On generalizing driver gaze zone estimation using convolutional neural networks
Authors:
- 1 June 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 849-854
Abstract
The knowledge of driver distraction will be important for self driving cars in the near future to determine the handoff time to the driver. Driver's gaze direction has been previously shown as an important cue in understanding distraction. While there has been a significant improvement in personalized driver gaze zone estimation systems, a generalized gaze zone estimation system which is invariant to different subjects, perspective and scale is still lagging behind. We take a step towards the generalized system using a Convolutional Neural Network (CNN). For evaluating our system, we collect large naturalistic driving data of 11 drives, driven by 10 subjects in two different cars and label gaze zones for 47515 frames. We train our CNN on 7 subjects and test on the other 3 subjects. Our best performing model achieves an accuracy of 93.36% showing good generalization capability.Keywords
This publication has 24 references indexed in Scilit:
- Where is the driver looking: Analysis of head, eye and iris for robust gaze zone estimation2014
- Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks2014
- Robust and continuous estimation of driver gaze zone by dynamic analysis of multiple face videos2014
- Effect of Passenger Presence on Older Drivers’ Risk of Fatal Crash InvolvementTraffic Injury Prevention, 2014
- Real-Time System for Monitoring Driver VigilanceIEEE Transactions on Intelligent Transportation Systems, 2006
- The influence of passengers on the risk of the driver causing a car collision in SpainAccident Analysis & Prevention, 2004
- Determining driver visual attention with one cameraIEEE Transactions on Intelligent Transportation Systems, 2003
- Real-Time Eye, Gaze, and Face Pose Tracking for Monitoring Driver VigilanceReal-Time Imaging, 2002
- Real Time Visual Cues Extraction for Monitoring Driver Vigilance2001
- Pupil detection and tracking using multiple light sourcesImage and Vision Computing, 2000