Remote sensing is a promising technology that finds as diverse applications as defence, urban planning, healthcare, and environmental management. Collecting countrywide statistics of crop yield is one of the main tasks of remote sensing. Acquiring and processing very high-resolution (VHR) satellite images are means accomplishing this task. Processing these remotely sensed (RS) images requires not only great computational power but also efficient algorithms for image segmentation and classification. This thesis aims at presenting the work carried out for applying computationally efficient spectral and textural analysis on very high-resolution RS images, and combining the results from the two analyses for improved classification of vegetation covers. The spectral analysis presented here adopts the unsupervised approach of classification, whereas the textural analysis adopts the supervised approach of classification. The fusion of the contour information from the unsupervised spectral analysis with the pixel class information from the supervised textural analysis yields successful classification results. The thesis takes as a test case, a site covered with orchards, truck crops, crop fields, vineyards, forest, and fallows from Nîmes region, France. The real contribution includes improved version of the unsupervised classification method based on k-means clustering, a method of introducing rotation invariance into the texture features based on discrete Fourier transform, and a method of fusing a supervised classification with an unsupervised classification. This thesis is all about developing these algorithms.
