0

what is a suitable way to detect road markings. I am currently using the canny algorithm to detect edges, I then use LMS and RANSAC to try and highlight the road markings specifically. Instead I am getting lines in undesired areas within the image, is there away to use canny to reduce noise or any other general pre-processing I need to do in order to achieve desired results?

John321
  • 45
  • 5
  • This [paper](https://www.researchgate.net/profile/Oleksandr_Bailo/publication/312286941_Robust_Road_Marking_Detection_and_Recognition_Using_Density-Based_Grouping_and_Machine_Learning_Techniques/links/59f0228f0f7e9baeb26ad615/Robust-Road-Marking-Detection-and-Recognition-Using-Density-Based-Grouping-and-Machine-Learning-Techniques.pdf) describes an approach to detect road markings. – Alex Bailo Aug 05 '18 at 14:14

1 Answers1

0

The first stage in canny is to apply a Gaussian filter to reduce the noise in the image.

If you want to get a better noise reduction you can do one of the following:

  1. As part of the Canny algorithm choose a bigger Gaussian kernel and with a bigger standard deviation . The problem with this method is that you can loose a lot of details in the image.
  2. Use a bilateral filter of the image before using Canny. For an explanation about bilateral filter look at: How to remove grainy details from an image
Community
  • 1
  • 1
Amitay Nachmani
  • 3,259
  • 1
  • 18
  • 21