pakopon Posted June 17, 2013 Report Share Posted June 17, 2013 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 Quote Link to comment
ShaunR Posted June 17, 2013 Report Share Posted June 17, 2013 The IMAQ Spoke might be worth looking at Quote Link to comment
pakopon Posted June 17, 2013 Author Report Share Posted June 17, 2013 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. Quote Link to comment
ShaunR Posted June 17, 2013 Report Share Posted June 17, 2013 (edited) The vision toolkit is for, well, vision (images, OCR, camera feature detection.etc) I would take a look instead at the Robotics toolkit which has path planning, obstacle avoidance, directed graphs etc. Edited June 17, 2013 by ShaunR Quote Link to comment
pakopon Posted June 17, 2013 Author Report Share Posted June 17, 2013 I'll check it out. Thanks. Quote Link to comment
pakopon Posted June 17, 2013 Author Report Share Posted June 17, 2013 So, I tested "Spoke.vi" and I compared it with Extract Contour and simulated LIDAR lines. It works perfect for simulating a Robot Scan Match based on LIDAR devices, Thanks a lot. Quote Link to comment
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.