Jump to content

SR Works for Image/Target recognition


Colby
 Share

Recommended Posts

Hello All,

 

I have been enjoying developing with testing out the Vive Pro for the past little while and I am excited about the possibilities of what AR will bring to high-end VR. 

 

I have been working on a demo attempting to use the front-facing cameras to detect image targets placed in a room. Then have some objects in the experience placed correctly where they are at in the room. An example would be for the Pro Cameras recognize a target next to a light switch and have a light switch in the experience appear at the same location. As I get further I will try to share some update videos and such. 

 

But I am curious if anyone else is doing something similar and what their current approach is. 

I have used OpenCV to train custom image targets and also tools like Vuforia. The tricky part is then translating that position of the target in the real world to the accurate corresponding position in the virtual world.  I have also thought about using the OBJ generated room mesh scan from the cameras to add references points on the model itself. But It would ideal to use the AR place objects for dynamically placed objects. For others, this would be a cool way to have tracked objects without any additional hardware. I am hoping that there will a solution packaged in SRWorks. Does anyone know if there is anything on the roadmap for SR Works to have anything like that?

 

Best, 

 

Colby

 

Link to comment
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
 Share

×
×
  • Create New...