Skip to content

vinaykumarhegde/lane_detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Lane Detection and Tracking

Sample code to detect lanes in the highway images and track it's x-intercept value in the image.

Image Processing

To account for real world lighting conditions, we can use Adaptive Bilateral Filtering (selectively smooth the image and preserves the edges) and Histogram Equalizations. Below pictures show the results.

Adaptive Bilateral Filtering

bilateral_filter

Histogram Equalization

hist_1 hist_2

Lane Detection

From the enhanced images, Canny Edge Detector is used to detect the edges in the image and filter out the noisy edges. Using this binay image from the edge detctor, Hough Transform is used to extract the line information. All the detected lines are used to vote for the possible x-intercept value and strength proportional to their importance and location. Below is one example:

Canny Edge Detection

canny

Lane Detection

lane

Tracking

Once the lane is detected in one image, it's x-intercept values is used in Particle Filter to track the x-intercept values in the next images from the video sequence.

Demo Video:

[Watch on YouTube]

About

Lane Detection and Particle Filter Tracking

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages