ABSTRACT:To delineate the geological formation at the surface, satellite image classification approaches are often preferred. This study aims to produce a super resolved map with better delineation of the litho-contacts from the medium resolution Landsat image. Conventionally used per-pixel classification provides an output map at the same resolution of the satellite image, while the super resolved map provides the high resolution output map using the medium resolution image. In this study, four test sites are considered for delineating different litho-contacts using super resolution mapping approach in Cuddalore district, southern India. The test sites consists of charnockite, fissile hornblende-biotite gneiss, marine sandstone and sandstone with clay, limestone with calcareous shale and clay, clay with limestone bands/lenses, mio-pliocene and quaternary argillaceous and calcareous sandstone, fluvial and fluviomarine formations. This work compares the per-pixel, super resolved output derived from linear spectral unmixing (LSU) based HNN and spectral angle mapper (SAM) based HNN approaches. The super resolution mapping approach was performed on the medium resolution (30m) Landsat image to obtain the litho-contact maps and the results are compared with the existing maps and observations from field visits. The results showed improved accuracy (90.92%) of the map prepared by the SAM based super resolution approach compared to the LSU based super resolution approach (90.14%) and the maximum likelihood classification approach (83.74%). Such an improved accuracy of the super resolved map (6m resolution) is due to the fact that the lithological mapping is done not merely at the resolution of the image, but at the sub-pixel level. Hence, it is inferred that super resolution mapping applied to multispectral images may be preferred for mapping lithounits and litho-contacts than the conventional per-pixel and sub-pixel image classification methods.
Image classification has evolved from per-pixel to sub-pixel and from sub-pixel to super resolution mapping approaches. Super-resolution mapping (SRM) is a technique which allows mapping at the sub-pixel scale. Super-resolution mapping proves to be the better approach for the accurate classification of coarse spatial resolution images and to resolve mixed pixels in the boundary of such images. The accuracy of the super-resolved output depends on the input derived from the soft classification technique. This paper aims to compare the potential of support vector machine (SVM), spectral angle mapper (SAM) and linear spectral unmixing (LSU) as inputs for super-resolution mapping. The fraction image, distance measure image and probability image obtained from linear spectral unmixing, spectral angle mapper and support vector machine respectively are used as an input for super resolution mapping designed on Hopfield Neural Network (HNN) for the Hyperion image of Peechi reservoir, south India. Effectiveness of the inputs is evaluated by estimating the waterspread area of the Peechi reservoir from each of the outputs. The results indicate that the accuracy of any superresolution approach depends on the inputs from the soft classification approaches. The accuracy of the water spread area estimated from the classified outputs is 95.9%, 96.6% and 99.7% from LSU, SAM and SVM respectively as inputs for the SRM method. Thus, the HNN based SRM method proves to be better when the soft classification input is from SVM.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.