Abstract:
Distracted driving deaths have skyrocketed in recent years. Deep learning can detect distracted driving. Real-time detection requires an optimized network with a small number of parameters, high accuracy, and high speed. A decreasing filter size D-HCNN model with 0.76M parameters is proposed. HOG feature images, L2 weight regularization, dropout, and batch normalization improve D-HCNN. We evaluate D-HCNN on two public datasets, AUC Distracted Driver (AUCD2) and State Farm Distracted Driver Detection (SFD3), and discuss its benefits and principles. AUCD2 and SFD3 have 95.59% and 99.87% accuracy, respectively, higher than many other state-of-the-art methods.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
