International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 08 | Aug 2023
p-ISSN: 2395-0072
www.irjet.net
Enhancing Autonomous Vehicle Applications with Advanced Lane Detection and Tracking Dr. Jyoti R Maranur1, Gangu 2 1
Associate. Professor, Dept. of Computer Science and Engineering, Sharnbasva University, Kalaburagi ,Karnataka , India 2 Student, Dept. of Computer Science and Engineering, Sharnbasva University, Kalaburagi ,Karnataka ,India -------------------------------------------------------------------------***-----------------------------------------------------------------------
Abstract
challenges. By harnessing the capabilities of OpenCV, a versatile and open-source computer vision library, this system aims to provide vehicles with the critical ability to comprehend and interpret road markings, allowing them to navigate with heightened precision. The project's methodology revolves around the strategic combination of k-means clustering and Canny edge detection algorithms. Kmeans clustering is employed to segment the road environment into distinct regions, thereby enhancing the system's ability to differentiate between lane markings and other visual elements. Canny edge detection, a cornerstone technique in image processing, aids in identifying edges and contours, enabling the system to pinpoint the boundaries of lanes with remarkable accuracy. The significance of this project lies in its potential to significantly improve the safety and reliability of autonomous vehicles. By integrating the advanced capabilities of OpenCV, k-means clustering, and Canny edge detection, the system can contribute to a more robust perception of the vehicle's surroundings, facilitating better decision-making and trajectory planning. In the subsequent sections of this project, we will delve deeper into the implementation details, experimental setup, results, and conclusions. Through this exploration, we aim to illuminate the transformative role that intelligent lane detection and tracking systems, powered by OpenCV and fundamental image processing techniques, can play in shaping the future of autonomous vehicle applications. By capitalizing on the inherent adaptability of the OpenCV toolkit and the precision of k-means clustering and Canny edge detection, our project aspires to not only enhance lane detection accuracy but also contribute to a comprehensive perception module that empowers autonomous vehicles to navigate complex urban and highway environments seamlessly. Through these concerted efforts, we seek to redefine the boundaries of autonomous vehicle capabilities, ushering in a new era of safer, more efficient, and intelligent transportation.
In the rapidly evolving landscape of autonomous vehicles, ensuring safe and efficient navigation is of paramount importance. This project centers around the augmentation of autonomous vehicle capabilities through the implementation of advanced lane detection and tracking systems. By harnessing cutting-edge computer vision techniques, the project aims to provide vehicles with an enhanced ability to identify and track lane boundaries on diverse roadways. The project's primary objective is to develop and integrate a robust lane detection and tracking system that can seamlessly operate under various lighting and environmental conditions. Through the utilization of deep learning algorithms and real-time processing, the system aims to accurately discern lane markings and fluctuations, enabling the vehicle to maintain its intended path and make informed decisions. Methodologically, the project involves the training of convolutional neural networks (CNNs) on extensive datasets of road images, enabling the model to recognize intricate lane patterns and adapt to real-world scenarios. Furthermore, a fusion of sensor data, including cameras and LiDAR, contributes to a comprehensive perception of the vehicle's surroundings. Keywords: Autonomous vehicles, Lane detection, Lane tracking, Advanced computer vision, Deep learning
1. INTRODUCTION In the evolving realm of autonomous vehicles, one of the paramount challenges is to ensure safe and reliable navigation in diverse and often unpredictable real-world environments. The advent of advanced computer vision techniques has opened avenues for addressing this challenge, with lane detection and tracking playing a pivotal role in enhancing the autonomy and safety of vehicles. This project delves into the realm of autonomous vehicle applications, focusing on the development and integration of an intelligent lane detection and tracking system, leveraging the power of OpenCV, k-means clustering, and Canny edge detection techniques. The main objective of this project is to augment autonomous vehicles with an intelligent system that accurately identifies, delineates, and tracks lane boundaries under varying lighting conditions, road geometries, and environmental
© 2023, IRJET
|
Impact Factor value: 8.226
2. Related Works Article[1]A Comprehensive Review of Lane Detection and Tracking Techniques for Autonomous Vehicles by Lee, J. et al. in 2021 This survey offers a comprehensive examination of lane detection and tracking methods, emphasizing OpenCV, k-
|
ISO 9001:2008 Certified Journal
|
Page 510