Computer vision‐based recognition of driver distraction: A review

Moslemi, Negar; Soryani, Mohsen; Azmi, Reza

doi:10.1002/cpe.6475

Cited by 25 publications

(18 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reason is that visible spectrum cameras are affordable and their integration in modern systems is easy to implement. However, due to illumination limitations in real driving conditions, NIR external illumination and IR camera sensors are preferred since the use of DMS can be extended to low-light conditions [ 34 , 35 ]. Other works have integrated depth sensors to provide additional data to the DMS algorithms and better predict driver state [ 36 ].…”

Section: Driver Monitoring Methods and Datasetsmentioning

confidence: 99%

Challenges of Large-Scale Multi-Camera Datasets for Driver Monitoring Systems

Ortega

Cañas

Nieto

et al. 2022

Sensors

View full text Add to dashboard Cite

Tremendous advances in advanced driver assistance systems (ADAS) have been possible thanks to the emergence of deep neural networks (DNN) and Big Data (BD) technologies. Huge volumes of data can be managed and consumed as training material to create DNN models which feed functions such as lane keeping systems (LKS), automated emergency braking (AEB), lane change assistance (LCA), etc. In the ADAS/AD domain, these advances are only possible thanks to the creation and publication of large and complex datasets, which can be used by the scientific community to benchmark and leverage research and development activities. In particular, multi-modal datasets have the potential to feed DNN that fuse information from different sensors or input modalities, producing optimised models that exploit modality redundancy, correlation, complementariness and association. Creating such datasets pose a scientific and engineering challenge. The BD dimensions to cover are volume (large datasets), variety (wide range of scenarios and context), veracity (data labels are verified), visualization (data can be interpreted) and value (data is useful). In this paper, we explore the requirements and technical approach to build a multi-sensor, multi-modal dataset for video-based applications in the ADAS/AD domain. The Driver Monitoring Dataset (DMD) was created and partially released to foster research and development on driver monitoring systems (DMS), as it is a particular sub-case which receives less attention than exterior perception. Details on the preparation, construction, post-processing, labelling and publication of the dataset are presented in this paper, along with the announcement of a subsequent release of DMD material publicly available for the community.

show abstract

Section: Driver Monitoring Methods and Datasetsmentioning

confidence: 99%

Challenges of Large-Scale Multi-Camera Datasets for Driver Monitoring Systems

Ortega

Cañas

Nieto

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…"Deep learning", the promising direction of artificial intelligence, accounts for a large proportion of work in this field currently [80]. Meanwhile, the rise of "computer vision" has empowered distraction detection [10] and new human-machine interaction modes to reduce distraction like gesture interaction [92].…”

Section: Plos Onementioning

confidence: 99%

“…For example, the distracting effect of telephones [5], the impact of roadside billboards [6] and young drivers' distraction problems [7] have been discussed thoroughly. And there have also been reviews concentrating on certain research methods like naturalistic driving study [8], on certain distraction measurements like eye movement [9] and on certain data processing ways like the application of computer vision in distraction recognition [10]. Meanwhile, more general themes that contain driving distraction have been systematically addressed, such as driver understanding and modeling [11], contributors of road accidents [12], as well as road safety [13,14].…”

Section: Introductionmentioning

confidence: 99%

Understanding the domain of driving distraction with knowledge graphs

Feng

2022

PLoS ONE

View full text Add to dashboard Cite

This paper aims to provide insight into the driving distraction domain systematically on the basis of scientific knowledge graphs. For this purpose, 3,790 documents were taken into consideration after retrieving from Web of Science Core Collection and screening, and two types of knowledge graphs were constructed to demonstrate bibliometric information and domain-specific research content respectively. In terms of bibliometric analysis, the evolution of publication and citation numbers reveals the accelerated development of this domain, and trends of multidisciplinary and global participation could be identified according to knowledge graphs from Vosviewer. In terms of research content analysis, a new framework consisting of five dimensions was clarified, including “objective factors”, “human factors”, “research methods”, “data” and “data science”. The main entities of this domain were identified and relations between entities were extracted using Natural Language Processing methods with Python 3.9. In addition to the knowledge graph composed of all the keywords and relationships, entities and relations under each dimension were visualized, and relations between relevant dimensions were demonstrated in the form of heat maps. Furthermore, the trend and significance of driving distraction research were discussed, and special attention was given to future directions of this domain.

show abstract

“…3) The architecture is divided into three branches every branch is responsible for one of the three intrinsic Euler angles. The feature extraction is based on mobile net [34] and inception network [35]. The model has three branches for Euler angles prediction.…”

Section: ) Head Position Estimationmentioning

confidence: 99%

Multimodel System for Driver Distraction Detection and Elimination

et al. 2022

View full text Add to dashboard Cite

On average 3,700 people lose their lives on roads every day due to car accidents as a result of drivers' distraction. In this research, a proposed hybrid approach is presented. The approach is based on deep learning to detect the driver's actions and eliminate the driver's distraction as a packed solution. The detection is performed by analyzing the driver's actions and his head pose. The elimination is made by using voice commands that are based on trigger words, speech to text, and text classification models to access the car's functions such as the air-condition, radio, etc. The results of the driver's actions classification showed 94.1% accuracy on the AUC benchmark database for driver distraction achieving the state-of-the-art accuracy on this benchmark. The results of the command to text classification is 95.19% while the results of the head pose estimation show a 6.21-degree MAE in face angles detection. With using our car commands dataset, the domain of the speech recognition output is more focused on car commands. The previously mentioned algorithms are beneficial to the safety of the driver. He can use his voice to operate the car accessories. His alert state is monitored and he is warned through an alarm if a distraction is detected. However, this research is not concerned with the detection of retinal abnormalities such as sleeping with eyes open. The results of real-time testing show 0.080 second response time for the driver's behavior classification and command following with the use of graphical processing units.

show abstract

Computer vision‐based recognition of driver distraction: A review

Cited by 25 publications

References 62 publications

Challenges of Large-Scale Multi-Camera Datasets for Driver Monitoring Systems

Challenges of Large-Scale Multi-Camera Datasets for Driver Monitoring Systems

Understanding the domain of driving distraction with knowledge graphs

Multimodel System for Driver Distraction Detection and Elimination

Contact Info

Product

Resources

About