Attention: Answers.ros.org is deprecated as of August the 11th, 2023. Please visit robotics.stackexchange.com to ask a new question. This site will remain online in read-only mode during the transition and into the foreseeable future. Selected questions and answers have been migrated, and redirects have been put in place to direct users to the corresponding questions on Robotics Stack Exchange. Additional details are available here.

the scale problem of libviso2

libviso2

asked 2013-11-07 21:41:23 -0500

Lily
1 ●1 ●1 ●1

Hello! I use my own images to run libviso2, but the result is not very well. There existed a scale problem in both mono and stereo program. There are two sample rates in my experiments. One is 5 m/frame, another is 1 m/frame. The results showed between two consecutive frames, the distance in stereo system are about 10 meters and 2 meters respectively. However, in mono system the distance are about 1 meters and 0.2 meters respectively. How can I solve it? Thank you!

edit retag flag offensive close merge delete

add a comment

1 Answer

Sort by » oldest newest most voted

answered 2013-12-28 12:03:01 -0500

Miquel Massot

1471 ●7 ●17 ●33 http://srv.uib.es/

In mono odometry, the scale is a parameter you have to fix. From two consecutive frames it's impossible to compute scale. Using stereo image pairs for each frame helps reduce error and provides additional depth and scale information.

edit flag offensive delete link

add a comment

Question Tools

1 follower

Stats

Asked: 2013-11-07 21:41:23 -0500

Seen: 315 times

Last updated: Dec 28 '13

the scale problem of libviso2 edit

1 Answer

Question Tools

Stats

Related questions

the scale problem of libviso2