Start a new topic

Point Cloud Object Recognition

SDK Version 9.0 Professional Edition

Unity 2018.4.22f1


I am trying to rotate the 3D point cloud and have it translate over to Unity with the .wto extension. I've made my rotation in Wikitude Studio and saved it, then downloaded the file and brought it over to Unity; however, I don't see the translation go through in Unity. Below are the two images, first one being the studio and the second being the preview in Unity, where you'll see that the rotation did not seem like it was saved from Wikitude Studio. Is it possible to get this working as I would like to ensure that my custom augmentations are truly aligned to my object and I would rather not rotate my all my canvas/components.

image


image



Hi Tai,

this issue is known and under investigation right now. I will try to update you ASAP on this matter.


Kind regards,
Gökhan

Hi Tai,

sorry that it took so long! I have some good news. Wikitude Studio just received a major update and I would kindly ask you to try out your workflow again (save your point cloud transforms in Wikitude Studio, export the target collection and import it into Unity).


Kind regards,

Gökhan

Thank you Gökhan,


I do have another question though -- it has to do with taking pictures for object recognition based off of 'object recognition best practices' : https://www.wikitude.com/documentation/latest/unity/objecttargetguide.html


1. "Ideally take pictures from the same area of the object from different spots" -- I am assuming this means take images of an area of the object, but at different angles?

2. "Use pictures with some overlap between each other" -- I am unsure what this means, am I basically just taking multiple pictures of the same area & angle (basically duplicate)?
3. Should I always start the initial collection of images of the object in a white background and upload, and then transition the object to an area with different background colors, or it doesn't matter which background I use first?


Regarding taking pictures for objects that are rather large (lets say a statue based off of your example -- https://www.youtube.com/watch?v=IdnA1xXZe2M), 


4. how would I capture images of the object following the best practices as it may be too large to fit a background studio or have even lighting (I have an object I need to recognize and it is fairly large).


5. "Avoid taking pictures from a very close distance (few centimeters) -- my large object has components within it, I assume it's okay to take pictures of a section of that object after taking pictures of the entire object to provide more accurate data points, or does every picture need to include the entirety of the object?


Thank you, please let me know if I need to create a new topic instead.

Hi Tai,


Your questions are very interessting and should definetly be mirrored in the documentation itself! Could you please open a new topic on this?


Kind regards,
Gökhan

Login or Signup to post a comment