Support Vector Selection and Adaptation and its application in remote sensing

Kaya, Gulsen Taskin; Ersoy, Okan K.; Kamasak, Mustafa E.

doi:10.1109/rast.2009.5158235

Cited by 6 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where: Support vector machine (SVM) is a supervised classification method derived from statistical learning theory that often yields good classification results from complex and noisy data [15][16][17][18]. SVM separates the classes with a decision surface that maximizes the margin between the classes [19].…”

Section: Minimum Distance Using Mahalanobis Distancementioning

confidence: 99%

Accuracy Analysis Comparison of Supervised Classification Methods for Anomaly Detection on Levees Using SAR Imagery

2017

View full text Add to dashboard Cite

This paper analyzes the use of a synthetic aperture radar (SAR) imagery to support levee condition assessment by detecting potential slide areas in an efficient and cost-effective manner. Levees are prone to a failure in the form of internal erosion within the earthen structure and landslides (also called slough or slump slides). If not repaired, slough slides may lead to levee failures. In this paper, we compare the accuracy of the supervised classification methods minimum distance (MD) using Euclidean and Mahalanobis distance, support vector machine (SVM), and maximum likelihood (ML), using SAR technology to detect slough slides on earthen levees. In this work, the effectiveness of the algorithms was demonstrated using quad-polarimetric L-band SAR imagery from the NASA Jet Propulsion Laboratory's (JPL's) uninhabited aerial vehicle synthetic aperture radar (UAVSAR). The study area is a section of the lower Mississippi River valley in the Southern USA, where earthen flood control levees are maintained by the US Army Corps of Engineers.

show abstract

Section: Minimum Distance Using Mahalanobis Distancementioning

confidence: 99%

Accuracy Analysis Comparison of Supervised Classification Methods for Anomaly Detection on Levees Using SAR Imagery

2017

View full text Add to dashboard Cite

show abstract

“…The SVSA method consists of two stages: selection of support vectors obtained by LSVM and adaptation of the selected support vectors [4]. In the selection stage, some of the support vectors are eliminated as they are not sufficiently useful for classification.…”

Section: Support Vector Selection and Adaptationmentioning

confidence: 99%

Hybrid SVM and SVSA method for classification of remote sensing images

Kaya

Ersoy

Kamasak

2010

2010 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

A linear support vector machine (LSVM) is based on determining an optimum hyperplane that separates the data into two classes with the maximum margin. The LSVM typically has high classification accuracy for linearly separable data. However, for nonlinearly separable data, it usually has poor performance. For this type of data, the Support Vector Selection and Adaptation (SVSA) method was developed, but its classification accuracy is not very high for linearly separable data in comparison to LSVM. In this paper, we present a new classifier that combines the LSVM with the SVSA, to be called the Hybrid SVM and SVSA method (HSVSA), for classification of both linearly and nonlinearly separable data and remote sensing images as well. The experimental results show that the HSVSA has higher classification accuracy than the traditional LSVM, the nonlinear SVM (NSVM) with the radial basis kernel, and the previous SVSA.

show abstract

“…SUPPORT VECTOR SELECTION AND ADAPTATION Support vector selection and adaptation (SVSA) is a novel supervised classification method that can classify both linearly and nonlinearly separable data [7]- [8]. The method uses the support vectors obtained by a linear support vector machine (LSVM), and selects the most useful vectors in terms of classification accuracy, which are called reference vectors.…”

Section: Introductionmentioning

confidence: 99%

Spectral and spatial classification of earthquake images by support vector selection and adaptation

Kaya

Ersoy

Kamasak

2010

2010 International Conference of Soft Computing and Pattern Recognition

Self Cite

View full text Add to dashboard Cite

The aim of this study is to extract homogenous and edge regions from a post-earthquake Quickbird satellite image with high resolution and to combine this spatial information with spectral information in classification of earthquake damage. In order to extract the homogenous and edge regions from the image, a spatial filtering approach and Canny filter were used. A novel method called support vector selection and adaptation (SVSA) was used in classification of earthquake damage. Pixel and texture-based classification were separately carried out in order to show their comparative classification performance. For implementation, a small region from city of Bam in Iran was selected.

show abstract

Support Vector Selection and Adaptation and its application in remote sensing

Cited by 6 publications

References 10 publications

Accuracy Analysis Comparison of Supervised Classification Methods for Anomaly Detection on Levees Using SAR Imagery

Accuracy Analysis Comparison of Supervised Classification Methods for Anomaly Detection on Levees Using SAR Imagery

Hybrid SVM and SVSA method for classification of remote sensing images

Spectral and spatial classification of earthquake images by support vector selection and adaptation

Contact Info

Product

Resources

About