Extract line network from binary images

[Igby]

I would like to create a LabView VI that receives an input image and the RGB-color codes of the powerlines depicted in the image. The output should (eventually) consist of id'd polygonial connections and their coordinates.

Right now I've finished creating a VI that converts the source image to a binary image with the respective line color types extracted into a binary image (see below).

I've been trying to apply some of edge/line finding VIs supplied by LabView Vision, but the results have not been very convincing.

I have considered implementing some sort of vectorization algorithm like 'Straight Line Extraction Using Iterative Total Least Squares Methods' or even some sort of line-walking-and-mapping algorithm, but before I do so I'd like to know if there already is some kind of fitting algorithm out there.

Attached you can find examples for the source and binary images.

Thanks in advance for your input!

[Suse]

Hi lbgy,

I had a look at the functions included in Vision. Maybe you can fix it with the Imaq Extract Contour VI in the LabVIEW palette.

Best regards

Suse

[AmitShachaf]

What you are trying to do looks like a cool algorithm.

I would be interested to see how it comes out.
I was in a talk a few years back were they implemented kalmen filter to track the roads and connect the broken lines. I still have the summary I believe.

It was done in matlab not labview.

I implemented in the past algorithm in labview that brake the line to short segments and use radon transform to detect the lines.

When the sections are sufficiently short a curve line is almost strait line. Then when you have multiple short segments of strait line you can fit the line between the points.

This algorithm worked great for me. It was for the paper industry. Problem was a little bit different.

Thanks - Amit,