Show simple item record

dc.contributor.authorAksoy, S.en_US
dc.contributor.authorAkçay H. G.en_US
dc.contributor.authorWassenaar, T.en_US
dc.date.accessioned2016-02-08T10:00:30Z
dc.date.available2016-02-08T10:00:30Z
dc.date.issued2010en_US
dc.identifier.issn0196-2892
dc.identifier.urihttp://hdl.handle.net/11693/22466
dc.description.abstractAutomatic mapping and monitoring of agricultural landscapes using remotely sensed imagery has been an important research problem. This paper describes our work on developing automatic methods for the detection of target landscape features in very high spatial resolution images. The target objects of interest consist of linear strips of woody vegetation that include hedgerows and riparian vegetation that are important elements of the landscape ecology and biodiversity. The proposed framework exploits the spectral, textural, and shape properties of objects using hierarchical feature extraction and decision-making steps. First, a multifeature and multiscale strategy is used to be able to cover different characteristics of these objects in a wide range of landscapes. Discriminant functions trained on combinations of spectral and textural features are used to select the pixels that may belong to candidate objects. Then, a shape analysis step employs morphological top-hat transforms to locate the woody vegetation areas that fall within the width limits of an acceptable object, and a skeletonization and iterative least-squares fitting procedure quantifies the linearity of the objects using the uniformity of the estimated radii along the skeleton points. Extensive experiments using QuickBird imagery from three European Union member states show that the proposed algorithms provide good localization of the target objects in a wide range of landscapes with very different characteristics. © 2009 IEEE.en_US
dc.language.isoEnglishen_US
dc.source.titleIEEE Transactions on Geoscience and Remote Sensingen_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/TGRS.2009.2027702en_US
dc.subjectLinear object detectionen_US
dc.subjectMultiscale texture analysisen_US
dc.subjectObject-based performance evaluationen_US
dc.subjectShape analysisen_US
dc.titleAutomatic mapping of linear woody vegetation features in agricultural landscapes using very high resolution imageryen_US
dc.typeArticleen_US
dc.departmentDepartment of Computer Engineeringen_US
dc.citation.spage511en_US
dc.citation.epage522en_US
dc.citation.volumeNumber48en_US
dc.citation.issueNumber1en_US
dc.identifier.doi10.1109/TGRS.2009.2027702en_US
dc.publisherInstitute of Electrical and Electronics Engineersen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record