Position - , rotation - , scale - , and orientation - invariant multiple object recognition from cluttered scenes

A method of tracking objects in video sequences despite any kind of perspective distortion is demonstrated. Moving objects are initially segmented from the scene using a background subtraction method to minimize the search area of the filter. A variation on the Maximum Average Correlation Height (MACH) filter is used to create invariance to orientation while giving high tolerance to background clutter and noise. A log r-θ mapping is employed to give invariance to in-plane rotation and scale by transforming rotation and scale variations of the target object into vertical and horizontal shifts. The MACH filter is trained on the log r-θ map of the target for a range of orientations and applied sequentially over the regions of movement in successive video frames. Areas of movement producing a strong correlation response indicate an in-class target and can then be used to determine the position, in-plane rotation and scale of the target objects in the scene and track it over successive frames.