Scribd
Upload
6 views8 pages

Description To Wakewave

The document outlines the development of a machine learning-based driver drowsiness detection system utilizing facial landmark analysis to enhance road safety. By monitoring eye closure and employing a convolutional neural network, the system alerts drivers when drowsiness is detected. Future research aims to improve detection accuracy and integrate this technology into automotive safety systems.

Uploaded by

sosix83887
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
6 views8 pages

Description To Wakewave

The document outlines the development of a machine learning-based driver drowsiness detection system utilizing facial landmark analysis to enhance road safety. By monitoring eye closure and employing a convolutional neural network, the system alerts drivers when drowsiness is detected. Future research aims to improve detection accuracy and integrate this technology into automotive safety systems.

Uploaded by

sosix83887
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 8

Enhancing Road Safety: Implementing a

Machine Learning-Based Driver Drowsiness


Detection System Using Facial Landmark
Analysis
Introduction to Drowsiness Detection

A countless number of people drive on the highway day and


night. Taxi drivers, bus drivers, truck drivers and people traveling
long-distance suffer from lack of sleep. Due to which it becomes
very dangerous to drive when feeling sleepy.

Drowsiness detection is a safety technology that can prevent


accidents that are caused by drivers who fell asleep while
driving.
The objective of this intermediate Python project is to build a
drowsiness detection system that will detect that a person’s
eyes are closed for a few seconds. This system will alert the
driver when drowsiness is detected.
Understanding Drowsiness in Drivers

Driver drowsiness can lead to severe accidents and fatalities.


Recognizing the signs of drowsiness through facial
expressions is crucial. This slide discusses common indicators
such as eye closure, yawning, and head nodding that can
signal a driver's fatigue.

Drowsiness in drivers can be detected by monitoring eye


closure and facial landmarks using a camera. By analyzing the
Eye Aspect Ratio (EAR) through Mediapipe’s Face Mesh, the
system predicts drowsiness and alerts the driver if their eyes
remain closed for too long.
Machine Learning Techniques

Image Capture: Images will be gathered from the


webcam using OpenCV.

Face Detection: The face in the image will be detected,


and a Region of Interest (ROI) will be created.

Eye Detection: Eyes within the ROI will be detected and


fed to the classifier.

Classification: The classifier will categorize whether the


eyes are open or closed.

Drowsiness Detection: A score will be calculated to


determine if the person is drowsy.
The 68-point face detection method uses Dlib’s pre-trained shape predictor model to identify and monitor 68
facial landmarks, including the eyes, eyebrows, nose, mouth, and jawline. In a drowsiness detection system,
these landmarks are crucial for calculating the Eye Aspect Ratio (EAR). By analyzing the EAR, the system can
determine if the driver’s eyes are closed for an extended period, indicating drowsiness. This real-time analysis
enhances driver safety by providing timely alerts.
The model we used is built with Keras using Convolutional Neural Networks (CNN). A convolutional neural network
is a special type of deep neural network which performs extremely well for image classification purposes. A CNN basically
consists of an input layer, an output layer and a hidden layer which can have multiple layers. A convolution operation is
performed on these layers using a filter that performs 2D matrix multiplication on the layer and filter. The final layer is
also a fully connected layer with 2 nodes. A Relu activation function is used in all the layers except the output layer in
which we used Softmax.
Conclusion

In conclusion, a machine learning-based drowsiness detection system


using facial landmark analysis can significantly improve road safety.
Future research should focus on enhancing detection accuracy and
integrating this technology into automotive safety systems for
broader implementation. In this Python project, a drowsy driver alert
system was built using OpenCV to detect faces and eyes with a Haar
cascade classifier, and a CNN model was used to predict the status.
This system can be implemented in various ways to enhance driver
safety.
Thanks
!

You might also like