibration on the visual features. Non-visual features such as steering wheel angle and indicator position are extracted from a RaceLogic VBOX system. The approach is evaluated on a dataset containing multiple 60 second samples from 14 participants recorded while driving in a natural environment. We compare our multimodal approach to separate unimodal approaches using both Support Vector Machine (SVM) and Random Forests (RF) classifiers. RF Mean Decrease in Gini Index is used to rank selected features which gives insight into the selected features and improves the classifier performance. We demonstrate that our multimodal approach yields significantly higher results than unimodal approaches. The final model achieves an average F1 score of 70.5% across the six classes.
dc.publisherIEEE
dc.titleMultimodal classification of driver glance
dc.typeConference Object
prism.endingPage394
prism.publicationDate2018
prism.publicationName2017 7th International Conference on Affective Computing and Intelligent Interaction, ACII 2017
prism.startingPage389
prism.volume2018-January
dc.identifier.doi10.17863/CAM.27954
dcterms.dateAccepted2017-07-14
rioxxterms.versionofrecord10.1109/ACII.2017.8273629
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2018-01-29
dc.contributor.orcidRobinson, Peter [0000-0003-0347-3789]
dc.contributor.orcidSkrypchuk, Lee [0000-0002-9619-6161]
rioxxterms.typeConference Paper/Proceeding/Abstract
pubs.conference-name2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII)
pubs.conference-start-date2017-10-23
pubs.conference-finish-date2017-10-26
rioxxterms.freetoread.startdate2019-01-29


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record