Driver Drowsiness Detection Using CNN and HAAR
Year: 2025
Type: article
Abstract: A major risk factor for traffic accidents is tiredness among drivers . It is a serious issue that emphasizes the necessity of real- time, efficient detection and preventive techniques. In order to effectively identify driver drowsiness, this research presents a hybrid technique that combines Convolunal Neural Network(CNN) and Haar Cascade. Because of its effectiveness in real-time application, the Haar Cascade method is employed for the detection of facial and eye regions. A CNN is then used to examine the identified eye regions and determine if the driver is awake orsleepy. High accuracy in identifying patterns of drowsiness is ensured by training the machine on annotated datasets of eye pictures.The suggested method strikes a balance between accuracy and speed, which qualifies it for real-time vehicle time vehicle deployment. The durability and dependability of this approach are demonstrated by experimental fundings, offering a workable way to improve road safety.
Authors: Gaurav Singh, Vikas Yadav, Durgesh Gaur, Nancy Agrawal
Language: English
Subfield: Experimental and Cognitive Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W4408844649