Secondary camera, ghost overlay, video merge... I do not know if what I mean has a more specific name.
I wonder if this is a thing. This could be insightful for example in racing sports where participants race one after another e.g. alpine skiing, downhill mountain bike, showjumping etc. E.g. comparing the current starter to the leader.
Given the camera position is fixed and only the camera angle and zoom is varying to focus on the current starter, the tasks to be able to overlay videos would be to:
- match the timing, i.e. both videos start when the timer starts
- align and overlay the videos according to specific marker points. Keypoint detection and tracking.
- get the opacity right so that both videos are visible
My question is if there is any research on this. If so, what keywords do I need to search for?
Edit: My seach led me to SIFT (Scale Invariant Feature Transform) and SURF (Speeded-Up Robust Features). Feature matching should be possible with kNN or brute force. A lot can be done with OpenCV.