I am trying to calculate the trajectory of a moving object (specifically, a thrown object) through a series of video frames. My tracking algorithm can reliably detect ~90% of the object occurrences throughout the video, giving an x, y, and radius size (in pixels) value. However, the tracking method is not resilient to noise and therefore a lot of false-positives are picked up too.
I was wondering if anyone could point me in the right direction to finding an algorithm that will help me to:
- (1) Filter the noisy data from the found points
- (2) build a good trajectory estimation using these filtered points and a simple physics model
- (3) potentially even help to interpolate points within the trajectory that were missed by the tracking algorithm.
Any help would be greatly appreciated.