GEOSCAN Search Results: Fastlink


TitleFully polarimetric synthetic aperture radar (SAR) processing for crop type identification
AuthorHong, G; Wang, S; Li, J; Huang, J
SourcePhotogrammetric Engineering and Remote Sensing no. 2, 2015 p. 109-117,
Alt SeriesEarth Sciences Sector, Contribution Series 20140171
PublisherAmerican Society for Photogrammetry and Remote Sensing
Mediapaper; on-line; digital
File formatpdf
Subjectsremote sensing; radar imagery; Cloude and Pottier decomposition; polarimetric synthetic aperture radar; polarimetric decomposition; accuracy
ProgramAquifer Assessment & support to mapping, Groundwater Geoscience
AbstractThe target or polarimetric decomposition is widely used to process a multi-polarization SAR imagery to establish a correspondence between physical characteristics of interested objects and observed scattering mechanisms. Polarimetric decomposition parameters are used as the basis for developing new classification methods for analyzing polarimetric SAR data. This study proposes to combine two polarimetric decomposition parameters (entropy (H) and angle (a)) derived from Cloude and Pottier decomposition method and total scattered power (Span) in crop type identification. Support vector machine (SVM) classification algorithm is selected as a classifier to resolve limitations of classifications based on polarimetric decomposition parameters. The advantages of the proposed method are determined by comparing with other commonly used methods based on polarimetric features and the results produced from the coherency matrix, i.e., without target decomposition. Results show that the proposed method is about 10% better than other methods based on polarimetric features without Span, and it outperforms the result from the coherency matrix with about 4% improvement in the overall accuracy.
Summary(Plain Language Summary, not published)
Mapping surface water cycle and groundwater recharge needs information for vegetation on an aquifer surface. This paper presents a new approach for mapping crop types using Radarsat-2 satellite data. This approach combines two polarimetric SAR methods and works to improve crop type identification. The advantages of the proposed method and the substantial improvement in results for identifying crop types are demonstrated by comparing with other commonly used methods based on polarimetric features. The results will improve water cycle mapping and water resources assessment using the CCRS EALCO modelling system.