DRIVER DROWSINESS DETECTION SYSTEM

Abstract

ABSTRACT A driver drowsiness detection system 100, comprising a camera 102 configured to capture real-time images of a driver's face, a convolutional neural network (CNN)-based deep learning model 104 trained to analyse said real-time images for identifying facial features indicative of driver drowsiness, an image processing module 106 to detect and monitor eye status based on eye aspect ratio (EAR), and a warning module 108 configured to emit an audible alarm if the deep learning model determines that the driver's eyes remain closed beyond a predetermined threshold duration, wherein the system operates in real-time to monitor driver alertness and issue warnings.

Specification

Description:FIELD OF THE DISCLOSURE
[0001] This invention generally relates to a field of field of driver safety systems, and in particular, to a driver drowsiness detection and alarm system using computer vision and deep learning techniques to enhance on-road safety by monitoring driver alertness in real-time and issuing timely alerts in cases of drowsiness.
BACKGROUND

[0002] The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology.
[0003] Driver fatigue is a significant cause of road accidents worldwide, often resulting in serious injuries or fatalities. , Claims:1. A driver drowsiness detection system 100, comprising:
a camera 102 configured to capture real-time images of a driver's face,
a convolutional neural network (CNN)-based deep learning model 104 trained to analyse said real-time images for identifying facial features indicative of driver drowsiness,
an image processing module 106 to detect and monitor eye status based on eye aspect ratio (EAR), and
a warning module 108 configured to emit an audible alarm if the deep learning model determines that the driver's eyes remain closed beyond a predetermined threshold duration, wherein the system operates in real-time to monitor driver alertness and issue warnings.

2. The driver drowsiness detection system 100 as claimed in claim 1, further comprising a feature adjustment module that adapts the deep learning model based on variable lighting conditions and individual driver characteristics, thereby improving detection accuracy under diverse driving environments.

Documents