Change detection through subspace projection using Independent Component Analysis to track moving targets in scenery

The majority of change detection algorithms for imagery require a differencing of recorded intensity or phase values between images. For these algorithms to properly function, geometric alignment must be performed between the images. For moving targets this is not always possible. The technique presented does not require that the images be perfectly aligned. The method of performing change detection is based upon the concept of image subspace projection. A set of "basis" image maps are formed when combined with a mixing matrix can recreate the original image. The subsequent images are then projected into the base image. The projected image is then subtracted from the original image to perform the change detection. The basis images are computed by applying Independent Component Analysis (ICA) to the sampled image. A spatial filter and then an adaptive threshold filter are applied to pass the locations of changes in the images into the tracking filter. Tracking is performed through the use of multiple motion models. The filter's motion models are adaptive added or deleted as required by the moving object's dynamics. The moving object's state is estimated through extended Kalman filtering.