Skip to content

Detection of lane of a straight road & distinguish b/w solid & dashed lane lines

Notifications You must be signed in to change notification settings

sparsh-b/lane_detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Detect straight lane & distinguish b/w solid & dashed lane

  • This is done as part of project2 of ENPM673 at UMD.
  • Conversion to grayscale, binary thresholding, dilation & erosion, connected component analysis are applied in succession.
  • Blobs of sensible sizes are isolated.
  • Canny edges are detected.
  • Hough lines are applied to detect the lines.
  • The outputted lines are filtered to isolate 2 groups of lines which are sloped around 50 & 120 degrees.
  • An average line which fits each group is calculated. This step gave 2 lines corresponding to 2 lanes.
  • Once both the lanes are detected, the number of white pixels each of the lane lines sits on (when the lane lines are superimposed on the lanes) are calculated & the lane line sitting on fewer number of white pixels is considered as the broken line & the other as the solid line.
  • Link to output video
  • Usage python3 detect_lane.py

Note:

  • The developed algorithm will work for straight lanes.
  • It might have limitations when the lanes are not very bright.

About

Detection of lane of a straight road & distinguish b/w solid & dashed lane lines

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages