This asset is a Marker-Less Augmented Reality Example using the actual environment as input instead of printed square markers and display 3d model in WebCamTexture in real-time.
I am trying to adjust the source code so it works with multiple images but i am not having much success with the task.
I have adjusted the buildpatternfromimage() to receive a List of patterns, have the matcher train from the List Descriptors that is returned but furthet along, the detection keeps detecting only the 1st image of the set.
Would it be possible to include in the source code a way of having the detecting compare the frame with a set of images (in this case is the same object in a 360° view from several images)?
Hi!
I am trying to adjust the source code so it works with multiple images but i am not having much success with the task.
I have adjusted the buildpatternfromimage() to receive a List of patterns, have the matcher train from the List Descriptors that is returned but furthet along, the detection keeps detecting only the 1st image of the set.
Would it be possible to include in the source code a way of having the detecting compare the frame with a set of images (in this case is the same object in a 360° view from several images)?
Thank you!!