In this paper, we proposed a new method to generate forest type classification maps accurately and efficiently using high-resolution imagery, such as aerial photographs. We introduced hierarchical image segmentation techniques which not only make use of high-resolution images, but also combine low-resolution images created from the high resolution images themselves. One of the major challenges in object-based classification is the selection of the right texture features for the accurate classification of forest types. Here we proposed three new types of structural texture features, namely, the pattern of illuminated / shadowed pixels, the pattern of the boundary lines of illuminated / shadowed crown areas, and local binary pattern textures to describe the morphological characteristics of forests. Regarding the choice of spectral features, we utilized normalized spectral features of the illuminated areas of tree crowns. For each object, spectral and textural features were calculated, and forest classification was performed using the Nearest Neighbor classification method. To assess the effectiveness of the proposed method, the classified map was verified by comparing the entire map to a visual interpretation map. Furthermore, we also compared the accuracy and processing time of the proposed object-based method with those of the conventional object-based classification method. Our evaluation confirmed that by utilizing the proposed method we could achieve classification results that were at a practical level close to the results of visual interpretation.
Since the 1990s, the Egyptian government has embarked on two national projects on settlement and agricultural development in the Western desert in preparation for expected future population growth. One of them is the Toshka irrigation project, which carries water from Lake Nasser through the depression of El Kharga towards Farafra Oasis. Another is the East Oweinat project, which has enlarged agricultural land in the south of the Western desert by developing water resources from underground aquifers of Nubian sandstone. This paper focuses on the El Kharga Oasis, which has had its own water source since ancient days, to extract characteristics of the land use change of the western desert area in conjunction with the two national projects from Landsat chronological data of the last three decades. Land coverage was classified by conducting brightness adjustment using bands 7, 4 and 3, and the classification process was based on the k-means method in advance. Against the background of political unrest in recent years, the area of Toshka Lake is shrinking, and agricultural land development area in the Toshka region has become unstable. The land use change of Kharga Oasis in the past 30 years has shown gradual increases of date palm and acacia grove areas (1.5 % per year on average), fields and/or pastures with dense palm trees (1.8 % per year), fields and/or pastures with scarce palm trees (0.6 % per year), and crop fields (0.9 % per year), with somewhat greater increases of fallow fields (2.3 % per year on average) and abandoned fields and residential areas (2.6 % per year). The extensive land use characterized by the expanding pasture may drastically change in the future by the extension of the Toshka waterways. Kharga Oasis, with its rich archaeological resources, and now its moderate economic base for settlement, may once again experience high population growth in the northeast direction.