Driver drowsiness detection in video sequences using hybrid selection of deep features

Article Computer Science, Artificial Intelligence

Deep CNN models-based ensemble approach to driver drowsiness detection

Mohit Dua et al.

Summary: Accidents are often caused by drowsy drivers, and a study has proposed a system using deep learning models to detect driver drowsiness with 85% accuracy. The system classifies features such as hand gestures, facial expressions, and head movements to distinguish between non-drowsiness and drowsiness.

NEURAL COMPUTING & APPLICATIONS (2021)

添加到收藏夹

Article Engineering, Civil

EEG-Based Driver Drowsiness Estimation Using an Online Multi-View and Transfer TSK Fuzzy System

Yizhang Jiang et al.

Summary: This paper proposes an online multi-view and transfer TSK fuzzy system for driver drowsiness estimation, which has higher interpretability and can better utilize pattern information from different views.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2021)

添加到收藏夹

Article Neurosciences

A Framework for Instantaneous Driver Drowsiness Detection Based on Improved HOG Features and Naive Bayesian Classification

Samy Bakheet et al.

Summary: An innovative framework for driver drowsiness detection is proposed in this paper, incorporating an adaptive descriptor formed from improved HOG features and a Naive Bayes classifier. Experimental results show a competitive detection accuracy of 85.62% on the NTHU-DDD dataset, demonstrating the potential of the framework to be a strong contender for state-of-the-art baselines.

BRAIN SCIENCES (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Efficient and compact face descriptor for driver drowsiness detection

Abdelmalik Moujahid et al.

Summary: The study introduces a compact face monitoring system based on a compact face texture descriptor to effectively capture drowsy features. By utilizing a multi-scale pyramidal face representation and feature selection process, it shows promising results in drowsiness detection when compared to other methods.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

添加到收藏夹

Review Engineering, Civil