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.
Options

Show Attributes On A moving Body in real world - Holo lenses

can we popup attributes on a real world object when looking through holo lense . How can I achive this ?

Answers

  • Options

    @JosephPaul,

    It isn't easy, and nothing automatically built-in, but you could, with a bit of sleight-of-hand.

    You could try the difficult task of object recognition with Microsoft cognitive services or another computer vision library of your choice using the RGB camera, then map this to 3d coordinates to find the location relative to the HoloLens device, and dynamically create a popup label.

    An easier approach would be to have a way to tag objects in your room before hand (maybe by walking around and tapping on surfaces), then dropping small invisible markers with spatial anchors attached to remember the spot between hololens sessions. You can then use those to place your popups.

    James Ashley
    VS 2017 v5.3.3, Unity 2017.3.0f3, MRTK 2017.1.2, W10 17063
    Microsoft MVP, Freelance HoloLens/MR Developer
    www.imaginativeuniversal.com

  • Options
    utekaiutekai ✭✭✭

    I suspect this is going to end up being an easier endeavor than has been thus far, but the reason is the approach has been to use spatial mapping to find and follow those people you want to mark (a non-workable approach). Or loading up and running locally some heavy-weight image/video processing software.

    A better approach is to use offsite services to track and tag, and use the hololens for display only, rather than performing the raw processing.

    For instance, there are now Cognitive Services APIs that track motion, and those APIs can be used for tagging. This same API also tracks faces, so identifying people either by motion or face tracking, and enhancing that physical image with holographic details is a do-able project.

    I'm not very enamored by the current results provided by Cognitive Services, but they seem to be getting better (and as well the services portfolio is growing). Network delays to offload video and get back results is also going to be an issue, as well as the fees for this service. But it's cheap/free to investigate if they'll work in your use case, and relatively easy to connect with them and start experimenting.

Sign In or Register to comment.