Home / Current Issue / Paper 1711980
AI-Based Driving Assist System Using Machine Learning and Computer Vision
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence and Machine Learning
DOI: https://doi.org/10.64388/IREV9I5-1711980
Abstract
Driving safety remains one of the most critical challenges due to human errors, distractions, and environmental conditions. This research presents an AI-based Driving Assist System that leverages computer vision and deep learning to detect lanes, traffic signs, pedestrians, and driver drowsiness in real time. Using convolutional neural networks (CNN), OpenCV, and machine learning algorithms, the system enhances situational awareness and provides real-time alerts to prevent accidents. The proposed system integrates multiple modules?lane detection, driver monitoring, and object detection?into a unified framework designed for affordability and adaptability. Experimental results demonstrate that the hybrid vision-based approach achieves high detection accuracy under varying conditions, contributing to safer and smarter driving.
Keywords
Driving Assist, Computer Vision, CNN, Lane Detection, Drowsiness Detection, AI, Deep Learning, Real-time Alerts.
How to cite this paper
@article{1711980,
author = {Atharva Dhumal, Om Ghorpade, Nishad Gurav, Sahil Choudhari, Prof. R. R. Bhuvad},
title = {AI-Based Driving Assist System Using Machine Learning and Computer Vision},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {9},
number = {5},
pages = {938-944},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1711980.pdf},
abstract = {Driving safety remains one of the most critical challenges due to human errors, distractions, and environmental conditions. This research presents an AI-based Driving Assist System that leverages computer vision and deep learning to detect lanes, traffic signs, pedestrians, and driver drowsiness in real time. Using convolutional neural networks (CNN), OpenCV, and machine learning algorithms, the system enhances situational awareness and provides real-time alerts to prevent accidents. The proposed system integrates multiple modules?lane detection, driver monitoring, and object detection?into a unified framework designed for affordability and adaptability. Experimental results demonstrate that the hybrid vision-based approach achieves high detection accuracy under varying conditions, contributing to safer and smarter driving.},
keywords = {Driving Assist, Computer Vision, CNN, Lane Detection, Drowsiness Detection, AI, Deep Learning, Real-time Alerts.},
month = {November},
doi = {https://doi.org/10.64388/IREV9I5-1711980}
}