Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

SVO Monocular code does not work with images in "mono16" format (TUM-VI) #51

Open
joshi-bharat opened this issue Sep 28, 2018 · 2 comments

Comments

@joshi-bharat
Copy link

The images from (TUM-VI dataset cannot be loaded with error Unknown image type 2!. It would be better if you could add support for "mono16" images as well.

@slinshady89
Copy link

slinshady89 commented Jun 2, 2019

I had the same issue.
go to svo_interface line 198 and change:

image = cv_bridge::toCvCopy(msg)->image;

to

image = cv_bridge::toCvShare(imageMessage, sensor_msgs::image_encodings::BGR8)->image;

But somehow the tracking of features is lost sometimes maybe due to my change.
Probably a conversion with cv::cvtColor(src, bwsrc, cv::COLOR_RGB2GRAY); would do it. I should check that too for myself ;)

@joshi-bharat
Copy link
Author

I actually converted the dataset to mono8. Not sure about the SVO performance though.

kazeka added a commit to kazeka/rpg_svo_example that referenced this issue Jan 21, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants