 Landsat imagery has been used extensively for land cover classification since its launch in the 1970s. Over the years, various methods have been developed to improve accuracy and efficiency of land cover classification. These include visual analyses, unsupervised and supervised pixel-based classification methods, sub-pixel, knowledge-based, contextual-based, object-based image analysis, OBA, and hybrid approaches. Each approach has advantages and disadvantages depending on the type of landscape being analyzed. For example, OBIA has been shown to provide better results than pixel-based methods for certain types of landscapes, but it requires careful selection of segmentation scales and may not work well for some types of landscapes. Hybrid approaches have also been found to be effective in some cases, but they require more time and resources to implement. In general, the best results will depend on the type of landscape being analyzed, the type of classification method chosen, and the proper implementation of the selected method. This article was authored by Darius Fiery and Justin Morgan Roth. We are article.tv, links in the description below.