Scholarlink

<p>The primary aim of this research is to identify driver drowsiness to prevent car accidents and improve road safety. This study explores and proposes potential solutions to mitigate drowsiness-related accidents and enhance overall road security by monitoring the indicators such as driver’s eye, mouth, and head movements. An algorithm has been developed to track these movements. This work includes analyzing CNN and computer vision models for eye detection, yawn detection, and head movement. The CNN models are trained by using MRL and YawDD datasets for eye and mouth tracking. In the computer vision approach, Dlib and MediaPipe library functions are used for tracking facial landmarks. In this approach also, three features namely, head &amp; eye movements, and yawns are considered for drowsiness detection. Highest accuracy of 84.53% and 96.42% is obtained using CNN approach for MRL Eye and YawDD Dataset, respectively. Performance of the computer vision-based approach is better as compared to CNN method.</p>

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

Smart Driver Assistance: Real-Time Drowsiness Detection Leveraging Facial Cues with MediaPipe and OpenCV

  • 期刊论文

  • 发表日期：

    2026年2月2日

查看全文
  • Lidiya Lilly Thampi,
  • Neethu C T,
  • Ariveeti Karthikeya Reddy,
  • Ibrahim Ahmed Khan,
  • M. A. Aswathy,
  • Abhishek Kumar,
  • Sunny Kumar

摘要

The primary aim of this research is to identify driver drowsiness to prevent car accidents and improve road safety. This study explores and proposes potential solutions to mitigate drowsiness-related accidents and enhance overall road security by monitoring the indicators such as driver’s eye, mouth, and head movements. An algorithm has been developed to track these movements. This work includes analyzing CNN and computer vision models for eye detection, yawn detection, and head movement. The CNN models are trained by using MRL and YawDD datasets for eye and mouth tracking. In the computer vision approach, Dlib and MediaPipe library functions are used for tracking facial landmarks. In this approach also, three features namely, head & eye movements, and yawns are considered for drowsiness detection. Highest accuracy of 84.53% and 96.42% is obtained using CNN approach for MRL Eye and YawDD Dataset, respectively. Performance of the computer vision-based approach is better as compared to CNN method.