A SUREY ON A Classical Computer Vision Pipeline For Lane Detection And Turn prediction In Autonomous Driving

  • Unique Paper ID: 178097
  • PageNo: 2164-2169
  • Abstract:
  • Autonomous driving is a major advancement in AI, with Lane Detection Systems (LDS) playing a crucial early role. As urban traffic grows, road safety becomes essential, with many accidents caused by unintended lane departures. Advanced Driver Assistance Systems (ADAS) like Lane Departure Warning and Adaptive Cruise Control help vehicles assess their surroundings and react to potential dangers. However, complex road environments pose challenges in accurate lane prediction. Key visual cues include road boundaries, pavement texture, and lane markings. Machine learning has significantly improved lane detection through image processing and computer vision. In a typical LDS, frames from a real-time video feed are converted to grayscale, denoised using a Gaussian filter, and processed with a Canny Edge Detector to highlight lane edges. A region of interest is then isolated, and the Hough Line Transform (HLT) identifies lane lines, which are superimposed on the original image to estimate the vehicle’s position within the lane. Let me know if you'd like this shorter or even more technical. –

Copyright & License

Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

BibTeX

@article{178097,
        author = {Katuru Vinod and Shankar Prakash Vallam and Pulla Ramji Ambedkar and Polamreddy Mounika and Thota Naveen and Patanam Hema},
        title = {A SUREY ON A Classical Computer Vision Pipeline For Lane Detection And Turn prediction In Autonomous Driving},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {2164-2169},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178097},
        abstract = {Autonomous driving is a major advancement in AI, with Lane Detection Systems (LDS) playing a crucial early role. As urban traffic grows, road safety becomes essential, with many accidents caused by unintended lane departures. Advanced Driver Assistance Systems (ADAS) like Lane Departure Warning and Adaptive Cruise Control help vehicles assess their surroundings and react to potential dangers. However, complex road environments pose challenges in accurate lane prediction. Key visual cues include road boundaries, pavement texture, and lane markings. Machine learning has significantly improved lane detection through image processing and computer vision. In a typical LDS, frames from a real-time video feed are converted to grayscale, denoised using a Gaussian filter, and processed with a Canny Edge Detector to highlight lane edges. A region of interest is then isolated, and the Hough Line Transform (HLT) identifies lane lines, which are superimposed on the original image to estimate the vehicle’s position within the lane.
Let me know if you'd like this shorter or even more technical. –},
        keywords = {Lane Detection, Autonomous Driving Car, Computer Vision, Hough Transform, Canny Edge Detector , Trajectory Prediction},
        month = {May},
        }

Cite This Article

Vinod, K., & Vallam, S. P., & Ambedkar, P. R., & Mounika, P., & Naveen, T., & Hema, P. (2025). A SUREY ON A Classical Computer Vision Pipeline For Lane Detection And Turn prediction In Autonomous Driving. International Journal of Innovative Research in Technology (IJIRT), 11(12), 2164–2169.

Related Articles