Toward Automated Land Cover Classification in Landsat Images Using Spectral Slopes at Different Bands

For last two decades, various techniques have been advanced for classification of satellite imageries. A vast majority of them are supervised/semisupervised requiring manual selection of samples for each class. Some of the unsupervised approaches are based on hard thresholds and particular to image acquisition modules. In this study, we propose a spectral-slope-based classification technique and subsequently summarize the changes in temporal image sets. Using the properties of spectral slopes, we propose a set of rules for selection of training samples from Landsat imageries for classifying the land cover. The images are initially classified into three classes: water, vegetation, and vegetation-void. Further, vegetation and vegetation-void regions are classified into proper vegetation and dry cropland, and urban land and bare land, respectively. The initial classification is performed by support vector machines, and the second-level classification is performed through k-means clustering and subsequent labeling of clusters to subclasses. Considering temporal images of the same scene, postclassification change summarization is carried out to quantize the land variations, both qualitatively (type of change) and quantitatively (volume of change).The approach has been used in the analysis of images acquired by different sensors operating under similar wavelength ranges.