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.
Best framework for hologram placement based on image detection?
SNKaupe
✭
Hi there,
I'm trying to set up an application to recognize one or more real-world objects to determine the HoloLenses placement in regards to said objects. My goal is to do this on several devices, gathering the data needed to allow me to place them into a single virtual coordinate system and share detected object locations or placed holograms.
I found this thread that referenced several frameworks to perform marker detection. However, I'm unsure how up-to-date the information there is and if I've understood them correctly. It seems to me as if I have basically four options:
- PosterCalibrationSample from the Mixed Reality Companion Toolkit. This seems nice and easy to use on a first glance, but the precision doesn't seem up to my needs. I couldn't find any reference to any major improvements in this area. Has anyone recently used this and achieved a precision of less than a centimeter?
- HoloLensARToolkit. Again, looks somewhat easy to use and atleast the demo image looks fine (if a bit wobbly). However, it seems to have only been tested on Visual Studio 2017, while I'm back on the 2015 version and hesitant to update my install due to some legacy software I'm working with. Also, no achievable precision was given. Has anyone experience with this toolkit and its achievable precision, preferably on Visual Studio 2015?
- Vuforia. Possibly the most mature version, but according to the feature matrix, we'd probably need atleast the Classic license, even though development itself seems to be free. Still, I couldn't find any hard numbers concerning the precision Vuforia manages to achieve. Does anybody have some of those?
- DIY. I'd like to avoid that, as I do not have any kind of noticable background in image processing and object detection.
In general, does anyone have experience with one or more of these frameworks and would be willing to tell me how they measure up in regards to both, ease of use and precision? Or did I maybe miss another framework that I could make use of?