The Driver Distraction Detection Algorithm AttenD

Kircher, Katja; Ahlström, Christer

doi:10.1201/9781315578156-23

Cited by 33 publications

(50 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This was measured as the mean amount of time the driver spent glancing away from the road between each button press, not including the time spent looking at the road. The fourth and final DV was the AttenD algorithm (Kircher and Ahlstrom, 2009). AttenD provides insight into how a driver balances their visual attention between activities.…”

Section: Sa During In-vehicle Multitaskingmentioning

confidence: 99%

“…As current eye tracking cannot determine what the driver is looking at depth-wise, the region will be coded neutrally and therefore whenever the driver is looking at the HUD, the buffer value will remain the same. As soon as they glance to another region, the ruleset defined in (Kircher and Ahlstrom, 2009) will be followed. For consistency, this will be the case during all experimental conditions.…”

Section: Attention Management Bothmentioning

confidence: 99%

“…For Attention Management (AM, Figure 17), the AttenD algorithm was used, with HUD coded neutrally (Kircher and Ahlstrom, 2009). The mean value produced a significant main effect of Interface Type [F (4,146) = 5.54, p = .000].…”

Section: Condition 1 2 3 and 5 (15 Mins Each)mentioning

confidence: 99%

See 2 more Smart Citations

Unconstrained design: improving multitasking with in-vehicle information systems through enhanced situation awareness

Skrypchuk

Langdon

Sawyer

et al. 2019

Theoretical Issues in Ergonomics Science

View full text Add to dashboard Cite

In the age of information, in-vehicle multitasking is inevitable. The popularity of the automobile in combination with the demands of everyday life presents a demand to do more than simply focus on the road. Situation Awareness (SA) is a theory that allows designers to understand how operators interact in dynamic, complex environments. Unconstrained Design is proposed as a way of enhancing multitasking performance in-vehicle. This paper presents an experimental investigation into human-machine interface concepts that aim to support drivers to multitask in-vehicle when frequent task switching is required. Two SA-based approaches were investigated, one which focussed on supporting preparation for a Non-Driving Related Activity (NDRA), and one which focussed on supporting the Driving Related Activity (DRA) when an NDRA is active. While multitasking, Contextual Cueing, using a Head-up Display, produced significant reductions in NDRA response time while an auditory lane keeping aid increased the amount of time a driver spent in the central region of a lane. This provides evidence to suggest that using SA and Unconstrained Design as a philosophy for the design of IVIS that supports drivers' ability to multitask in-vehicle, could lead to task performance improvements.

show abstract

Section: Sa During In-vehicle Multitaskingmentioning

confidence: 99%

Section: Attention Management Bothmentioning

confidence: 99%

See 1 more Smart Citation

Unconstrained design: improving multitasking with in-vehicle information systems through enhanced situation awareness

Skrypchuk

Langdon

Sawyer

et al. 2019

Theoretical Issues in Ergonomics Science

View full text Add to dashboard Cite

show abstract

“…If the drivers gaze is directed away from the field relevant for driving, their visual attention is considered to be away from the road. AttenD identifies visual distraction in real time based on single long glances as well as repetitive glances (Kircher and Ahlström, 2013). Glances can be described as gaze duration and gaze frequency on a particular area of interest.…”

Section: Driver Monitoring Systemsmentioning

confidence: 99%

“…A simple yet effective algorithm was implemented that alerted drivers based on their group condition after a number of seconds of gaze fixation off the road. An algorithm similar to the AttenD algorithm was used by adjusting the field relevant for driving and the time buffer that decrements when the driver is looking away from the field relevant for driving (Kircher and Ahlström, 2013).…”

Section: Dms and Algorithmsmentioning

confidence: 99%

Enhancing situational awareness in highly automated vehicles through driver monitoring

Kashef¹

View full text Add to dashboard Cite

With the development of level 3 AVs, drivers can now disengage from the driving task for extended periods of time. However, drivers are still responsible for the overall safety of their drive. Moreover, when drivers are not engaged in their monitoring task, they lose situational awareness. This leaves drivers vulnerable when they have to retake control from the AV. This research looks to advance the development of camera-based driver monitoring systems that measure situational awareness. In addition, this research examines the effect of adaptable warning systems on driver situational awareness and takeover performance. In this study, we use situational awareness as ground truth to compare adaptable warning systems that reengage drivers in the monitoring task. Camera-based driver monitoring systems that measure gaze behavior can be used to adapt warning systems. Twenty-four participants split into three groups were asked to drive for approximately 40 miles in a level 3 AV simulator while completing a visual-manual secondary task. During the drive, participants experienced four events in which they had to disengage from the secondary task and take back control from the AV. Two interface designs based on gaze behavior were compared to a baseline warning system. The Attentional Maintenance group was given an alert throughout the drive after a fixed amount of time in which their gaze was directed away from the road. The State-Contingent Takeover group was given an alert only before takeover events after a fixed amount of time in which their gaze was directed away from the road. Results show that attentional maintenance alerts can increase situational awareness and takeover response time during automation failure. Future research to increase situational awareness is discussed in terms of advancements in cognitive control and bilateral communication between the driver and the AV.

show abstract