Compensated Rotational-Invariant Fast Motion Tracking with Collateral Trajectory Guess
A. N. Jayalath, Mohammad A. U. Khan · 2014
In this paper we introduce a method to track the motion of a fast moving objects, in a video with blurred background images being captured by a rotating camera. When tracking motion of a fast-moving object like a car, we need to find solutions basically for two issues. Firstly, to eliminate the rotational effect of the camera we need to find a method of matching two given consecutive frames in the sequence. Because of the fast rotation of the camera that follows the moving vehicles, the use of feature points (i.e. detection and matching) is of little value as we get blurred background (and possibly blurred foreground objects as well). Secondly, it is necessary to identify a fast-processing method either to develop a reference background for an indirect method, or to detect fast-moving objects in direct processing for motion tracking.