Scholarlink

Driver drowsiness is a foremost reason of road accidents, and detecting it is crucial for preventing such incidents. With the rise of in-vehicle cameras and sensors, computer vision and machine learning have emerged as effective tools for this task. This paper reviews various computer vision-based methods, including feature-based and machine learning approaches, with a focus on Convolutional Neural Networks (CNNs). CNNs, capable of automatically learning features from images, are particularly suited for detecting drowsiness. The proposed CNN-based system uses a dashboard-mounted camera to analyze facial expressions, eye closure, and head pose to detect drowsiness, aiming to enhance driver safety and reduce accidents.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Automatic Driver Drowsiness Detection: A Deep Learning Solution Using Eye and Head Movement Analysis

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • M. Kalpana Chowdary,
  • Mounika Undadi,
  • Allam Balaram,
  • Ajmeera Kiran,
  • N. Shirisha,
  • K. Shekhar

摘要

Driver drowsiness is a foremost reason of road accidents, and detecting it is crucial for preventing such incidents. With the rise of in-vehicle cameras and sensors, computer vision and machine learning have emerged as effective tools for this task. This paper reviews various computer vision-based methods, including feature-based and machine learning approaches, with a focus on Convolutional Neural Networks (CNNs). CNNs, capable of automatically learning features from images, are particularly suited for detecting drowsiness. The proposed CNN-based system uses a dashboard-mounted camera to analyze facial expressions, eye closure, and head pose to detect drowsiness, aiming to enhance driver safety and reduce accidents.