METHOD FOR DETECTING DROWSY DRIVERS IN REAL-TIME VIDEO SEQUENCES

Abstract

ABSTRACT A method (100) for detecting drowsy drivers in real-time video sequences. Further, the method comprising capturing video data of a driver's face using a camera. Further, the method (100) comprising the steps of extracting facial features from the captured video data using a Convolutional Neural Network (CNN). Further, the method (100) comprising the steps of analysing the extracted features over time with a Long Short-Term Memory (LSTM) network to determine the driver's drowsiness state. Further, the method (100) comprising the steps of tracking eye movements and eyelid behaviour using eye-tracking algorithms to enhance the accuracy of drowsiness detection. Further, the method (100) comprising the steps of generating an alert if the driver's drowsiness level exceeds a predetermined threshold.

Specification

Description:
FIELD OF THE DISCLOSURE
[0001] This invention generally relates to the field of driver safety and, in particular, to a method for detecting drowsy drivers through the use of machine learning algorithms that analyze video sequences of drivers to accurately assess their alertness levels and mitigate the risks associated with drowsy driving.
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] The increasing prevalence of drowsy driving has become a significant public safety concern, contributing to a substantial numb , Claims:1. A method (100) for detecting drowsy drivers in real-time video sequences, the method comprising the steps of:
capturing video data of a driver's face using a camera;
extracting facial features from the captured video data using a Convolutional Neural Network (CNN);
analysing the extracted features over time with a Long Short-Term Memory (LSTM) network to determine the driver's drowsiness state;
tracking eye movements and eyelid behaviour using eye-tracking algorithms to enhance the accuracy of drowsiness detection; and
generating an alert if the driver's drowsiness level exceeds a predetermined threshold.

2. The method (100) as claimed in claim 1, wherein the eye-tracking algorithms include Cascade Classifiers and Camshift algorithms for improved tracking of the driver's eye movements and eyelid behaviour.

Documents