What Can Be Predicted from Six Seconds of Driver Glances?

@article{Fridman2017WhatCB,
  title={What Can Be Predicted from Six Seconds of Driver Glances?},
  author={Alex Fridman and Heishiro Toyoda and Sean Seaman and Bobbie D. Seppelt and Linda S. Angell and Joonbum Lee and Bruce Mehler and B. Reimer},
  journal={Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems},
  year={2017}
}
We consider a large dataset of real-world, on-road driving from a 100-car naturalistic study to explore the predictive power of driver glances and, specifically, to answer the following question: what can be predicted about the state of the driver and the state of the driving environment from a 6-second sequence of macro-glances? The context-based nature of such glances allows for application of supervised learning to the problem of vision-based gaze estimation, making it robust, accurate, and… 

Figures and Tables from this paper

Using Naturalistic Vehicle-Based Data to Predict Distraction and Environmental Demand
This research utilized vehicle-based measures from a naturalistic driving dataset to detect distraction as indicated by long off-path glances (≥ 2 s) and whether the driver was engaged in a secondary
Dynamics of Driver's Gaze: Explorations in Behavior Modeling and Maneuver Prediction
TLDR
It is shown that condensing gaze dynamics into durations and frequencies leads to recurring patterns based on driver activities, and modeling these patterns show predictive powers in maneuver detection up to a few hundred milliseconds a priori.
Predicting Drivers’ Eyes-Off-Road Duration in Different Driving Scenarios
TLDR
Time series of glance allocations could be used to predict driving behavior and indentify driving environment and the developed models in this study could contribute to the development of scenario sensitive visual inattention prewarning system.
A Driver Situational Awareness Estimation System Based on Standard Glance Model for Unscheduled Takeover Situations
TLDR
A driver situational awareness estimation system based on glance information and a situational awareness assist system to visually indicate regions with insufficient glance found that the assist system drastically improved driving performance and reduced the number of accidents during takeover.
Development of a Situational Awareness Estimation Model Considering Traffic Environment for Unscheduled Takeover Situations
TLDR
A new SA estimation model considering driving-relevant objects and the relationship between parameters was developed and it was found that unscheduled TO led to maneuver error and glance behavior differed from individuals.
How do Environmental Factors Affect Drivers’ Gaze and Head Movements?
Studies have shown that environmental factors affect driving behaviors. For instance, weather conditions and the presence of a passenger have been shown to significantly affect the speed of the
Assessing the effect of in-vehicle task interactions on attention management in safety-critical events
Two analytic techniques were applied to study patterns of onand off-road glances in naturalistic driving. The dataset used in this study was the Naturalistic Engagement in Secondary Task (NEST)
MIT Advanced Vehicle Technology Study: Large-Scale Naturalistic Driving Study of Driver Behavior and Interaction With Automation
TLDR
The governing objectives of the MIT Advanced Vehicle Technology study are to undertake large-scale real-world driving data collection that includes high-definition video to fuel the development of deep learning-based internal and external perception systems and gain a holistic understanding of how human beings interact with vehicle automation technology.
Predicting Environmental Demand and Secondary Task Engagement using Vehicle Kinematics from Naturalistic Driving Data
TLDR
This paper focuses on exploiting the vehicle kinematic signals from a naturalistic driving dataset to estimate motor control difficulty associated with the driving environment, and detect whether the driver was engaged in a secondary task or not.
Drivers’ Visual Attention Characteristics under Different Cognitive Workloads: An On-Road Driving Behavior Study
TLDR
The current study finds that the difference between an on-road test and a driving simulation is that during the on- road driving process, drivers are twice as attentive to the front area than to the driving simulator.
...
1
2
3
4
...

References

SHOWING 1-10 OF 42 REFERENCES
How Dangerous Is Looking Away From the Road? Algorithms Predict Crash Risk From Glance Patterns in Naturalistic Driving
TLDR
The distraction level estimated by the algorithms that include current glance duration provides the most sensitive indicator of crash risk, and inform the design of algorithms to monitor driver state that support real-time distraction mitigation systems.
Nonintrusive Detection of Driver Cognitive Distraction in Real Time Using Bayesian Networks
TLDR
Bayesian networks (BNs), a data mining method, are applied to develop a real-time approach to detecting cognitive distraction using drivers’ eye movements and driving performance and demonstrate that BNs, especially DBNs, can detect driver cognitive distraction by extracting information from complex behavioral data.
Comparison of Two Eye-Gaze Based Real-Time Driver Distraction Detection Algorithms in a Small-Scale Field Operational Test
TLDR
The study describes and compares two different algorithms for gaze-based driver distraction detection based on the eye tracking data obtained in a field study and shows that both algorithms have potential for detecting driver distraction, but that no effect of the distraction warnings on attention as defined by the algorithms could be observed.
A visual approach for driver inattention detection
The 100-Car Naturalistic Driving Study Phase II – Results of the 100-Car Field Experiment
The "100-Car Naturalistic Driving Study" is a three-phased effort designed to accomplish three objectives: Phase I, Conduct Test Planning Activities; Phase II, Conduct a Field Test; and Phase III,
Real-Time Detection of Driver Cognitive Distraction Using Support Vector Machines
As use of in-vehicle information systems (IVISs) such as cell phones, navigation systems, and satellite radios has increased, driver distraction has become an important and growing safety concern. A
'Owl' and 'Lizard': patterns of head pose and eye pose in driver gaze classification
TLDR
This paper estimates head pose and eye pose from monocular video using methods developed extensively in prior work and describes how that accuracy varies between people, gaze strategies, and gaze regions.
Evaluation of Strategies for Integrated Classification of Visual-Manual and Cognitive Distractions in Driving
TLDR
The two-stage strategy was found to be sensitive for identifying states of visual-manual distraction; however, the strategy also produced a higher false alarm rate than direct-mapping and needs to account for strategic levels of vehicle control.
...
1
2
3
4
5
...