The Mixed Reality Forums here are no longer being used or maintained.
There are a few other places we would like to direct you to for support, both from Microsoft and from the community.
The first way we want to connect with you is our mixed reality developer program, which you can sign up for at https://aka.ms/IWantMR.
For technical questions, please use Stack Overflow, and tag your questions using either hololens or windows-mixed-reality.
If you want to join in discussions, please do so in the HoloDevelopers Slack, which you can join by going to https://aka.ms/holodevelopers, or in our Microsoft Tech Communities forums at https://techcommunity.microsoft.com/t5/mixed-reality/ct-p/MicrosoftMixedReality.
And always feel free to hit us up on Twitter @MxdRealityDev.
Align Hologram(s) with real world objects and/or room.
Looking for options to align a hologram (virtual object) with it's real work equivalent. For example overlaying virtual equipment exactly over the real ones or aligning a virtual representation of a room with the actual room it is based on.
I've looked at the newly released Vuforia 6, have used Vuforia for years, but they are licensing the hell out out of you to use Vuforia with Windows 10 or Hololens. Was thinking of using an AR Target on the object or in the room for alignment purposes.
Any thoughts?
Best Answer
-
OptionsCurvSurf ✭✭
@Vern_S
It's the Holy Grail of Computer Vision: Detect, recognize, and measure objects.An object has shape, size, position, and pose (rotation, orientation).
The current AR tools are based on planes, in other words, recognize and detect images (photos, videos) or planes (floor, wall). There are many other shapes than planes, e.g. boxes, spheres, cylinders, cones, rings, etc.
The next generation of AR is 3D AR: Detect, recognize, and measure 3D objects.
https://www.youtube.com/watch?v=C7mLH_5QzvU
https://www.youtube.com/watch?v=8ruiudETvuYOur FindSurface SDK for 3D AR will be prepared for public distribution 1Q 2017.
5
Answers
I haven't tried this, but for aligning a room one idea to look into would be to convert your spatial mapping to planes (https://github.com/Microsoft/HoloToolkit-Unity/blob/master/Assets/HoloToolkit/SpatialMapping/Scripts/SpatialProcessing/SurfaceMeshesToPlanes.cs) and use the generated planes to build your virtual representation. That will get you gross estimations of volume/alignment.
For recognizing an item, If your item is big enough for the planar extraction to work you may also be able to get a signature that your app could recognize. If you can make the assumption that your target is present, you could search all planes in the current environment for the group with most-similar properties to a pre-calculated signature, and select the most likely group to overlay a rendering on.
@Vern_S
It's the Holy Grail of Computer Vision: Detect, recognize, and measure objects.
An object has shape, size, position, and pose (rotation, orientation).
The current AR tools are based on planes, in other words, recognize and detect images (photos, videos) or planes (floor, wall). There are many other shapes than planes, e.g. boxes, spheres, cylinders, cones, rings, etc.
The next generation of AR is 3D AR: Detect, recognize, and measure 3D objects.
https://www.youtube.com/watch?v=C7mLH_5QzvU
https://www.youtube.com/watch?v=8ruiudETvuY
Our FindSurface SDK for 3D AR will be prepared for public distribution 1Q 2017.
Thanks guys for the responses. Additional computer vision capability is what is needed. It will come. Find Surface looks very promising. Thanks for sharing.
~V~