| 1. |
- Ahlström, Christer, et al.
(författare)
-
A gaze-based driver distraction warning system and its effect on visual behaviour
- 2013
-
Ingår i: IEEE transactions on intelligent transportation systems (Print). - : Institute of Electrical and Electronics Engineers (IEEE). - 1524-9050 .- 1558-0016. ; 14:2, s. 965-973
-
Tidskriftsartikel (refereegranskat)abstract
- Driver distraction is a contributing factor to many crashes; therefore, a real-time distraction warning system should have the potential to mitigate or circumvent many of these crashes. The objective of this paper is to investigate the usefulness of a real-time distraction detection algorithm called AttenD. The evaluation is based on data from an extended field study comprising seven drivers who drove on an average of 4351 ± 2181 km in a naturalistic setting.Visual behavior was investigated both on a global scale and on a local scale in the surroundings of each warning. An increase in the percentage of glances at the rear-view mirror and a decrease in the amount of glances at the center console were found. The results also show that visual time sharing decreased in duration from 9.94 to 9.20 s due to the warnings, that the time from fully attentive to warning decreased from 3.20 to 3.03 s, and that the time from warning to full attentiveness decreased from 6.02 to 5.46 s. The limited number of participants does not allow any generalizable conclusions, but a trend toward improved visual behavior could be observed. This is a promising start for further improvements of the algorithm and the warning strategy.
|
|
| 2. |
|
|
| 3. |
- Ahlström, Christer, et al.
(författare)
-
Considerations when calculating percent road centre from eye movement data in driver distraction monitoring
- 2009
-
Ingår i: Proceedings of the Fifth International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design. ; , s. 132-139
-
Konferensbidrag (refereegranskat)abstract
- Percent road center (PRC) is a performance indicator which is sensitive to driver distraction. The original definition of PRC is based on fixation data extracted from eye movement recordings, but it has also been suggested that PRC can be determined directly from the gaze data without segmenting it into saccades and fixations. The primary aim of this paper is to investigate if this is the case.Naturalistic driving data from a small scale field operational test comprising seven vehicles was used in the evaluation. It was found that PRC time traces based on gaze data and fixation data, respectively, were highly similar (correlation coefficient=0.95, average wavelet semblance=0.84) except for an absolute amplitude difference of about 8%. This indicates that the two approaches can be used interchangeably and that the processing step of segmenting gaze data into saccades and fixations can be left out.In addition to this finding, design issues related to the calculation of PRC are investigated. Especially, the impact of gaze cases pointing towards the intersection of the road centre area and the centre rear mirror were investigated. Results lead to conclude that gazes and fixations on the centre rear mirror should be removed from the PRC calculations, as they may negatively influence the correctness of the performance indicator.
|
|
| 4. |
|
|
| 5. |
- Kircher, Katja, 1973-, et al.
(författare)
-
Comparison of two eye-gaze based real-time driver distraction detection algorithms in a small-scale field operational test
- 2009
-
Ingår i: Proceedings of the 5th International Driving Symposium on Human Factors in Driver Assessment and Design. ; , s. 16-23
-
Konferensbidrag (refereegranskat)abstract
- Driver distraction is a field which has received increasing attention in the last years, especially after it became evident that distraction is a major factor contributing to road casualties. Monitoring, detecting and limiting driver distraction could contribute significantly to improve road traffic safety. With the introduction of novel unobtrusive gaze-tracking systems real-time algorithms based on the driver’s gaze direction can be developed for driver distraction warning systems.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. One algorithm relies on the metric “percent road centre” of gaze direction, the other on gaze zones in the vehicle. Results show 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.
|
|
| 6. |
|
|
| 7. |
- Kircher, Katja, 1973-, et al.
(författare)
-
Distraction and drowsiness - a field study : technical report
- 2009
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- The main goal of the distraction and drowsiness field study was to evaluate a system for detecting driver distraction and drowsiness. This report focuses on the system implementation and the algorithms detecting distraction and drowsiness. A vehicle was instrumented with video cameras, an automatic eye tracker and GPS receivers. Further data were read from the CAN bus of the car. The data were logged continuously with high frequency. The log system operated autonomously. Seven participants drove the vehicle during one month each. During the first ten days a behavioural baseline was collected. Afterwards the warnings were activated, such that the drivers received distraction warnings in form of a vibration in the seat when the algorithm determined that they had looked away from the forward roadway too much. A separate algorithm judged whether the drivers were drowsy or not. Questionnaires were administered on three occasions during the course of the study. No major problems were encountered during the field operational test (FOT), but a number of smaller problems had to be solved. However, in the end of the data collection period the computer installed in the car became more and more unstable, which led to increased data loss.
|
|
| 8. |
|
|
| 9. |
- Kircher, Katja, et al.
(författare)
-
Passering av buss i 30 km/h : utvärdering av säkerhetseffekter i samband med hastighetsgräns 30 km/h vid passering av buss - en simulatorstudie
- 2007
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- A simulator study was conducted to investigate the implementation of a new law which prescribes a speed limit of 30 km/h when passing buses equipped with a 30-sign and flashing lights. It was shown that the drivers follow the rule better when they pass a bus on their own side than when the bus was standing on the opposite side of the road. The slowest mean speeds were found when passing a bus on a road with a speed limit of 70 km/h. The highest speed reduction, however, was found when the posted speed limit was 90 km/h. A bus without signage did not induce the same speed reduction as a bus with signage, which means that the drivers were aware of the meaning of the signage. Driving behaviour showed that the flashing lights are of importance, because the drivers in the study started braking before the 30-sign was readable.
|
|
| 10. |
|
|
