Hello everyone.

We have decided to phase out the Mixed Reality Forums over the next few months in favor of other ways to connect with us.

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.

The plan between now and the beginning of May is to clean up old, unanswered questions that are no longer relevant. The forums will remain open and usable.

On May 1st we will be locking the forums to new posts and replies. They will remain available for another three months for the purposes of searching them, and then they will be closed altogether on August 1st.

So, where does that leave our awesome community to ask questions? Well, there are a few places we want to engage with you. 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. And always feel free to hit us up on Twitter @MxdRealityDev.

Vuforia object recognition

Hey guys, is somebody working with the vuforia solution?
If so, does anybody now how the object recognition works?
Are there any tutorials or has somebody made any experiences with vuforia object recognition?

Appreciate any answer.

Thank you for your attention

Answers

  • I don't have a link to a demo of the Object Recognition specifically, but I have done some Vuforia projects and the SDK includes a sample project or two.

    These links may be of some help to you:

    Demo Video
    Great video showing Vuforia integration with Unity and Vuforia running across a bunch of Windows devices. The HoloLens portion starts at 3:15. Totally worth watching the whole thing. (5:31)

     
    Main Page
    https://vuforia.com/blog/vuforia-6

    Getting Started Article
    https://blogs.windows.com/buildingapps/2016/10/12/how-to-develop-augmented-reality-apps-with-vuforia-for-windows-10/ 

    Printable Target Images for HoloLens Samples
    These images are used as tracking targets in the HoloLens samples included in the SDK. They must be printed at 247mm x 173mm (9.7" x 6.8") for models to align to them properly.
    https://developer.vuforia.com/sites/default/files/sample-apps/targets/imagetargets_targets.pdf

    Our Holographic world is here

    RoadToHolo.com      WikiHolo.net      @jbienz
    I work in Developer Experiences at Microsoft. My posts are based on my own experience and don't represent Microsoft or HoloLens.

  • Hi @jbienzms,

    thanks for your answer my friend. I already worked with the image targets and solved the solution with the object recognition. It works nearly the same way like image target. Another question if you dont mind: Is the hololens able to track or recognize real objects (e.g. a big milling machine) if so, how can i do that? Do i need the HTK??

    Also how can i anchor holograms into the real environment? As an engineer in the making its hard for me to deal with everything which has to do with computer science. I also have some difficulties to use the HTK and the scripts correctly?

    Do you have any idea?

    I appreciate it

  • @VR_HSRW1 HoloLens doesn't currently do object recognition in that way. There is a module called Spatial Understanding that can be used to figure out things like open spaces that connect the floor to the ceiling, or places where people can sit. But it doesn't do object recognition. The closest (that I know) are the object recognition system you've discovered in Vuforia and leveraging things like the Azure Face Recognition and other Computer Vision APIs.

    Hope that helps.

    Our Holographic world is here

    RoadToHolo.com      WikiHolo.net      @jbienz
    I work in Developer Experiences at Microsoft. My posts are based on my own experience and don't represent Microsoft or HoloLens.

  • @jbienzms,
    ok i understand. Did you work with vuforia? Do you know how to create more than one image target?
    I'll check the face recognition and the computer visions APIs as soon as possible
    Thank you

  • @VR_HSRW1 said:
    @jbienzms,
    ok i understand. Did you work with vuforia? Do you know how to create more than one image target?
    I'll check the face recognition and the computer visions APIs as soon as possible
    Thank you

    I believe the vuforia for hololens sample download already has the scene set up with two image targets, you can just copy the image target object as many times as you want, you just need to set up the marker data for those targets.

  • @Elspin, okay i'll check it out. Thank you a lot

  • @VR_HSRW1 said:
    @jbienzms,
    ok i understand. Did you work with vuforia? Do you know how to create more than one image target?
    I'll check the face recognition and the computer visions APIs as soon as possible
    Thank you

    Have a look at the Vuforia library How To Add Targets to a Device Database

    and the Vuforia Image Target Guide

    I have used this to produce new targets from a pictures in a book.

    The //Build 2016 showed just how to do this and Unity GDC 2017 showed model car then positioned a picture via HoloLens Spectator View Professional of a AR Real car in 3D.

Sign In or Register to comment.