A Computer Vision-Based Approach for Driver Distraction Recognition using Deep Learning and Genetic Algorithm Based Ensemble

@inproceedings{Kumar2021ACV,
  title={A Computer Vision-Based Approach for Driver Distraction Recognition using Deep Learning and Genetic Algorithm Based Ensemble},
  author={Ashlesha Kumar and Kuldip Singh Sangwan and Dhiraj},
  booktitle={ICAISC},
  year={2021}
}
As the proportion of road accidents increases each year, driver distraction continues to be an important risk component in road traffic injuries and deaths. The distractions caused by increasing use of mobile phones and other wireless devices pose a potential risk to road safety. Our current study aims to aid the already existing techniques in driver posture recognition by improving the performance in the driver distraction classification problem. We present an approach using a genetic… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 26 REFERENCES
Driver Distraction Identification with an Ensemble of Convolutional Neural Networks
TLDR
This paper presents the first publicly available dataset for driver distraction identification with more distraction postures than existing alternatives, and proposes a reliable deep learning-based solution that achieves a 90% accuracy. Expand
Driving posture recognition by convolutional neural networks
TLDR
A novel system which applies convolutional neural network to automatically learn and predict four driving postures to monitor driver hand position with discriminative information extracted to predict safe/unsafe driving posture is presented. Expand
Driving posture recognition by convolutional neural networks
TLDR
This study presents a novel system which applies convolutional neural network (CNN) to automatically learn and predict pre-defined driving postures to monitor driver hand position with discriminative information extracted to predict safe/unsafe driving posture. Expand
Real Time Detection of driver distraction using CNN
TLDR
This paper focuses on a methodology to reduce the accidents caused by distracted driver with deep neural networks, which consists of three models namely, vanilla CNN, Vanilla CNN with data augmentation, and CNN with transfer learning. Expand
Distracted driver classification using deep learning
TLDR
This research investigates distracted driver posture recognition as a part of the human action recognition framework through a combination of three of the most advanced techniques in deep learning, namely the inception module with a residual block and a hierarchical recurrent neural network. Expand
Distracted Driver Detection using Stacking Ensemble
TLDR
The model proposed in this paper can be used in a real- time environment to detect activities done by the driver and shows how models predict the desired classes. Expand
Real-time Distracted Driver Posture Classification
TLDR
A genetically-weighted ensemble of Convolutional Neural Networks using a genetic algorithm yields in better classification confidence and is presented as a thinned version of the ensemble that could achieve a 94.29% classification accuracy and operate in a realtime environment. Expand
Recognition of driving postures by contourlet transform and random forests
TLDR
With RF classifiers, the classification accuracies of eating are over 88% in holdout and cross-validation experiments, thus demonstrating the effectiveness of the proposed feature extraction method and the importance of RF classifier in automatically understanding and characterising driver behaviours towards human-centric driver assistance systems. Expand
Rethinking the Inception Architecture for Computer Vision
TLDR
This work is exploring ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization. Expand
ImageNet classification with deep convolutional neural networks
TLDR
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
...
1
2
3
...