Changes in the correlation between eye and steering movements indicate driver distraction
Download as DOCX, PDF1 like133 views
The document discusses using changes in the correlation between a driver's eye movements and steering movements to detect distraction. Drivers performed tasks in a simulator while eye and steering data were collected. The study found that even the weak correlation between eyes and steering during normal road scanning is sensitive to distraction. The time lag between eye and steering movements and the strength of their correlation changed with visual, cognitive, and combined distractions, demonstrating that eye-steering correlation statistics can detect distraction and differentiate between distraction types.
Changes in the correlation between eye and steering movements indicate driver distraction
- 1. CHANGES IN THE CORRELATION BETWEEN EYE AND STEERING MOVEMENTS INDICATE DRIVER DISTRACTION ABSTRACT: Driver distraction represents an increasingly important contributor to crashes and fatalities. Technology that can detect and mitigate distraction by alerting distracted drivers could play a central role in maintaining safety. Based on either eye measures or driver performance measures, numerous algorithms to detect distraction have been developed. Combining both eye glance and vehicle data could enhance distraction detection. The goal of this paper is to evaluate whether changes in the eye–steering correlation structure can indicate distraction. Drivers performed visual, cognitive, and cognitive/visual tasks while driving in a simulator. The auto- and cross-correlations of horizontal eye position and steering wheel angle show that eye movements associated with road scanning produce a low eye–steering correlation. However, even this weak correlation is sensitive to distraction. Time lead associated with the maximum correlation is sensitive to all three types of distraction, and the maximum correlation coefficient is most strongly affected by off-road glances. These results demonstrate that eye–steering correlation statistics can detect distraction and differentiate between types of distraction. EXISTING SYSTEM: DRIVER distraction is an important safety problem. Analysis of naturalistic data suggests distraction contributes to approximately 43% of motor vehicle crashes and 27% of near crashes. Analysis of fatal crashes shows that driver distraction contributed to an increasing proportion of crashes (i.e., 10% in 2005 and 16% in 2009, for a total of 5474 distraction related fatalities in 2009). This increase may reflect the rapidly developing invehicle technology and other electronic devices that place additional demands on drivers and might lead to distraction and diminished capacity to perform driving tasks. This situation threatens safe driving. Technology that can detect and mitigate distraction by providing drivers with feedback and alerts could play a central role in maintaining safety.
- 2. PROPOSED SYSTEM: In this paper, we are going to detect distraction based on visual behavior or driving performance. Identifying driver distraction in real time to predict dangerous situations associated with breakdowns in lane keeping control is a critical challenge in these systems’ design. For this purpose, it would be useful to define the relationship between visual behavior and vehicle control. Distraction might change the relationship between glance patterns and steering that lead to breakdowns in vehicle control, resulting in lane departures. Changes in this visual behavior–vehicle control relationship might indicate distraction. Thus, it is crucial to evaluate this relationship for normal (non-distracted) driving and examine if it changes with distraction. The perception–action control process plays a central role in driving, and a strong eye–steering correlation associated with this control process has been observed on curvy roads. This paper evaluates the eye–steering correlation on a straight road with the assumption that it might show a qualitatively and quantitatively different relationship compared with curvy roads and that it might be sensitive to distraction. HARDWARE REQURIMENT: Steering Angle Sensor Arm Microcontroller Bluetooth Pc Android Mobile Phone SOFTWARE REQURIMENT: Visual Studio Flash Magic
- 3. BLOCK DIAGRAM: Steering Angle Sensor ARM Controller PC with .NET Application Bluetooth