Attention estimation by simultaneous analysis of viewer and view

Publikation: Forskning - peer reviewKonferenceartikel i proceeding

Abstrakt

This paper introduces a system for estimating the attention of a driver wearing a first person view camera using salient objects to improve gaze estimation. A challenging data set of pedestrians crossing intersections has been captured using Google Glass worn by a driver. A challenge unique to first person view from cars is that the interior of the car can take up a large part of the image. The proposed system automatically filters out the dashboard of the car, along with other parts of the instrumentation. The remaining area is used as a region of interest for a pedestrian detector. Two cameras looking at the driver are used to determine the direction of the driver’s gaze, by examining the eye corners and the center of the iris. This coarse gaze estimation is then linked to the detected pedestrians to determine which pedestrian the driver is focused on at any given time.
Luk

Detaljer

This paper introduces a system for estimating the attention of a driver wearing a first person view camera using salient objects to improve gaze estimation. A challenging data set of pedestrians crossing intersections has been captured using Google Glass worn by a driver. A challenge unique to first person view from cars is that the interior of the car can take up a large part of the image. The proposed system automatically filters out the dashboard of the car, along with other parts of the instrumentation. The remaining area is used as a region of interest for a pedestrian detector. Two cameras looking at the driver are used to determine the direction of the driver’s gaze, by examining the eye corners and the center of the iris. This coarse gaze estimation is then linked to the detected pedestrians to determine which pedestrian the driver is focused on at any given time.
OriginalsprogEngelsk
TitelIEEE 17th International Conference on Intelligent Transportation Systems (ITSC), 2014
Antal sider7
ForlagIEEE Press
Publikationsdato8 okt. 2014
Sider1381-1387
ISBN (Trykt)9781479960798
DOI
StatusUdgivet - 8 okt. 2014
PublikationsartForskning
Peer reviewJa
BegivenhedInternational Conference on Intelligent Transportation Systems, 2014 - Qingdao, Kina
Varighed: 8 okt. 201411 okt. 2014
Konferencens nummer: 17

Konference

KonferenceInternational Conference on Intelligent Transportation Systems, 2014
Nummer17
LandKina
ByQingdao
Periode08/10/201411/10/2014

Download-statistik

Ingen data tilgængelig
ID: 206657865