Welcome to Scribd, the world's digital library. Read, publish, and share books and documents. See more
Download
Standard view
Full view
of .
Look up keyword
Like this
4Activity
0 of .
Results for:
No results containing your search query
P. 1
Driver Drowsiness Detection

Driver Drowsiness Detection

Ratings: (0)|Views: 242|Likes:
Published by Laveen Prabhu S

More info:

Published by: Laveen Prabhu S on Aug 28, 2012
Copyright:Attribution Non-commercial

Availability:

Read on Scribd mobile: iPhone, iPad and Android.
download as PDF, TXT or read online from Scribd
See more
See less

05/12/2015

pdf

text

original

 
 
Driver Drowsiness Detection
Laveen Prabhu Selvaraj (Im No. 303657)
Abstract
Sleep disorders and various common acute directly or indirectly affect the quality and
quantity of one‘s sleep or otherwise cause excessive daytime fatigue. About 29 600
Norwegian accident-involved drivers received a questionnaire about the last accidentreported to their insurance company. About 9200 drivers (31%) returned the questionnaire.The questionnaire contained questions about sleep or fatigue as contributing factors to theaccident. In addition, the drivers reported whether or not they had fallen asleep some timewhilst driving, and what the consequences had been. Sleep or drowsiness was acontributing factor in 3.9% of all accidents, as reported by drivers who were at fault for theaccident. This factor was strongly over-represented in night-time accidents (18.6%), inrunning-off-the-road accidents (8.3%), accidents after driving more than 150 km on one trip(8.1%), and personal injury accidents (7.3%).The most frequent consequence of fallingasleep
amounting to more than 40% of the reported incidents
was crossing of the rightedge-line before awaking, whereas crossing of the centre
line was reported by 16%. Drivers‘
lack of awareness of important precursors of falling asleep
like highway hypnosis, drivingwithout awareness, and similar phenomena
as well as a reluctance to discontinue drivingdespite feeling tired are pointed out as likely contributors to sleep-related accidents. Theenvisioned vehicle-based driver drowsiness detection system would continuously andunob
trusively monitor driver performance (and ―micro
-
performance‖ such as minute steering
movements) and driver psychophysiological status (in particular eye closure). The systemmay be programmed to provide an immediate warning signal when drowsiness is detectedwith high certainty, or, alternatively, to present a verbal secondary task via recorded voice asa second-stage probe of driver status in situations of possible drowsiness. The keyrequirements and R&D challenges for a successful countermeasure include lowcountermeasure cost, true unobtrusiveness, an acceptably-low false alarm rate, non-disruption of the primary driving task, compatibility and synergy with other IVHS crashavoidance countermeasures, and a warning strategy that truly sustains driver wakefulness or convinces him/her to stop for rest.
1. Introduction
Fatigued or drowsy drivers have long beenacknowledged to constitute a potentialtraffic safety hazard, and several researchstudies have addressed various aspects of the problem. Brown (1994) has presenteda comprehensive review and discussion of the research literature on the nature of fatigue and its effects on driver behavior and traffic accidents, on the basis of which
he concluded that ‗fati
gue is insufficientlyrecognized and reported as a cause of 
road accidents‘. In discussing the effects
of fatigue, Brown further points out that the
main effect is ‗a progressive withdrawal of attention from road and traffic demands‘. A
 most extreme form of withdrawal of attention is obviously the closing of eyesdue to sleepiness. To prevent accidents
 
