Identify vegetation lanes on image

asked 2017-09-04 10:43:14 -0500

manatttta gravatar image

I have images that consist of vegetation disponsed in lines (may or may not be straight lines).

I need to implement an algorithm that identifies those lines and produces a binary mask image tagging the vegetation pixels. This mask can whether be a dense mask (flagging all the identified vegetation pixels) or skeleton mask (1-pixel wide lines identifying the center of the vegetation lanes).

Here is an example of input images:

Image 1

And here is one of the possible expected outputs:

Example output

So far, I've tried the following approaches which result in the following problems:

  • Canny edge detector: yields lots of false positives due to shadows
  • Image threshold: yields false positives due to ground vegetation.

Anyone has more ideas?


edit retag flag offensive close merge delete


some more input images will be helpful to understand the problem.

sturkmen gravatar imagesturkmen ( 2017-09-04 10:59:40 -0500 )edit

I think auto local threshold (ex: Sauvola) will work in this case if you choose the right color space & chanel to reduce noise. You can also reduce noise using bandpass filter (FFT) before processing.

Ziri gravatar imageZiri ( 2017-09-05 02:51:41 -0500 )edit
sturkmen gravatar imagesturkmen ( 2017-09-05 05:37:21 -0500 )edit