Implementation of  Driver Fatigue Detection System For Loco Pilot, Preventing Train Accidents Using Python And ESP32 CAM

Simran Khan; Vivekanand P. Thakare; Rupali Bhalavi; Sana  Shaikh

Implementation of Driver Fatigue Detection System For Loco Pilot, Preventing Train Accidents Using Python And ESP32 CAM

Authors: Simran Khan, Vivekanand P. Thakare, Rupali Bhalavi, Sana Shaikh

Unique Paper ID: 182422
Volume: 12
Issue: 2
PageNo: 1905-1909

Keywords: Driver Fatigue Detection Loco Pilot Monitoring Train Accident Prevention ESP32-CAM Python OpenCV Real-time Image Processing Eye Blink Detection Yawning Detection Drowsiness Detection Face Monitoring System Internet of Things (IoT) Machine Learning Computer Vision Railway Safety System.

Abstract:
Fatigue among train drivers, especially loco pilots, has been identified as a critical factor contributing to train accidents worldwide. Prolonged working hours, monotonous routes, and high stress can lead to drowsiness and reduced alertness, severely impairing a driver’s ability to respond promptly to signals and track conditions. In response to this safety challenge, the proposed system leverages the capabilities of embedded systems and artificial intelligence to develop a real-time Driver Fatigue Detection System using the ESP32-CAM module and Python-based image processing techniques. The primary aim of this project is to proactively detect signs of drowsiness or inattention in the loco pilot and initiate preventive measures to avoid accidents. This system uses an ESP32-CAM, a compact microcontroller with an onboard camera and Wi-Fi capability, to continuously monitor the facial features of the loco pilot. The camera captures real-time video frames of the driver’s face, which are processed using machine learning algorithms either on-device or remotely using a server running Python. The Python-based backend employs computer vision techniques, particularly OpenCV and pre-trained models such as Haar cascades or Dlib’s facial landmark detectors, to detect key indicators of fatigue such as eye closure duration (PERCLOS), blink rate, yawning frequency, and head tilt. These features are essential in estimating the alertness level of the driver.

Download article

email to a friend

Cite This Article

ISSN: 2349-6002
Volume: 12
Issue: 2
PageNo: 1905-1909

Implementation of Driver Fatigue Detection System For Loco Pilot, Preventing Train Accidents Using Python And ESP32 CAM

Available:https://ijirt.org/Article?manuscript=182422

Impact Factor
8.01 (Year 2024)

UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now