Infrared-image classification using hidden Markov trees

Priya Bharadwaj, Lawrence Carin

Research output: Contribution to journalArticlepeer-review

35 Scopus citations


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.
Original languageEnglish (US)
Pages (from-to)1394-1398
Number of pages5
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number10
StatePublished - Oct 1 2002
Externally publishedYes


Dive into the research topics of 'Infrared-image classification using hidden Markov trees'. Together they form a unique fingerprint.

Cite this