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
Detect the state of a real object
JLF
✭
Let's say I have a real seesaw and in the fulcrum I have a marker which I detect with my Hololens. I have both (marker and seesaw) in view. I would like to know which end of the seesaw is up (the left or the right side). How can I analyze it?
I want to apply the same idea to any object, for example: get to know if a real switch is on or off, whether a traffic light is red, yellow or green, if it's there any car in a parking lot, etc.
0
Answers
Hey, @JLF
Should your solution be utilising markers or be markerless?
In case of the former you'd simply associate different markers representing different states of an object and make sure only one marker is visible at a time.
In case of the latter the task sounds so broad that it's pretty much evolving an eye and a brain and letting them learn for a few years. I'm not very familiar with modern day's machine learning advancements but perhaps some special cases like the traffic light colour could be implemented.
Hope this helps.
Building the future of holographic navigation. We're hiring.
Hi @stepan_stulov , it should be markerless.
I mean, I could add a marker to find a place or object (let's say I use a marker to know where the switch or traffic light is) but I can't use markers to know the state of that object (I can't use markers to know if the traffic light is in red, yellow or green, or switch is on or off).
The problem is that the "state" of an object is an extremely broad term. In case of a traffic light it's the color. In case of some, say, lever it's mechanical constitution of the object. In case, in case, in case...
You would have to limit the implementation to only one kinda of understanding of what the state of an object is and apply the right tech to it: spatial mapping, computer vision, markers etc. Perhaps you'll end up with a few different implementations like color-based, is/is-not based, etc.
But I don't believe there is a generic solution to this problem yet. It requires a human.
PS: As I said I have no idea about modern machine learning or computer vision advancements.
Building the future of holographic navigation. We're hiring.