Analysis of driver behaviors during common tasks using frontal video camera and CAN-Bus information

Jain, Jinesh; Busso, Carlos

doi:10.1109/icme.2011.6011950

Cited by 23 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Statistic analysis techniques such as ANOVA, correlation analysis, and hypothesis test are usually performed to determine whether the measurements are useful for inferring the distraction level of drivers [6], [23]- [26]. Other studies explore machine learning techniques to predict distractive driving behaviors.…”

Section: Detecting Driver Distractionsmentioning

confidence: 99%

“…In our previous studies, we have shown that valuable information signaling drivers' distraction can be extracted from nonintrusive sensors [6], [31], [32]. In particular, we considered features extracted from the CAN-bus, a camera facing the drivers, and a microphone array.…”

Section: A Multimodal Featuresmentioning

confidence: 99%

“…Then, the output of the classifiers is used to build a standard linear regression model that gives the precise head orientation (yaw, pitch, and roll movements) [41]. In our previous work, features extracted from the drivers' head pose were useful in binary classifiers, aiming to recognize drivers engaged in secondary tasks [6], [31] (i.e., task versus normal conditions). Therefore, we expect that they will be also useful for detecting visual and cognitive distractions.…”

Section: Can-bus Signal (Can)mentioning

confidence: 99%

“…These facts have motivated the research community to study cues that can signal driver distractions. Most of the relevant studies have focused on finding differences between normal and distracted driving behaviors [2]- [6]. In other studies, the drivers are considered to be distracted when they are performing secondary tasks [3], [7], [8].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Predicting Perceived Visual and Cognitive Distractions of Drivers With Multimodal Features

Busso

2015

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

A driver's behaviors can be affected by visual, cognitive, auditory, and manual distractions. While it is important to identify the patterns associated with particular secondary tasks, it is more general and useful to define distraction modes that capture the general behaviors induced by various sources of distractions. By explicitly modeling the distinction between types of distractions, we can assess the detrimental effects induced by new in-vehicle technology. This study investigates drivers' behaviors associated with visual and cognitive distractions, both separately and jointly. External observers assessed the perceived cognitive and visual distractions from real-world driving recordings, showing high interevaluator agreement in both dimensions. The scores from the perceptual evaluation are used to define regression models with elastic net regularization and binary classifiers to separately estimate the cognitive and visual distraction levels. The analysis reveals multimodal features that are discriminative of cognitive and visual distractions. Furthermore, the study proposes a novel joint visual-cognitive distraction space to characterize driver behaviors. A data-driven clustering approach identifies four distraction modes that provide insights to better understand the deviation in driving behaviors induced by secondary tasks. Binary and multiclass recognition problems demonstrate the effectiveness of the proposed multimodal features to infer these distraction modes defined in the visual-cognitive space.

show abstract

Section: Detecting Driver Distractionsmentioning

confidence: 99%

Section: A Multimodal Featuresmentioning

confidence: 99%

Section: Can-bus Signal (Can)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predicting Perceived Visual and Cognitive Distractions of Drivers With Multimodal Features

Busso

2015

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Motivated by previous successful work in [16], [17], an exhaustive list of statistical features is extracted from these 28 signals. Mostly extracted from the temporal signal, statistical features are straight forward to understand and extract in real-time processing.…”

Section: E Features Usedmentioning

confidence: 99%

Leveraging sensor information from portable devices towards automatic driving maneuver recognition

Sathyanarayana

Sadjadi

Hansen

2012

2012 15th International IEEE Conference on Intelligent Transportation Systems

View full text Add to dashboard Cite

With the proliferation of smart portable devices, more people have started using them within the vehicular environment while driving. Although these smart devices provide a variety of useful information, using them while driving significantly affects the driver's attention towards the road. This can in turn cause driver distraction and lead to increased risk of crashes. On the positive side, these devices are equipped with powerful sensors which can be effectively utilized towards driver behavior analysis and safety. This study evaluates the effectiveness of portable sensor information in driver assistance systems. Available signals from the CAN-bus are compared with those extracted from an off-the-shelf portable device for recognizing patterns in driving sub-tasks and maneuvers. Through our analysis, a qualitative feature set is identified with which portable devices could be employed to prune the search space in recognizing driving maneuvers and possible instances of driver distraction. An absolute improvement of 15% is achieved with portable sensor information compared to CAN-bus signals, which motivates further study of portable devices to build driver behavior models for driver assistance systems.

show abstract

Advances in Multimodal Tracking of Driver Distraction

Busso

Jain

2011

Digital Signal Processing for in-Vehicle Systems and Safety

View full text Add to dashboard Cite

Analysis of driver behaviors during common tasks using frontal video camera and CAN-Bus information

Cited by 23 publications

References 9 publications

Predicting Perceived Visual and Cognitive Distractions of Drivers With Multimodal Features

Predicting Perceived Visual and Cognitive Distractions of Drivers With Multimodal Features

Leveraging sensor information from portable devices towards automatic driving maneuver recognition

Advances in Multimodal Tracking of Driver Distraction

Contact Info

Product

Resources

About