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.
Need help with object tracking.
Hello guys,
I am very new to the Microsoft HoloLens community and programming in general. But I am willing to learn. My school recently bought a set of the HoloLens, and we are supposed to develop an app or of sort that detects object in a degraded visual environment. So I was hoping someone would be able to give me a basis on how I can approach this project. Based on my knowledge we can use the object detecting entities on the HoloLens, so far that's all I know. I would really appreciate some help.
Thanks
Vamshi Chittaluri
Best Answer
-
Options
CurvSurf
✭✭
Object detection (and/or recognition, measurement) in a degraded visual environment is absolutely impossible at the moment!
Even if we are armored in HW/SW technologies including 3-D cameras, mathematics, statistics, computer vision, robotics, we will be short on brains in timescale terms of at least 3~5 years.
5
Answers
@vamshi_chittaluri94
Object detection (and/or recognition, measurement) in a degraded visual environment is absolutely impossible at the moment!
Even if we are armored in HW/SW technologies including 3-D cameras, mathematics, statistics, computer vision, robotics, we will be short on brains in timescale terms of at least 3~5 years.
Hey CurvSurf,
Thanks for the input, I really appreciate it! Is there any way we can connect external sensors to the HoloLens. For example, object detection based on sensors that are connected to a body and they transmit the readings onto the HoloLens. Suppose I as a body am contained in a sphere, and I have multiple sensors attached to me that would map a sphere, and the HoloLens would present readings from the sensors that would show a close obstacle in my close vicinity on the sphere, with me being in the center.
Thanks
Vamshi Chittaluri
@vamshi_chittaluri94
Visual sensing inside a spherical spatial environment is hell on computer vision or photogrammetry because of the parameter singularity. There will be no diffenrence of object distances, when you are in the center of the sphere. It will be more terrible if there is no distinct features, e.g. non-periodical textures.
I correct above comments of:
In photogrammetry, 'danger cylinder' is well known.
Thanks, Is there a guide or something where I can follow for basic obstacle detection using the HoloLens? If I can aclamatize myself to the basics, I will explore further options available to me in this domain.
Thanks
Vamshi
@vamshi_chittaluri94
With 'basic' obstacle detection, any triangles of spatial mapping could be obstacle.
How a virtual character can avoid obstacles is the problem.