Driver Distraction Detection Based on the True Driver’s Focus of Attention

Huang, Tao; Fu, Rui

doi:10.1109/tits.2022.3166208

Cited by 21 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Iraqi et al [17] used a genetic algorithm to assign weights to an ensemble of CNNs and reached 94.29% with 62.00M parameters on the American University in Cairo dataset (AUC). Huang et al [18] introduced a deep 3D residual network with an attention mechanism and encoder-decoder for predicting the true driver's focus of attention. Recently, Wang et al [19] improved the generalization of DDD using multi-scale feature learning and domain adaptation.…”

Section: A Driver Distraction Detection: Handcrafted Architecturesmentioning

confidence: 99%

Resource-Conscious Architecture Search for Driver Distraction Detection: A Pareto Optimised Multi-Objective Approach

Bouali,

Ahmed,

Bradai

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Section: A Driver Distraction Detection: Handcrafted Architecturesmentioning

confidence: 99%

Resource-Conscious Architecture Search for Driver Distraction Detection: A Pareto Optimised Multi-Objective Approach

Bouali,

Ahmed,

Bradai

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Martin et al (2018) introduced a three stream RNN networks, where each stream focus attention on specific information: spatial, temporal and context. In Huang & Fu (2022), the authors recognize driver distraction based on two stages framework: the first stage aims to predict the true driver's focus of attention using a deep 3D residual network with an attention mechanism and encoder-decoder, and the second stage focuses on driver distraction detection based on the driver's focus of attention and the true driver's focus of attention. All those mentioned works are based on soft attention.…”

Section: Related Workmentioning

confidence: 99%

Deep learning-based hard spatial attention for driver in-vehicle action monitoring

Jegham

Alouani

Khalifa

et al. 2023

Expert Systems with Applications

View full text Add to dashboard Cite

“…The attention mechanism module was used to optimize feature weight, which significantly improved fatigue detection performance. Huang et al [17] designed a deep 3D residual network with an attention mechanism and introduced an encoder-decoder module to extract multiscale features. This method effectively detects driver distraction.…”

Section: Introductionmentioning

confidence: 99%

Driver Attention Detection Based on Improved YOLOv5

2023

View full text Add to dashboard Cite

In response to negative impacts such as personal and property safety hazards caused by drivers being distracted while driving on the road, this article proposes a driver’s attention state-detection method based on the improved You Only Look Once version five (YOLOv5). Both fatigue and distracted behavior can cause a driver’s attention to be diverted during the driving process. Firstly, key facial points of the driver are located, and the aspect ratio of the eyes and mouth is calculated. Through the examination of relevant information and repeated experimental verification, threshold values for the aspect ratio of the eyes and mouth under fatigue conditions, corresponding to closed eyes and yawning, are established. By calculating the aspect ratio of the driver’s eyes and mouth, it is possible to accurately detect whether the driver is in a state of fatigue. Secondly, distracted abnormal behavior is detected using an improved YOLOv5 model. The backbone network feature extraction element is modified by adding specific modules to obtain different receptive fields through multiple convolution operations on the input feature map, thereby enhancing the feature extraction ability of the network. The introduction of Swin Transformer modules in the feature fusion network replaces the Bottleneck modules in the C3 module, reducing the computational complexity of the model while increasing its receptive field. Additionally, the network connection in the feature fusion element has been modified to enhance its ability to fuse information from feature maps of different sizes. Three datasets were created of distracting behaviors commonly observed during driving: smoking, drinking water, and using a mobile phone. These datasets were used to train and test the model. After testing, the mAP (mean average precision) has improved by 2.4% compared to the model before improvement. Finally, through comparison and ablation experiments, the feasibility of this method has been verified, which can effectively detect fatigue and distracted abnormal behavior.

show abstract

Driver Distraction Detection Based on the True Driver’s Focus of Attention

Cited by 21 publications

References 34 publications

Resource-Conscious Architecture Search for Driver Distraction Detection: A Pareto Optimised Multi-Objective Approach

Resource-Conscious Architecture Search for Driver Distraction Detection: A Pareto Optimised Multi-Objective Approach

Deep learning-based hard spatial attention for driver in-vehicle action monitoring

Driver Attention Detection Based on Improved YOLOv5

Contact Info

Product

Resources

About