eCite Digital Repository

A multi-tier higher order Conditional Random Field for land cover classification of multi-temporal multi-spectral Landsat imagery


Salmon, BP and Kleynhans, W and Olivier, JC and Schwegmann, CP and Olding, WC, A multi-tier higher order Conditional Random Field for land cover classification of multi-temporal multi-spectral Landsat imagery, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 26-31 July 2015, Milan, Italy, pp. 4372-4375. ISBN 978-1-4799-7929-5 (2015) [Refereed Conference Paper]

Restricted - Request a copy

Copyright Statement

Copyright 2015 IEEE

Official URL:

DOI: doi:10.1109/IGARSS.2015.7326795


In this paper we present a 2-tier higher order Conditional Random Field which is used for land cover classification. The Conditional Random Field is based on probabilistic messages being passed along a graph to compute efficiently the conditional probability for a land cover class. Conventionally the information is passed among direct spatial neighbors to improve classification accuracy. The inclusion of higher order descriptive structures in the graphs allow for more information to be pass along to further improve classification accuracy. Unfortunately this increases the computational cost beyond what is feasible to classify a large geographical area. In this work we investigate a spatially based cluster potential to improve classification accuracy while keeping the computational costs tractable. We also expand the typical 1-tier protograph used in conventional CRFs to a 2-tier graph to encapsulate the temporal dimension. This further improves the classification accuracy by modeling the seasonal variations experienced throughout the year. The conventional and higher order CRF are compared to a Random Forest on monthly composited Landsat images. These two CRFs are then compared to the same CRFs expanded to a 2-tier graph. An overall improvement between 2-4% is observed in our study area which is located near the city of Vryheid, South Africa.

Item Details

Item Type:Refereed Conference Paper
Keywords:context awareness, graphical models, image classification, remote sensing, satellites, statistics
Research Division:Engineering
Research Group:Geomatic engineering
Research Field:Photogrammetry and remote sensing
Objective Division:Expanding Knowledge
Objective Group:Expanding knowledge
Objective Field:Expanding knowledge in engineering
UTAS Author:Salmon, BP (Dr Brian Salmon)
UTAS Author:Olivier, JC (Professor JC Olivier)
UTAS Author:Olding, WC (Mr Willem Olding)
ID Code:103119
Year Published:2015
Deposited By:Engineering
Deposited On:2015-09-22
Last Modified:2016-08-02

Repository Staff Only: item control page