Fuzzy based Hough Transform for Lane Mark Detection

Manpreet Kaur, Ravneet Kaur Sidhu


Lane Detection plays an important role in Intelligent Transportation system. Lane detection is an important aspect of autonomous vehicles. It is also a preventive measure for road accidents. Hough Transform technique uses the edge map obtained from segmentation to detect the lane marks. The overall objective of this paper is to improve the lane detection algorithm using adaptive segmentation techniques like Otsu, Fuzzy and K-means. It has been found that the value used to segment the road image containing lanes has been taken statically. To overcome this, a new lane detection method with an adaptive segmentation value has been proposed. This approach has the ability to boost the lane colorization in Far-view, Near-view and curved road images in efficient manner by utilizing the Additive Hough Transform algorithm with optimized segmentation techniques. Various parameters like Accuracy, F-measure, Mean Square Error are used for calculating the effectiveness of this technique. The proposed technique yields accurate results as compared to existing techniques. 

Full Text:


Copyright (c) 2016 Manpreet Kaur

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.


All published Articles are Open Access at  https://journals.pen2print.org/index.php/ijr/ 

Paper submission: ijr@pen2print.org