CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2002 vol.24 Issue No.10 - October
Issue No.10 - October (2002 vol.24)
<p><b>Abstract</b>—An image of a three-dimensional target is generally characterized by the visible target subcomponents, with these dictated by the target-sensor orientation (target pose). An image often changes quickly with variable pose. We define a class as a set of contiguous target-sensor orientations over which the associated target image is relatively stationary with aspect. Each target is in general characterized by multiple classes. A distinct set of Wiener filters are employed for each class of images, to identify the presence of target subcomponents. A Karhunen-Loeve representation is used to minimize the number of filters (templates) associated with a given subcomponent. The statistical relationships between the different target subcomponents are modeled via a hidden Markov tree (HMT). The HMT classifier is discussed and example results are presented for forward-looking-infrared (FLIR) imagery of several vehicles.</p>
Hidden Markov model, infrared imagery, classification.
Priya Bharadwaj, Lawrence Carin, "Infrared-Image Classification Using Hidden Markov Trees", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.24, no. 10, pp. 1394-1398, October 2002, doi:10.1109/TPAMI.2002.1039210