Abstract
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 on the observations-scattering mechanisms and exploiting the transitions between the scattering mechanisms we decide upon the HMM-land cover type. The classification process is based on the likelihood of observation sequences been evaluated by each model. The performance of the classification approach is assessed my means of fully polarimetric SLC SAR data from the broader area of Vancouver, Canada and was found satisfactory, reaching a success from 87% to over 99%.
Highlights
In the past several decades, Remote Sensing has gradually broadened being the cornerstone in a plethora of research topics
We present a novel land cover classification method based on Hidden Markov Models
We developed the hypothesis that each land cover type is uniquely characterized by an Hidden Markov Models (HMM). At this point, is important to take into consideration that this work differs from others, firstly as for the parallelism we follow with the components of an HMM land cover types and scattering mechanisms and secondly on the way the HMMs were trained
Summary
In the past several decades, Remote Sensing has gradually broadened being the cornerstone in a plethora of research topics. Coherent decomposition methods were developed to characterize completely polarized scattered waves, for which fully polarimetric information is contained in the scattering matrix. Polarimetric Land Cover Classification based on Markov Chains was proposed [12] which gives a high rate of success in discriminating between different land cover types. We developed the hypothesis that each land cover type is uniquely characterized by an HMM At this point, is important to take into consideration that this work differs from others, firstly as for the parallelism we follow with the components of an HMM land cover types and scattering mechanisms and secondly on the way the HMMs were trained. The novelty of the proposed method was challenged from the need to investigate for spatially extended targets, as land cover types, which led us to Hidden Markov Models.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
