Authors : Sammita Abhay; Vathsalya V.; Veena B.

Volume/Issue : Volume 10 - 2025, Issue 11 - November

---

Google Scholar : https://tinyurl.com/mu54x982

Scribd : https://tinyurl.com/3cvy6y43

DOI : https://doi.org/10.38124/ijisrt/25nov1132

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

---

Abstract : Distracted driving remains a primary contributor to many global road accidents, motivating advanced detection technologies for vehicle safety systems. This study introduces a hybrid approach using handcrafted features (HOG, Local Binary Patterns) and deep transfer learning (VGG16), combined with SVM, Random Forest, and XGBoost classifiers. Experiments with the State Farm Distracted Driver Detection dataset achieved accurate recognition of ten behaviors, such as texting and reaching behind. And our Streamlit- based application enables real-time, user-friendly prediction. The end resulting system is scalable, interpretable, and efficient, showing strong potential for AI powered better transportation solutions, making it suitable for practical safety applications.

Keywords : Distracted Driving, Deep Learning, Hybrid Architecture, Transfer Learning, VGG16, Convolutional Neural Network (CNN), Histogram Of Oriented Gradients (HOG), Local Binary Pattern (LBP), Machine Learning, Ensemble Classification, Xgboost, Random Forest, Support Vector Machine (SVM), Feature Fusion, Driver Monitoring System, Road Safety, Human–Computer Interaction, Intelligent Transportation Systems (ITS), Computer Vision, Real-Time Image Recognition, Model Deployment, Streamlit Application, Tensorflow, and Autonomous Vehicles.

References :

1. World Health Organization, Global Status Report on Road Safety, 2023.
   Available: https://www.who.int/publications
2. N. Dalal and B. Triggs, “Histograms of Oriented Gradients for Human Detection,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2005, pp. 886–893.
   doi: 10.1109/CVPR.2005.177
3. K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” arXiv preprint, 2014.
   doi: 10.48550/arXiv.1409.1556
4. R. Verma, S. Singh and P. Kumar, “Hybrid CNN–HOG Approach for Driver Distraction Detection,” IEEE Access, vol. 8, pp. 112435–112447, 2020.
   doi: 10.1109/ACCESS.2020.3002874
5. European Commission, Ethics Guidelines for Trustworthy AI, 2021.
   Available:https://digital-strategy.ec.europa.eu
6. A. Chaudhary and V. Balasubramanian, “Driver Distraction Detection Using Transfer Learning,” in Artificial Intelligence in Transportation, Springer, 2021, pp. 239–255.
   doi: 10.1007/978-3-030-64583-0_12
7. H. Zhang, Y. Wang and L. Yu, “Efficient Driver Posture Classification with CNN–HOG Fusion,” IEEE Intelligent Transportation Systems (ITS), 2022.
   doi: 10.1109/ITSC55140.2022.9922083