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.

Potential data loss with stereo_image_proc

asked 2013-05-18 11:48:12 -0500

mortonjt
217 ●7 ●8 ●15

updated 2014-01-28 17:16:34 -0500

ngrennan
1 ●1 ●1

Hello,

I have been messing around with the point clouds generated by stereo_image_proc for the bumblebee2 for a little bit now. I have just applied the toROSMsg command to convert my point clouds to opencv images and realized that there are many gapping holes in my images.

Is this a universal tendency for stereo_image_proc? Or is this an indication that I need to do much more parameter tuning via rqt_reconfigure?

edit retag flag offensive close merge delete

add a comment

1 Answer

Sort by » oldest newest most voted

answered 2013-05-19 21:23:08 -0500

Stefan Kohlbrecher

24361 ●173 ●299 ●444 https://www.energy-rob...

Yes, the artifacts you are seeing are related to how stereo block matching works. Parameter tuning will allow some optimization, but noise and gaps in stereo point clouds should be expected and will not go away completely in any but the most controlled scenarios.

The "Choosing good stereo parameters" tutorial provides some help on what the knobs are with regards to hopefully improving results.

edit flag offensive delete link

add a comment

Question Tools

1 follower

Stats

Asked: 2013-05-18 11:48:12 -0500

Seen: 263 times

Last updated: May 19 '13

Potential data loss with stereo_image_proc edit

1 Answer

Question Tools

Stats

Related questions

Potential data loss with stereo_image_proc