Modeling of Driver Behavior in Real World Scenarios Using Multiple Noninvasive Sensors

Li, Nanxiang; Jain, Jinesh; Busso, Carlos

doi:10.1109/tmm.2013.2241416

Cited by 77 publications

(46 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Li et al [31] used multimodal features to train binary and multiclass classification to identify drivers engaged in secondary tasks (i.e., is the driver using a cellphone?). The classifiers predicted with high accuracy the seven secondary tasks listed in Table I.…”

Section: Relation To Our Prior Workmentioning

confidence: 99%

“…In our previous work, we evaluated the distraction level of drivers using perceptual evaluation without making any distinction between the types of distractions [18], [31]. We realized that when the evaluators were asked to assess just "distraction", they mainly focused on visual distractions.…”

Section: Relation To Our Prior Workmentioning

confidence: 99%

“…Therefore, the observed differences can be mainly associated with the behaviors induced by secondary tasks. A detailed description of the protocol and recording settings can be found in the work of Li et al [31].…”

Section: Data Collectionmentioning

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%

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: Relation To Our Prior Workmentioning

confidence: 99%

Section: Relation To Our Prior Workmentioning

confidence: 99%

Section: Data Collectionmentioning

confidence: 99%

Section: A Multimodal Featuresmentioning

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

“…Research was carried out using an equipped car on a controlled track (Li et al, 2012). The vehicle used for the test was a Jaguar X-Type with automatic transmission and standard equipment, belonging to the Centro Studi e Ricerche (CSR) -Muralto, CH.…”

Section: Equipped Car In Real-life Drivingmentioning

confidence: 99%

How does a collision warning system shape driver's brake response time? The influence of expectancy and automation complacency on real-life emergency braking

Ruscio

Ciceri

Biassoni

2015

Accident Analysis & Prevention

View full text Add to dashboard Cite

Performance evaluation on the node mobility with respect to human driver behavior prediction in vehicular ad hoc network using adaptive deer hunting Optimized Link State Routing Protocol

Swamynathan¹,

Palanichamy²,

Jerald³

2021

Int J Communication

View full text Add to dashboard Cite

Summary In vehicular ad hoc network (VANET) broadcasting is considered as the critical area of research. The vehicles are connecting in an ad hoc manner to create a network of a wider range. In an intelligent transport system (ITS), with vehicle to vehicle (V2V) communication in the VANET is used to support the network backbone and which the accident prevention technique has been deployed for ensuring the road safety. The major reason for the road accident is the abnormal driving behavior of human drivers. The movement pattern of the vehicle is the main factor of the network topology so that the impact of human driving pattern influences the performance and behavior of the network. Driving behavior can be classified as reckless, normal, drunken, and fatigue driving. During driving, the behavior of human drivers was predicted in this paper, thereby providing the performance analysis on the mobility of the network. For the improvement of a driver behavior, the hybridized mega‐trend diffusion (MTD) with optimized deep belief network–sunflower optimization (DBN‐SFO) is used. Here, the network performance of the adaptive deer hunting Optimized Link State Routing Protocol (ADHOLSR) is analyzed in NS2 simulation platform.

show abstract

Modeling of Driver Behavior in Real World Scenarios Using Multiple Noninvasive Sensors

Cited by 77 publications

References 38 publications

Predicting Perceived Visual and Cognitive Distractions of Drivers With Multimodal Features

Predicting Perceived Visual and Cognitive Distractions of Drivers With Multimodal Features

How does a collision warning system shape driver's brake response time? The influence of expectancy and automation complacency on real-life emergency braking

Performance evaluation on the node mobility with respect to human driver behavior prediction in vehicular ad hoc network using adaptive deer hunting Optimized Link State Routing Protocol

Contact Info

Product

Resources

About