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.
Options
HoloLens + Cognitive Services = Object Recognition
james_ashley
✭✭✭✭
Because it gets asked about alot, I wanted to share Ron's vid demonstrating HoloLens Object Recognition with Cognitive Services: link
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
1
Comments
It would be "The Holy Grail" of computer vision.
The next problemo!
At the moment from the view point of CurvSurf, plane, box, sphere, cylinder, cone, and torus can be detected, recognized, and measured in real-time. The man-made objects.
I like where this is going.
https://github.com/Microsoft/Cognitive-Samples-VideoFrameAnalysis/
https://www.microsoft.com/cognitive-services/en-us/computer-vision-api
@james_ashley
is there any progress on that. ??
@Ankit09_Sangani He says on facebook that he's still working out the kinks before publishing the code.
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
@Ankit09_Sangani @james_ashley you can try my simple impl however, it's not Unity: https://github.com/xamarin/urho-samples/tree/master/HoloLens/CognitiveServices (video is clickable).
@Egorbo Thanks for this code sample. It shows the package Microsoft.ProjectOxford.Vision can indeed run directly on a hololens.
Thanks @Egorbo for putting it together and sharing - it's a great demonstration of what's possible. I know it's not your identification but I got some hilarious readouts when I asked it to "describe" some of the things around my office. Especially because it responds with such an authoritative voice! They include gems like:
Hi @Egorbo, thank you for sharing. What were your advantages using Urho over Unity? I'm unfamiliar with Urho so probably should be a separate thread.
@Jason Urho is a small but brave game engine all you need with it is just a small nuget package. It doesn't require installing some 3rd parties/editors and has a clean and simple API (same Entity-Component architecture).
@bhashem the code saves each frame before sending it to the service so you can check in "Photo gallery" quality of photos, maybe some of them are not very good and that's why CS won't give you a perfect result. Also, you can configure voice if you want
I find UrhoSharp to be a great engine for developing HoloLens applications, as you often want to add a few elements to the world, and are not really designing a "level".
For HoloLens experiences, programmatic APIs just fit very well and work great for prototyping.
There are two other bonuses in my mind: it is just a .NET library, so you get full access to Visual Studio and its tools as well as complete access to all WinRT APIs as well as all the latest C# features.
Egor has a Visual Studio extension as well that give you previewing capabilities for your assets on the IDE, which comes in very handy.
I've noticed you can also use the most recent .net frameworks with urhosharp, as compared to Unity.
Is there an asset store or something similar for urho? Can unity assets be used with the urho engine?
Just thinking through the whole development process and wondering about the limitations around urho as compared to unity.
@Egorbo Thanks for the info, looks quite interesting. When you mention Entity-Component architecture is data fairly easy to pass around from external sources?
@migueldeicaza I appreciate the additional info. You've sold me on giving it a try! I'll certainly check out Egor's extension.
hi! i clicked on the link to try and see the code but it lead on site and there was a page-not-found error.
can you send a link or the code itself?
https://github.com/xamarin/urho-samples/tree/master
HI @angelicaHolo
https://github.com/UoA-eResearch/hololens_facial_recognition
Thanks