Spatio-temporal contextual classification based on Markov random field modelA contextural classifier based on a Markov random field model, which can utilize both spatial and temporal contexts, is investigated. Spatial and temporal neighbors are defined, and the class assignment of each pixel is assumed to be dependent only on the measurement vectors of itself and those of its spatial and temporal neighbors according to the Markov random field property. Only interpixel class dependency context is used in the classification. The joint prior probability of the classes of each pixel and its spatial and temporal neighbors are modeled by a Gibbs random field. The classification is performed in a recursive manner. Experiments with multi-temporal Thematic Mapper data show promising results.
Document ID
19920052596
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Jeon, Byeungwoo (NASA Headquarters Washington, DC United States)
Landgrebe, D. A. (Purdue University West Lafayette, IN, United States)
Date Acquired
August 15, 2013
Publication Date
January 1, 1991
Subject Category
Earth Resources And Remote Sensing
Meeting Information
Meeting: IGARSS ''91: Annual International Geoscience and Remote Sensing Symposium