Map comparison methods that simultaneously address overlap and structure

Methods for map comparison such as the Kappa and Tau statistics have grown popular in applications of remote sensing accuracy assessment. These methods take pairs of raster maps as sets of paired observations and do not consider spatial structure except for cell-by-cell overlap. In contrast, landscape structure metrics such as mean patch size that are commonly used in landscape ecology do express spatial structure, however without addressing cell-by-cell overlap. This paper introduces a number of comparison methods that consider spatial structure and overlap simultaneously. They achieve this by involving the neighbourhood of a cell in the calculation of similarity at its location. For this, the methods make use of a distance weighted moving window. Two test cases demonstrate that the different comparison methods offer a spatial account of varied aspects of map similarity. It is found that the methods can best be used in conjunction with a visual analysis; they then serve to quantify, reject or confirm hypotheses.     

Comparison and relative quality assessment of the GLC2000, GLOBCOVER,MODIS and ECOCLIMAP land cover data sets at the African continental scale

Land cover dynamics at the African continental scale is of great importance for global change studies. Actually, four satellite-derived land cover maps of Africa now available, e.g. ECOCLIMAP, GLC2000, MODIS and GLOBCOVER, are based on images acquired in the 2000s. This study aims at stressing the compliances and the discrepancies between these four land cover classifications systems. Each of them used different mapping initiatives and relies on different mapping standards, which supports the present investigation. In order to do a relative comparison of the four maps, a preamble was to reconcile their thematic legends into more aggregated categories after a projection into the same spatial resolution. Results show that the agreement between the four land cover products is between 56 and 69%. While all these land cover datasets show a reasonable agreement in terms of surface types and spatial distribution patterns, mapping of heterogeneous landscapes in the four products is not very successful. Land cover products based on remote sensing imagery can indeed significantly be improved by using smarter algorithms, better timing of image acquisition, improved class definitions. Either will help to improve the accuracy of future land cover maps at the African continental scale. Data producers may use the areas of spatial agreement for training area selection while users might need to verify the information in the areas of disagreement using additional data sources.     

Classification method,spectral diversity,band combination and accuracy assessment evaluation for urban feature detection

Automatic extraction of urban features from high resolution satellite images is one of the main applications in remote sensing. It is useful for wide scale applications, namely: urban planning, urban mapping, disaster management, GIS (geographic information systems) updating, and military target detection. One common approach to detecting urban features from high resolution images is to use automatic classification methods. This paper has four main objectives with respect to detecting buildings. The first objective is to compare the performance of the most notable supervised classification algorithms, including the maximum likelihood classifier (MLC) and the support vector machine (SVM). In this experiment the primary consideration is the impact of kernel configuration on the performance of the SVM. The second objective of the study is to explore the suitability of integrating additional bands, namely first principal component (1st PC) and the intensity image, for original data for multi classification approaches. The performance evaluation of classification results is done using two different accuracy assessment methods: pixel based and object based approaches, which reflect the third aim of the study. The objective here is to demonstrate the differences in the evaluation of accuracies of classification methods. Considering consistency, the same set of ground truth data which is produced by labeling the building boundaries in the GIS environment is used for accuracy assessment. Lastly, the fourth aim is to experimentally evaluate variation in the accuracy of classifiers for six different real situations in order to identify the impact of spatial and spectral diversity on results. The method is applied to Quickbird images for various urban complexity levels, extending from simple to complex urban patterns. The simple surface type includes a regular urban area with low density and systematic buildings with brick rooftops. The complex surface type involves almost all kinds of challenges, such as high dense build up areas, regions with bare soil, and small and large buildings with different rooftops, such as concrete, brick, and metal.Using the pixel based accuracy assessment it was shown that the percent building detection (PBD) and quality percent (QP) of the MLC and SVM depend on the complexity and texture variation of the region. Generally, PBD values range between 70% and 90% for the MLC and SVM, respectively. No substantial improvements were observed when the SVM and MLC classifications were developed by the addition of more variables, instead of the use of only four bands. In the evaluation of object based accuracy assessment, it was demonstrated that while MLC and SVM provide higher rates of correct detection, they also provide higher rates of false alarms.