A novel land cover classification procedure is presented utilizing the infor</span><span style="font-family:Verdana;">mation content of fully polarimetric SAR images. The Cameron cohere</span&...A novel land cover classification procedure is presented utilizing the infor</span><span style="font-family:Verdana;">mation content of fully polarimetric SAR images. The Cameron cohere</span><span style="font-family:Verdana;">nt target decomposition (CTD) is employed to characterize land cover pixel by pixel. Cameron’s CTD is employed since it provides a complete set of elem</span><span style="font-family:Verdana;">entary scattering mechanisms to describe the physical properties of t</span><span style="font-family:Verdana;">he scatterer. The novelty of the proposed land classification approach lies on the fact that the features used for classification are not the types of the elementary </span><span style="font-family:Verdana;">scatterers themselves, but the way these types of scatterers alternate from p</span><span style="font-family:Verdana;">ixel </span><span style="font-family:Verdana;">to pixel on the SAR image. Thus, transition matrices that represent loc</span><span style="font-family:Verdana;">al Markov models are used as classification features for land cover classification. The classification rule employs only the most important transitions for decision making. The Frobenius inner product is employed as similarity measure. Ten different types of land cover are used for testing the proposed method. In this aspect, the classification performance is significantly high.展开更多
A land cover classification procedure is presented utilizing the information content of fully polarimetric SAR images. The Cameron coherent target decomposition (CTD) is employed to characterize each pixel, using a se...A land cover classification procedure is presented utilizing the information content of fully polarimetric SAR images. The Cameron coherent target decomposition (CTD) is employed to characterize each pixel, using a set of canonical scattering mechanisms in order to describe the physical properties of the scatterer. The novelty of the proposed classification approach lies on the use of Hidden Markov Models (HMM) to uniquely characterize each type of land cover. The motivation to this approach is the investigation of the alternation between scattering mechanisms from SAR pixel to pixel. Depending </span><span style="font-family:Verdana;">on the observations-scattering mechanisms and exploiting the transitions </span><span style="font-family:Verdana;">between the scattering mechanisms we decide upon the HMM-land cover type. The classification process is based on the likelihood of observation sequences </span><span style="font-family:Verdana;">been evaluated by each model. The performance of the classification ap</span><span style="font-family:Verdana;">proach is assessed my means of fully polarimetric SLC SAR data from the broader </span><span style="font-family:Verdana;">area of Vancouver, Canada and was found satisfactory, reaching a success</span><span style="font-family:Verdana;"> from 87% to over 99%.展开更多
文摘A novel land cover classification procedure is presented utilizing the infor</span><span style="font-family:Verdana;">mation content of fully polarimetric SAR images. The Cameron cohere</span><span style="font-family:Verdana;">nt target decomposition (CTD) is employed to characterize land cover pixel by pixel. Cameron’s CTD is employed since it provides a complete set of elem</span><span style="font-family:Verdana;">entary scattering mechanisms to describe the physical properties of t</span><span style="font-family:Verdana;">he scatterer. The novelty of the proposed land classification approach lies on the fact that the features used for classification are not the types of the elementary </span><span style="font-family:Verdana;">scatterers themselves, but the way these types of scatterers alternate from p</span><span style="font-family:Verdana;">ixel </span><span style="font-family:Verdana;">to pixel on the SAR image. Thus, transition matrices that represent loc</span><span style="font-family:Verdana;">al Markov models are used as classification features for land cover classification. The classification rule employs only the most important transitions for decision making. The Frobenius inner product is employed as similarity measure. Ten different types of land cover are used for testing the proposed method. In this aspect, the classification performance is significantly high.
文摘A land cover classification procedure is presented utilizing the information content of fully polarimetric SAR images. The Cameron coherent target decomposition (CTD) is employed to characterize each pixel, using a set of canonical scattering mechanisms in order to describe the physical properties of the scatterer. The novelty of the proposed classification approach lies on the use of Hidden Markov Models (HMM) to uniquely characterize each type of land cover. The motivation to this approach is the investigation of the alternation between scattering mechanisms from SAR pixel to pixel. Depending </span><span style="font-family:Verdana;">on the observations-scattering mechanisms and exploiting the transitions </span><span style="font-family:Verdana;">between the scattering mechanisms we decide upon the HMM-land cover type. The classification process is based on the likelihood of observation sequences </span><span style="font-family:Verdana;">been evaluated by each model. The performance of the classification ap</span><span style="font-family:Verdana;">proach is assessed my means of fully polarimetric SLC SAR data from the broader </span><span style="font-family:Verdana;">area of Vancouver, Canada and was found satisfactory, reaching a success</span><span style="font-family:Verdana;"> from 87% to over 99%.