Hello everyone.
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.
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.
Comments
The point cloud generated by Apple ARKit with iPhone/iPad without 3-D camera is highly noisy.
However, one of the advantages of the current combination of ARKit with iPhone/iPad is that the measurement distance is limitless if you can translate large enough your iPhone/iPad.
You could even measure the moon by using an iPhone/iPad IF you could translate (i.e. without rotating) enough your iPhone/iPad.
The passive 3-D measuring method (photogrammetry, stereo vision, multi-view geometry) will govern in 5 years. The active method (laser scanner) will disappear.
In next few weeks, by using an iPad with ARKit, we will let to fly a virtual airplane around a dome in an amuse park in Korea. The virtual airplane will be occluded when it is flying behind the dome. In order to get a point cloud of the dome, we will need only to move the iPad about 5 m laterally across to the dome. Intel RealSense, Google Tango, Microsoft HoloLens cannot, because the object distance and size is too large.

Today morning I visited the amuse park. The dome was smaller than I guessed. I got a point cloud (the yellow points) by using an iPad and walking around the dome from 5~7 m distance.
In next few weeks, virtual airplane and cars will circulate around the real dome. Of course, with occlusion.
Definitely early Sept. virtual car and airplane will be wandering on and over the real dome in an amuse park in Korea of 37.43373 127.01940.
If they are going or flying behind the dome they will disappear.
I.e., virtual objects are occluded by real objects.
It's a real magic!
We have experimented on ARKit with an iPad Pro.
Even though the point cloud is highly noisy, CurvSurf FindSurface extracted successfully a sphere for gym ball and a plane for floor. The extracted sphere and plane are in contact.
Gym ball
Point Cloud generated by an iPad Pro with ARKit
Front view
Side view
Top view
Experiment on ARKit with iPad Pro.
https://www.youtube.com/watch?v=2TlJ_8Tq6js
https://youtube.com/watch?v=2TlJ_8Tq6js
CurvSurf will release end Oct. 2017 the C# source code of the Revit Plugin for automatic feature extraction from point cloud by using FindSurface SDK.
The C# source code is free for any usage including modification and distribution.
FindSurface SDK is free for one month testing.
Functions:
• Import point cloud
• Automatic feature extraction of plane, sphere, cylinder, cone, and torus
• Show/hide individual features, inliers, outliers
• Set control parameter values.
Usage:
1. Set program control parameter values:
Real Time 3-D Object Recognition
CurvSurf FindSurface detects, recognizes, and determines the shape, size, location, and orientation of object surfaces in real time.
The RGB images are not used yet, only point cloud.
FindSurface is working in single-thread mode.
https://youtube.com/watch?v=6tn4rMeIBaw
Hi Cristian,
HoloLens is not a device for real time application at all.
HoloLens provides only sparse mesh (spatial mapping, not raw depth data) updated at ca. 1 fps.
FYI,
Google Tango has 5 fps, Intel RealSense has max. 120 fps updating speed of raw dense depth data stream.
As you may know CurvSurf FindSurface can handle raw dense depth data stream in real time.
Joon
We developed a process for scanning in real time with HoloLens but, it is slow so we had to ignore this solution. Because of this, we want to know is CurvSurf FindSurface can help us to detect objects like boxes as well as working with Holotoolkit.
In case that CurvSurf FindSurface was good option for us, what are the steps for integrating it with HoloLens?
Thanks in advance,
Cristian.
@CristianGómez
CurvSurf FindSurface will be available End Jan. 2018 under license. CurvSurf FindSurface is working on Windows (not UWP) and Linux.
YouTube Channel CurvSurf includes videos of detecting and determining the shape, size, position, and orientation of primitive objects including planes, boxes, spheres, cylinders, cones, and tori.
Best,
Joon
Real Time 3-D Object Recognition
3-D Augmented Reality - Apple ARKit
Virtual airplane rotates around a gym ball with occlusion.
Sphere fitting to point cloud determines the position and size of gym ball.
Used:
We will be rotating a virtual real-sized airplane around a real dome of 40 m diameter with occlusion.
Active mobile 3-D cameras, e.g. Google Tango, MS HoloLens, Intel RealSense, are categorically excluded from generating point cloud of large objects. Only passive 3-D measurement methods are under consideration, e.g. ARKit, ARCore, Stereo Vision, etc.
FindSurface SDK - Simple GUI Demo
https://www.youtube.com/watch?v=28mJQVDwzhI
Wall (plane), ball (sphere), pipe (cylinder), paper cone, and elbow (torus).
The point cloud was captured by Google Tango and saved in xyz-format.
The touching size is to be adjusted to the object size.
Find Plane.
Find Sphere.
Find Cylinder.
Find Cone.
Find Torus.
Source codes are available at https://github.com/CurvSurf.
FindSurface SDK can be downloaded from https://developers.curvsurf.com.
FindSurface SDK - Revit Plugin Demo
https://www.youtube.com/watch?v=ThpXAFJEBJ4
1. Select a target shape from menu
2. Click a point among point cloud
3. Repeat from the 1st step again.
FindSurface SDK - Revit Plugin Demo
https://youtu.be/ThpXAFJEBJ4
Source codes are available at https://github.com/CurvSurf.
FindSurface SDK can be downloaded from https://developers.curvsurf.com.
FindSurface SDK - Revit Plugin Demo
https://youtu.be/ThpXAFJEBJ4
Source codes are available at https://github.com/CurvSurf.
FindSurface SDK can be downloaded from https://developers.curvsurf.com.
FindSurface SDK - Revit Plugin Demo
https://youtu.be/ThpXAFJEBJ4
Source codes are available at https://github.com/CurvSurf.
FindSurface SDK can be downloaded from https://developers.curvsurf.com.
FindSurface SDK - Revit Plugin Demo
https://youtu.be/ThpXAFJEBJ4
Source codes are available at https://github.com/CurvSurf.
FindSurface SDK can be downloaded from https://developers.curvsurf.com.
FindSurface SDK - Revit Plugin Demo
https://youtu.be/ThpXAFJEBJ4
FindSurface SDK - Revit Plugin Demo
https://youtu.be/ThpXAFJEBJ4
FindSurface SDK - Revit Plugin Demo
FindSurface SDK - Revit Plugin Demo
https://youtu.be/ThpXAFJEBJ4
FindSurface SDK - Revit Plugin Demo
https://youtu.be/ThpXAFJEBJ4
FindSurface SDK - Revit Plugin Demo
https://youtu.be/ThpXAFJEBJ4