I created a App which has two different phases.
In the first phase, the App takes a Picture and calculates the Descriptors(36 Elements) for the KeyPoints of the Image in different scales with blurring. After calculating this, it puts the Descriptors into a KD-Tree (as keys so its a 36D-Tree). All of these Actions are made in the native Part of my Application.
After that, I reconfigure the Camera and try to get every "Latest" frame of the Camera and calculate the KeyPoints/Descriptors of this Frame.
Now I want to Match that with the Descriptors in the KD-Tree, and thought to use a Matcher from OpenCV, so I dont have a too huge workload with this task.
Is it possible to use the Flann or the BrutforceMatcher from OpenCV for this Task?
Or do I have to make my own Implementation of the Matching algorithm?
The descriptor values are saved into a vector.
↧