 
related to drowsiness and sleeping behindthe wheel, it is important to acquireprecise knowledge about the extent of theproblem as well as its preconditions andconsequences. The following issues, all of which are investigated empirically in thepresent study, are considered relevant for a better understanding of sleep-relatedaccidents.1. What is the proportion of accidentscaused by fatigue or sleep behind thewheel, and what are the most likely typesof accidents to occur under theseconditions?2. How prevalent is the problem of actuallyfalling asleep while driving?3. What are the most frequentconsequences of falling asleep whiledriving?4. To what extent is sleeping behind thewheel related to characteristics of thedriver, the road and traffic conditions, andthe trip?These drowsiness detection methods canbe categorized into three major approaches:
• Active driving or on
-board detection:Preventing accidents caused bydrowsiness behind the steering wheel ishighly desirable but requires techniques
for continuously estimating driver‘s
abilities of perception, recognition andvehicle control abilities. This paper proposes methods for drowsinessestimation that combine theelectroencephalogram (EEG) log subbandpower spectrum, correlation analysis,principal component analysis, and linear regression models to indirectly estimate
driver‘s drowsiness level in a virtual
-reality-based driving simulator. Resultsshow that it is feasible to quantitatively
monitor driver‘s alertness with concurrent
changes in driving performance in arealistic driving simulator.
• Imaging processing techniques: this
approach analyzes the images capturedby cameras to detect physical changes of drivers, such as eyelid movement, eyegaze, yawn, and head nodding. For example, the PERCLOS systemdeveloped by W. W. Wierwile et. al. usedcamera and imaging processingtechniques to measure the percentage of eyelid closure over the pupil over time.The three-in-one vehicle operator sensor developed by Northrop Grumman Co. alsoused the similar techniques. Although thisvision based method is not intrusive andwill not cause annoyance to drivers, thedrowsiness detection is not so accurate,which is severely affected by theenvironmental backgrounds, drivingconditions, and driver activities (such asturning around, talking, and picking upbeverage). In addition, this approachrequires the camera to focus on a relativesmall area
(around the driver‘s eyes). It
thus requires relative precise camerafocus adjustment for every driver.
• Physiological signal detection
techniques: this approach is to measurethe physiological changes of drivers frombiosignals, such as theelectroencephalogram (EEG),electrooculograph (EOG), andelectrocardiogram (ECG or EKG). Sincethe sleep rhythm is strongly correlatedwith brain and heart activities, thesephysiological biosignals can give accuratedrowsiness/sleepiness detection.However, all the researches up to date inthis approach need electrode contacts on
drivers‘ head, face, or chest. Wiring is
another problem for this approach. Theelectrode contacts and wires will annoythe drivers, and are difficult to beimplemented in real applications.
 
 
2. Active Driving or On board DetectionBasic Concepts
 As indicated earlier, the basic idea behindvehicle-based detection is to monitor thedriver unobtrusively by means of an on-board system that can detect when thedriver is materially impaired bydrowsiness. The concept involves sensingvarious drivers related and driving relatedvariables. Computing measures fromthese variables online and then using themeasures in a combined manner to detectwhen drowsiness is occurring. Measuresare combined because no singleunobtrusive operational measure appearsadequate in reliably detecting drowsiness.The most promising approach usesmathematical optimization procedures todevelop algorithms with the highestpotential detection accuracy. Techniquesnormally employed include multipleregression and linear discriminatedanalyses. More exotic techniques couldalso be employed in the future, includingneural networks, pattern recognition andfuzzy logic. Optimization of algorithms for detection of drowsiness requires a
definitional measure of ―actual‖
drowsiness. Such a measure may bebased on physiological, performance, or subjective attributes and need not beobtainable operationally. However, themeasure must be available in experimentsso that operational detection algorithms
can be ―trained‖ to
indicate the value of the definitional measure. This concept isdepicted inFigure 1.
Figure 1.
concept of using operationalmeasures to predict definitional measuresof drowsinessOn the left are measures that can beobtained in the driving environment. Thesemeasures (with the exception of secondary task measures) are obtainableoperationally from the vehicle withoutdisturbing the driver. They can be used invarious combinations for algorithmdevelopment. On the right are variouscandidate definitional measures. AVEOBSis an observer rating measure, EYEMEASand PERCLOS are measures of slow eye-closure, and NEWDEF is a measurecomposed of slow eye-closure, variousEEG waveform amplitudes (Alpha, Beta,and Theta), and mean heart rate. A givenalgorithm would be directed at indicatingthe level of only one definitional measure,or possibly a linear combination of them.In any case, operationally availablemeasures (on the left) are used to detectthe level of the definitional measure of drowsiness (on the right), with thresholdsset to indicate when drowsiness hasexceeded a pre-specified level.

Activity (4)

You've already reviewed this. Edit your review.
1 thousand reads
1 hundred reads
ArminMaglić liked this
Sara Ram liked this

You're Reading a Free Preview

Download
scribd
/*********** DO NOT ALTER ANYTHING BELOW THIS LINE ! ************/ var s_code=s.t();if(s_code)document.write(s_code)//-->