Driver distraction based lane-keeping assistance

Blaschke, Christoph; Breyer, F.; Färber, Berthold; Freyer, Jörn; Limbacher, Reimund

doi:10.1016/j.trf.2009.02.002

Cited by 73 publications

(45 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such a smart assistance, which recognizes driver's intention and state, would allow for a greater safety margin, without irritating the driver with false alarms or inappropriate interventions in normal driving conditions, so enhancing the user acceptability. Therefore, in recent years, several methods have been published, which aims at estimating driver's distraction (for example [17]- [20]) or also which concentrate on the detection and modeling of fatigue or stress as fundamental causes for driver's inattention (like [21]- [22]). …”

Section: Distraction Definitionmentioning

confidence: 99%

Real-Time Detection System of Driver Distraction Using Machine Learning

Tango

Botta

2013

IEEE Trans. Intell. Transport. Syst.

157

View full text Add to dashboard Cite

Abstract-There is an accumulating evidence that driver's distraction is a leading cause of vehicle crashes and incidents. In particular, it has become an important and growing safety concern with the increasing use of the so-called In-Vehicle Information Systems (IVIS) and Partially Autonomous Driving Assistance Systems (PADAS). Thereby, the detection of the driver status is of paramount importance, in order to adapt IVIS and PADAS accordingly, so avoiding or mitigating their possible negative effects. The purpose of this paper is to illustrate a method for the non-intrusive and real-time detection of visual distraction, based on vehicle dynamics data and without using the eye-tracker data as inputs to classifiers. Specifically, we present and compare different models, based on well-known Machine Learning methods. Data for training the models were collected using a static driving simulator, with real human subjects performing a specific secondary task (SURT) while driving. Different training methods, model characteristics and feature selection criteria have been compared. Based on our results, SVM has outperformed all the other ML methods, providing the highest classification rate for most of the subjects. Potential applications of this research include the design of adaptive IVIS and of "smarter" PADAS.Index Terms -Accident prevention; artificial intelligence and machine learning; driver' distraction and inattention; intelligent supporting systems.

show abstract

Section: Distraction Definitionmentioning

confidence: 99%

Real-Time Detection System of Driver Distraction Using Machine Learning

Tango

Botta

2013

IEEE Trans. Intell. Transport. Syst.

157

View full text Add to dashboard Cite

show abstract

“…The car was equipped with the Audi Multimedia System (see Figure 1) and an interface to measure Controller Area Network (CAN)-Bus data. Additionally, a head tracking system [9] was installed, which was able to measure head position and head rotation. This data was also sent on CAN-Bus.…”

Section: Database and Signalsmentioning

confidence: 99%

“…This would allow for a greater safety margin without irritating the driver with false alarms in normal driving situations. In [9] three main approaches to such a recognition are discussed: monitoring of driver's perception, monitoring of driver steering and lane-keeping behavior, and the recognition of the driver's involvement in a secondary task itself. In recent years, several techniques trying to estimate the driver to be distracted have been published.…”

mentioning

confidence: 99%

Online Driver Distraction Detection Using Long Short-Term Memory

Wöllmer

Blaschke

Schindl

et al. 2011

IEEE Trans. Intell. Transport. Syst.

153

111

View full text Add to dashboard Cite

Abstract-Lane-keeping assistance systems for vehicles may be more acceptable to users if the assistance was adaptive to the driver's state. To adapt systems in this way, a method for detection of driver distraction is needed. Thus, we propose a novel technique for on-line detection of driver's distraction, modeling the long-range temporal context of driving and head tracking data. We show that Long Short-Term Memory (LSTM) recurrent neural networks enable a reliable, subject-independent detection of inattention with an accuracy of up to 96.6 %. Thereby our LSTM framework significantly outperforms conventional approaches such as Support Vector Machines.

show abstract

“…In the technology-equipped vehicle perspective, numerous studies have reported positive effects of the Advanced Driver Assistance Systems (ADAS) on safer driving style. Results from the studies suggested that meaningful improvements in driving safety behavior were observed [2][3][4][5]. For example, Son et al suggested that the ADAS supported male drivers significantly increased the time headway safety margin [2].…”

Section: Introductionmentioning

confidence: 99%

2C5-1 Effect of advanced driver assistance systems on driving style and fuel economy

Son

Park

Kim

2015

The Japanese journal of ergonomics

View full text Add to dashboard Cite

It is known that driving style is highly correlated with safety and fuel economy. In general, drivers who have moderate driving style shows safer driving behavior than aggressive drivers, and they may achieve higher fuel efficiency than their aggressive counterpart. Some previous studies found forward collision warning systems supported to change driving style toward safer behavior. However, their potential benefit of improving fuel economy was not clearly evaluated.This paper aims to analyze the effect of the advanced driver assistance systems (ADAS) on driving style and fuel economy using field operational test data from 52 participants. A half of participants were supported by ADAS and the others were not supported. Each participant drove approximately 5.5 km of rural road (about 10 minutes), 6.2 km of urban road (about 25 minutes) and 9.6 km of highway (about 10 minutes). The results suggested that there has been significant interaction between ADAS and gender on driving style, and consequently ADAS supported younger male drivers' improvement in fuel efficiency was observed.

show abstract

Driver distraction based lane-keeping assistance

Cited by 73 publications

References 8 publications

Real-Time Detection System of Driver Distraction Using Machine Learning

Real-Time Detection System of Driver Distraction Using Machine Learning

Online Driver Distraction Detection Using Long Short-Term Memory

2C5-1 Effect of advanced driver assistance systems on driving style and fuel economy

Contact Info

Product

Resources

About