Jump to content

Good method for detecting walls in a map


Recommended Posts

Good morning,

 

I'm spending a lot of time trying to convert a simple map into a set of segments in order to perform a Scan Matching with diferent robot poses for localization. I see there's a huge number of tools in Labview regarding Computer Vision and Pattern Matching but, until now, I can't find anything that satisfies my needs.

I tryed Edge Detection.vi but it returns not only the segment of wall but a complete line from side to side of the ROI as you can try in the example I attached. In addition, Edge detection doesn't work well with diagonal walls. 

I could use Contour Detection.vi but it turns out that is computationally expensive according to perfermance profile plus it detects contours as points but I need lines because my map is composed of simple straight lines.

Finally I tried IMAQ Rake 3 but I don't know very well how it works and there's no examples of use in the examples folder.

 

Labview is an amazing programa with a lot of already made complex nodes, There must be a way to simulate what a robot equipped with a Laser Range Finder or LIDAR would see if running in a very simple 2D room.

 

Thanks in advance.

Find_Edge_Detection.vi

post-35621-0-61333100-1371455769.png

Link to comment

I though that was only for detecting circular shapes. I'll give it a try, lets see.

Do you now any node to compute Scan/Line Matching given a map and a set of points defining a contour? Like in the figure I attached. 

I initially thought coding the algorithms manually, but since there's plenty of Machine Vision nodes in LabView 2011 I would like to use as much high level nodes as I can. I even saw some LIDAR nodes but they seem to be only for communication purposes, not for simulation.

 

Thanks for answering.

post-35621-0-30802100-1371467848.png

Link to comment

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.

Guest
Unfortunately, your content contains terms that we do not allow. Please edit your content to remove the highlighted words below.
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

×
×
  • Create New...

Important Information

By using this site, you agree to our Terms of Use.