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 my point cloud is merge to background data . #7006

Closed
vigneshsara opened this issue Aug 3, 2020 · 5 comments
Closed

why my point cloud is merge to background data . #7006

vigneshsara opened this issue Aug 3, 2020 · 5 comments

Comments

@vigneshsara
Copy link

Required Info
Camera Model D400
Firmware Version (Open RealSense Viewer --> Click info)
Operating System & Version Linux (Ubuntu 18.0
Platform PC
SDK Version 2
Language C++
Segment Robot

Issue Description

i have taken the point cloud data in high_density mode in 1000mm and 750mm height, on 1000mm my point cloud data is merge to background(ground) , if i decrease the height to 750mm its not look like that , please ref the below images

750mm height image
Screenshot from 2020-08-03 15-36-11

1000mm height image
1000mm_cloud

  1. this is except behavior in depth algorithm when increase the height ???
  2. Its is any possible to get the 750mm behavior in 1000mm height.
@MartyG-RealSense
Copy link
Collaborator

Hi @vigneshsara The 1000 mm point cloud looks much more "wavy" compared to the 750 mm distance. Increased waviness in the point cloud can be a known consequence as the camera is moved further away (if increasing the distance of the camera from the observed object is what you mean by "height").

There are a couple of very good references about point cloud waviness:

#1375
#4553

Could you test whether you get an improved cloud with the "Default" preset please, as this has clean edges and reduced point cloud spraying.

@vigneshsara
Copy link
Author

HI @MartyG-RealSense thank for your replay . but my question is not based on waviness nature of the cloud. Its is split between the object and background (ground) .in 750mm the split is more visible but in 1000mm split is not visible.

@MartyG-RealSense
Copy link
Collaborator

MartyG-RealSense commented Aug 3, 2020

Error in depth measurement scales linearly with distance. The further that the camera moves away from the observed object, the greater the amount of error in the measurements becomes. This is known as RMS error.

It looks to me though that the separation in the 750 mm image is not a "split" but an area that is empty of depth data because the camera cannot read depth detail from that side of the object at that distance for some reason. Such areas are typically rendered as plain black, as there is no depth information in them.

In the 1000 mm image, you can see the edges of the box much better. So in that respect, the 1000 mm image is the better depth image of the two (aside from the increased waviness).

@MartyG-RealSense
Copy link
Collaborator

Hi @vigneshsara Do you still require assistance with this case, please? Thanks!

@MartyG-RealSense
Copy link
Collaborator

Case closed due to no further comments received.

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

No branches or pull requests

2 participants