A MRF model-based segmentation approach to classification for multispectral imagery

Sarkar, Arnab; Biswas, Mainak; Kartikeyan, B.; Kumar, Vinod; Majumder, K. L.; Pal, Deepika

doi:10.1109/tgrs.2002.1010897

Cited by 79 publications

(62 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even though image segmentation has been heavily studied in image processing and computer vision fields, and despite the early efforts [6] that use spatial information for classification of remotely sensed imagery, segmentation algorithms have only recently started receiving emphasis in remote sensing image analysis. Examples of image segmentation in the remote sensing literature include region growing [7] and Markov random field models [8] for segmentation of natural scenes, hierarchical segmentation for image mining [9], region growing for object level change detection [10] and fuzzy rule-based classification [11], and boundary delineation of agricultural fields [12].…”

Section: Introductionmentioning

confidence: 99%

Spatial Techniques for Image Classification

Aksoy¹

2006

Signal and Image Processing for Remote Sensing

View full text Add to dashboard Cite

The constant increase in the amount and resolution of remotely sensed imagery necessitates development of intelligent systems for automatic processing and classification. We describe a Bayesian framework that uses spatial information for classification of high-resolution images. First, spectral and textural features are extracted for each pixel. Then, these features are quantized and are used to train Bayesian classifiers with discrete non-parametric density models. Next, an iterative split-and-merge algorithm is used to convert the pixel level classification maps into contiguous regions. Then, the resulting regions are modeled using the statistical summaries of their spectral, textural and shape properties, and are used with Bayesian classifiers to compute the final classification maps. Experiments with three ground truth data sets show the effectiveness of the proposed approach over traditional techniques that do not make strong use of region-based spatial information.

show abstract

Section: Introductionmentioning

confidence: 99%

Spatial Techniques for Image Classification

Aksoy¹

2006

Signal and Image Processing for Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Various segmentation methods for remote sensing images have been proposed in the literature [62], [63], [64], [65], [66] [84]. Edge based segmentation is based on detection of edges.…”

Section: Spatial-spectral Classificationmentioning

confidence: 99%

Consensual and Hierarchical Classification of Remotely Sensed Multispectral Images

Lee

Ersoy

2006

2006 IEEE International Symposium on Geoscience and Remote Sensing

View full text Add to dashboard Cite

“…In this work the MRF has been defined over pixel sites, and as such, the computation time for such an approach is expected to be very high when large number of groundtruth classes occur in a natural scene, which is usually the case. We attempt this investigation in a way similar to [6]. After an initial segmentation performed by a technique developed in the framework for tonal region image , we define a MRF on the sites comprising the initial oversegmented regions.…”

Section: Introductionmentioning

confidence: 99%

A MRF Based Segmentatiom Approach to Classification Using Dempster Shafer Fusion for Multisensor Imagery

Sarkar¹,

Banerjee²,

Nair³

et al. 2004

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract.A technique has been suggested for multisensor data fusion to obtain landcover classification. It takes care of feature level fusion with Dempster-Shafer rule and data level fusion with Markov Random Field model based approach vis-a-vis for determining the optimal segmentation. Subsequently, segments are validated and classification accuracy for the test data is evaluated. Two illustrations of data fusion of optical images and a Synthetic Aperture Radar (SAR) image is presented and accuracy results are compared with those of some recent techniques in literature for the same image data.

show abstract

A MRF model-based segmentation approach to classification for multispectral imagery

Cited by 79 publications

References 29 publications

Spatial Techniques for Image Classification

Spatial Techniques for Image Classification

Consensual and Hierarchical Classification of Remotely Sensed Multispectral Images

A MRF Based Segmentatiom Approach to Classification Using Dempster Shafer Fusion for Multisensor Imagery

Contact Info

Product

Resources

About