Ask Your Question
0

SLAM localizing methods based on camera?

asked 2018-03-05 09:47:16 -0500

HaroldVD gravatar image

updated 2018-03-05 07:57:25 -0500

Are there any SLAM methods that can create a map from the camera output based on colors in ROS? Im working on a project where I can only get an absolute position by using lines that are drawn on the floor, just like a football field.

Most SLAM methods Ive seen like this one: https://vision.in.tum.de/research/vsl... rely a lot on depth-perception. I am just wondering which slam methods can detect (big & long) lines on the floor. I cant rely on walls or objects being detected mostly because the robot sometimes has to navigate in huge halls where the walls are really far away.

edit retag flag offensive close merge delete

1 Answer

Sort by ยป oldest newest most voted
1

answered 2018-03-05 16:31:00 -0500

Gayan Brahmanage gravatar image

You are not able to apply Gmapping directly for this application because it does not give a promising result when enough features are not available in the sensor field of view. RGB-D SLAM also will not work as you have repetitive patterns on your RGB images.

I think your problem seems easy than general SLAM problem. You can extract those line segments using a line detector from RGB image. Then use ICP algorithm to align those frames.

If you need a more robust result, you can use the same method with Rao-Blackwellized particle filter that is used in Gmapping. But you need an accurate data association strategy to work with RBPF.

edit flag offensive delete link more

Your Answer

Please start posting anonymously - your entry will be published after you log in or create a new account.

Add Answer

Question Tools

Stats

Asked: 2018-03-05 07:55:56 -0500

Seen: 219 times

Last updated: Mar 05 '18