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

why are my image drift went object dynamic ? help me plese . #12

Closed
supamon opened this issue Apr 30, 2015 · 3 comments
Closed

why are my image drift went object dynamic ? help me plese . #12

supamon opened this issue Apr 30, 2015 · 3 comments
Labels

Comments

@supamon
Copy link

supamon commented Apr 30, 2015

I can edit the problem?thank you My research, I use version rgbdslamv2.
picture http://image.ohozaa.com/view2/y9BCYXObWfxP7f6j

@kbalisciano
Copy link
Contributor

Try moving back from the camera. In the depth map it looks like you have a little double vision due to the limitations of the camera

On Apr 30, 2015, at 4:42 AM, supamon notifications@github.com wrote:

I can edit the problem?thank you My research, I use version rgbdslamv2.
picture http://image.ohozaa.com/view2/y9BCYXObWfxP7f6j


Reply to this email directly or view it on GitHub.

@supamon
Copy link
Author

supamon commented Jul 20, 2015

c-club-zaa@hotmail.com

@felixendres
Copy link
Owner

It seems the person is very near (less than 80cm) to the camera, therefore the visual features found on the person cannot be located in space and will be ignored. This reduces the amount of features available for estimating the motion. If part of the scene is dynamic the dynamic part may then easily "hijack" the motion estimation. Dynamic scenes are only handled well if the majority of the features are static. I usually had good results, even when people moved in the scene, but as I said, there neeed to be enough static features to "anchor" the motion estimates.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

3 participants