Road Lane Detection and Obstacle Recognition using YOLO and OpenCV
Authors:
- 21 May 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1386-1392
Abstract
Strong Lane detection and object identification are essential for safe navigation in advanced driver assistance systems (ADAS) and autonomous driving. Using OpenCV for lane marker extraction and YOLO (You Only Look Once) for real-time object identification, this paper aims to create an effective lane detecting system. In order to precisely identify lane borders, OpenCV is used to process video frames using methods including Canny edge detection, Hough Transform, and perspective transformation. A thorough road scene analysis is ensured by YOLO, a deep learning-based object detection framework that recognizes cars, pedestrians, and other road impediments in real time. By combining these technologies, lane departure warnings and obstacle avoidance alerts are provided, improving driving safety. This system is appropriate for autonomous vehicles, driver assistance apps, and smart transportation systems since it is built for real-time performance. The suggested method advances intelligent transportation systems by achieving high accuracy and efficiency.Keywords
This publication has 16 references indexed in Scilit:
- Smart Lane Detection Using Open CV And Image Processing2022
- On-board Camera-based Lane and Traffic Sign Detection for 2 Wheeler HeadLamp2022
- Lane Departure Warning System using TDA3x_rvp Board2020
- Lane Detection and Lane Departure Warning System using Color Detection Sensor2019
- A Robust Approach for Lane Detection in Challenging Illumination Scenarios2018
- Lane Departure Warning System for Advanced Drivers Assistance2018
- Simple robust road lane detection algorithm2014
- Road Lane Detection with Improved Canny Edges Using Ant Colony Optimization2010
- Lane detection system based on software and hardware codesign2009
- New lane detection algorithm for autonomous vehicles using computer vision2008