POSTPROCESSING OF CORRELATION FOR ORIENTATION ESTIMATION

We present a high-SNR approach to estimating the orientation of distor ted target objects, where the distortion is out-of-plane rotation. The presence and position of the targets are detected with a bank of dist ortion-invariant correlation filters. The filter set we use, known as hybrid composite filters, yields complex responses at the target locat ions, The peak magnitude responses indicate target locations. The corr elation phase angles, at the target locations, are linearly combined i nto complex signatures unique to a particular orientation. A maximum-l ikelihood M-ary classification algorithm is used to determine the most likely orientation from a finite number of orientations. In practice, we do not use all the hybrid filters and the ones we do use are optim ally selected and combined for detection and discrimination. Given the target location, additional filtering can be accomplished with an inn er-product operation rather than correlation. A second set of filters, optimized for angle estimation, are applied as inner products at the target locations to construct the orientation signatures. A rigorous m athematical treatment of the optimum signature detection architecture is presented and numerical simulations demonstrate the capabilities of this approach. (C) 1997 Society of Photo-Optical Instrumentation Engi neers.