Development of spectral spatial strategies for detection of engineered objects using hyperspectral data

Abstract

Humans all across the globe migrate to cities/urban areas in search of better newlinelivelihood. In India alone, the migrant population moving to cities is likely to rise to newline40% by 2030. Urbanization takes a heavy toll of the scarce resources. Besides, there newlineare many adverse environmental effects of rapid urbanization. Urban planners, newlinetherefore, have to continuously control and monitor the urban expansion, plan newlineamenities, make judicious allocation of lands for industries, residences and agriculture, newlineensure low environmental pollution and simultaneously also address several other newlinechallenges of urban planning. newlineRemote sensing in general has been a very important supporting tool in the newlinehands of urban planners in assessment of existing urban growth particularly in newlineextraction of different levels of urban engineered surfaces such as roads and roofs etc. newlineand its interpolation to assess future urban growth. The development in the field of newlineremote sensing has therefore always been of interest to urban planners. The newlinedevelopment of Hyperspectral Remote Sensing has further enabled urban planners in newlinebetter assessment of urban expanse. However, though hyperspectral data is significantly newlinemore useful to the urban planners, it comes with its own set of challenges such as newlinespectral variability, mixed pixel problems, accuracy requirements, requirement of newlinerecovery shape for correct identification of urban engineered surfaces (roads and roofs), newlineselection of an appropriate approach such as target detection/classification/machine newlinelearning approach for information extraction providing better accuracy etc. The present Thesis explores one of the relevant problems useful for urban newlineplanners i.e development of spectral-spatial strategies for detection of engineered newlineobjects using hyperspectral data. This problem has been explored under three newlineiv newlineobjectives. The first objective deals with an exhaustive comparative assessment of newlinestandard spectral target detection algorithms for engineered objects using hyperspectral newlinedata, under four categories.