Search

We have investigated multi-temporal polarimetric synthetic aperture radar (SAR) data for urban land-cover classification using an object-based support vector machine (SVM) in combinations of rules. Six-date RADARSAT-2 high-resolution polarimetric SAR data in both ascending and descending passes were acquired in the rural–urban fringe of the Greater Toronto Area during the summer of 2008. The major land-use/land-cover classes include high-density residential areas, low-density residential areas, industrial and commercial areas, construction sites, parks, golf courses, forests, pasture, water, and two types of agricultural crops. Various polarimetric SAR parameters were evaluated for urban land-cover mapping and they include the parameters from Pauli, Freeman and Cloude–Pottier decompositions, the coherency matrix, intensities of each polarization, and their logarithm forms. The multi-temporal SAR polarimetric features were classified first using an SVM classifier. Then specific rules were developed to improve the SVM classification results by extracting major roads and streets using shape features and contextual information. For the comparison of the polarimetric SAR parameters, the best classification performance was achieved using the compressed logarithmic filtered Pauli parameters. For the evaluation of the multi-temporal SAR data set, the best classification result was achieved using all six-date data (kappa = 0.91), while very good classification results (kappa = 0.86) were achieved using only three-date polarimetric SAR data. The results indicate that the combination of both the ascending and the descending polarimetric SAR data with an appropriate temporal span is suitable for urban land-cover mapping. [ABSTRACT FROM AUTHOR]

This research investigates urban sprawl in the Greater Toronto Area (GTA) between 1985 and 2005 and the nature of the resulting landscape fragmentation, particularly with regard to the Oak Ridges Moraine (ORM), an ecologically important area for the region. Six scenes of Landsat TM imagery were acquired in summer of 1985, 1995, and 2005. These images and their texture measures were classified into eight land cover classes with very satisfactory final overall accuracies (93-95 %). Analysis of the classifications indicated that urban areas grew by 20 % between 1985 and 1995 and by 15 % between 1995 and 2005. Landscape fragmentation due to spatio-temporal land cover changes was evaluated using urban compactness indicators and landscape metrics, and results from the latter were used to draw conclusions about probable environmental impact. The indicator results showed that urban proportions increased in nearly all areas outside of the metropolitan center, including on portions of the ORM. The landscape metrics reveal that low density urban areas increased significantly in the GTA between 1985 and 2005, mainly at the expense of agricultural land. The metric results indicate increased vulnerability and exposure to adverse effects for natural and semi-natural land cover through greater contrast and lowered connectivity. The degree of urban perimeter increased around most environmentally significant areas in the region. Changes like these negatively impact species and the regional water supply in the GTA. Further investigation into specific environmental impacts of urban expansion in the region and which areas on the ORM are most at risk is recommended. [ABSTRACT FROM AUTHOR]