File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A pixel shape index coupled with spectral information for classification of high spatial resolution remotely sensed imagery

TitleA pixel shape index coupled with spectral information for classification of high spatial resolution remotely sensed imagery
Authors
KeywordsIndependent components analysis (ICA)
Integration of shape and spectra
Shape feature
Support vector machine (SVM)
Issue Date2006
Citation
IEEE Transactions on Geoscience and Remote Sensing, 2006, v. 44, n. 10, p. 2950-2961 How to Cite?
AbstractShape and spectra are both important features of high spatial resolution remotely sensed (HSRRS) imagery, and they are concrete manifestation of textures on such imagery. This paper presents a spatial feature index, pixel shape index (PSI), to describe the shape feature in a local area surrounding a pixel. PSI is a pixel-based feature which measures the gray similarity distance in every direction. As merely the shape feature is inadequate for classifying HSRRS imagery, a transformed spectral feature extracted by independent component analysis is added to the input vectors of our classifier, and this replaces the original multispectral bands. Meanwhile, a fast fusion algorithm that integrates both shape and spectral features using the support vector machine has been developed to interpret the complex input vectors. The results by PSI are compared with some spatial features extracted using wavelet transform, gray level co-occurrence matrix, and the length-width extraction algorithm to test its effectiveness. The experiments demonstrate that PSI is capable of describing shape features effectively and result in more accurate classifications than other methods. While it is found that spectral and shape features can complement each other and their integration can improve classification accuracy, the transformed spectral components are also found to be more suitable for classification. © 2006 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/330084
ISSN
2023 Impact Factor: 7.5
2023 SCImago Journal Rankings: 2.403
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorZhang, Liangpei-
dc.contributor.authorHuang, Xin-
dc.contributor.authorHuang, Bo-
dc.contributor.authorLi, Pingxiang-
dc.date.accessioned2023-08-09T03:37:40Z-
dc.date.available2023-08-09T03:37:40Z-
dc.date.issued2006-
dc.identifier.citationIEEE Transactions on Geoscience and Remote Sensing, 2006, v. 44, n. 10, p. 2950-2961-
dc.identifier.issn0196-2892-
dc.identifier.urihttp://hdl.handle.net/10722/330084-
dc.description.abstractShape and spectra are both important features of high spatial resolution remotely sensed (HSRRS) imagery, and they are concrete manifestation of textures on such imagery. This paper presents a spatial feature index, pixel shape index (PSI), to describe the shape feature in a local area surrounding a pixel. PSI is a pixel-based feature which measures the gray similarity distance in every direction. As merely the shape feature is inadequate for classifying HSRRS imagery, a transformed spectral feature extracted by independent component analysis is added to the input vectors of our classifier, and this replaces the original multispectral bands. Meanwhile, a fast fusion algorithm that integrates both shape and spectral features using the support vector machine has been developed to interpret the complex input vectors. The results by PSI are compared with some spatial features extracted using wavelet transform, gray level co-occurrence matrix, and the length-width extraction algorithm to test its effectiveness. The experiments demonstrate that PSI is capable of describing shape features effectively and result in more accurate classifications than other methods. While it is found that spectral and shape features can complement each other and their integration can improve classification accuracy, the transformed spectral components are also found to be more suitable for classification. © 2006 IEEE.-
dc.languageeng-
dc.relation.ispartofIEEE Transactions on Geoscience and Remote Sensing-
dc.subjectIndependent components analysis (ICA)-
dc.subjectIntegration of shape and spectra-
dc.subjectShape feature-
dc.subjectSupport vector machine (SVM)-
dc.titleA pixel shape index coupled with spectral information for classification of high spatial resolution remotely sensed imagery-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TGRS.2006.876704-
dc.identifier.scopuseid_2-s2.0-34247346536-
dc.identifier.volume44-
dc.identifier.issue10-
dc.identifier.spage2950-
dc.identifier.epage2961-
dc.identifier.isiWOS:000240881300011-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats