Multisource Classification of Color and Hyperspectral Images Using Color Attribute Profiles and Composite Decision Fusion

Thoonen, Guy; Mahmood, Zahid; Peeters, Stijn; Scheunders, Paul

doi:10.1109/jstars.2011.2168317

Cited by 34 publications

(17 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These thresholds originate from [5] and are adopted in [8] for the University of Pavia image, displaying good results. Fig.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Usually, to combine the APs with the spectral features, both feature sets are simply concatenated. For the automatic threshold selection algorithm, the thresholds listed in the left part of Table 1 [5] and are successfully adopted for the Pavia University image in [8]. Once again, an SVM classifier with RBF kernel is applied for classification.…”

Section: Experiments and Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Automatic threshold selection for morphological attribute profiles

Mahmood

Thoonen

Scheunders

2012

2012 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

In this article, an automatized procedure for selecting informative values of the thresholds, essential for the construction of morphological attribute profiles, is proposed. To this end, connected component analysis is performed on a preliminary supervised or unsupervised classification result that does not involve contextual information. Subsequently, after extracting the relevant attributes from each of the connected components, the threshold values are found by grouping the attribute vectors using a clustering algorithm. In our experiments, we demonstrate the effect of image scaling on the selected thresholds. In addition, we show the advantage of using our automatic threshold selection approach with respect to manual selection, by both monitoring redundancy and performing a classification experiment.

show abstract

“…These thresholds originate from [5] and are adopted in [8] for the University of Pavia image, displaying good results. Fig.…”

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Experiments and Resultsmentioning

confidence: 99%

Automatic threshold selection for morphological attribute profiles

Mahmood

Thoonen

Scheunders

2012

2012 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

show abstract

“…The problems of multisource and multitemporal land cover mapping have been extensively studied in [5][6][7]. In [5], the authors modeled the multisource and multitemporal images to have the MRF properties, and used this model to develop an image classification algorithm for remote sensing images.…”

Section: Introductionmentioning

confidence: 99%

“…In [5], the authors modeled the multisource and multitemporal images to have the MRF properties, and used this model to develop an image classification algorithm for remote sensing images. Thoonen et al in [6] attempted to jointly classify a high spatial resolution color and a low resolution hyperspectral image of the same scene. In their work, a composite decision fusion (CDF) strategy combining a kernel-based decision fusion technique with the composite kernel classification has been introduced.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Joint Land Cover Mapping and Image Registration Algorithm Based on a Markov Random Field Model

Kasetkasem

Rakwatin²,

Sirisommai

et al. 2013

Remote Sensing

View full text Add to dashboard Cite

Abstract:Traditionally, image registration of multi-modal and multi-temporal images is performed satisfactorily before land cover mapping. However, since multi-modal and multi-temporal images are likely to be obtained from different satellite platforms and/or acquired at different times, perfect alignment is very difficult to achieve. As a result, a proper land cover mapping algorithm must be able to correct registration errors as well as perform an accurate classification. In this paper, we propose a joint classification and registration technique based on a Markov random field (MRF) model to simultaneously align two or more images and obtain a land cover map (LCM) of the scene. The expectation maximization (EM) algorithm is employed to solve the joint image classification and registration problem by iteratively estimating the map parameters and approximate posterior probabilities. Then, the maximum a posteriori (MAP) criterion is used to produce an optimum land cover map. We conducted experiments on a set of four simulated images and one pair of remotely sensed images to investigate the effectiveness and robustness of the proposed algorithm. Our results show that, with proper selection of a critical MRF parameter, the resulting LCMs derived from an unregistered image pair can achieve an accuracy that is as high as when images are perfectly aligned. Furthermore, the registration error can be greatly reduced. OPEN ACCESSRemote Sens. 2013, 5 5090 Keywords: joint land cover mapping and registration; Markov random field; optimum classifier; mean field theory; EM algorithm

show abstract