Driver Drowsiness Behavior Detection and Analysis Using Vision-Based Multimodal Features for Driving Safety

Keyphrases

• Behavior Analysis 100%
• Multimodal Features 100%
• Monitoring System 100%
• Driving Safety 100%
• Driver Drowsiness 100%
• Driver Drowsiness Detection 100%
• Misbehavior Detection 100%
• Drowsy Driving 100%
• Vision-based 100%
• Drowsiness 66%
• Recognition Model 66%
• Extreme Learning Machine Model 66%
• Behavior Recognition 33%
• Detection Accuracy 33%
• Minimal Intervention 33%
• In-vehicle 33%
• Neural Network Learning 33%
• Convolutional Neural Network 33%
• Extreme Learning Machine 33%
• Detection Model 33%
• Driving Scenarios 33%
• Infrared Camera 33%
• Facial Landmark Detection 33%
• Facial Landmarks 33%
• End-to-end Convolutional Neural Network 33%
• Vehicle Crash 33%
• Driving Dataset 33%
• Naturalistic Driving 33%
• Multi-modal Feature Representation 33%
• Neural Network Classifier 33%
• Multimodal Fusion 33%
• Drowsiness Detection 33%
• Head Pose 33%
• Sunglasses 33%
• Convolutional Neural Network Regression 33%
• Neural Network Regression Model 33%
• Public Dataset 33%

Engineering

• Monitoring System 100%
• Extreme Learning Machine 100%
• Convolutional Neural Network 100%
• Recognition Model 66%
• Experimental Result 33%
• Field Test 33%
• Multi-Modal Fusion 33%
• Light Condition 33%
• Infrared Camera 33%

Computer Science

• Monitoring System 100%
• Extreme Learning Machine 100%
• Convolutional Neural Network 100%
• Experimental Result 33%
• Drowsiness Detection 33%
• Head Information 33%