The use of context in the classification of urban aerial imagery

Urban regions present some of the most challenging areas for the remote sensing community. Many different types of land cover have similar spectral responses, making them difficult to distinguish from one another. Traditional per-pixel classification techniques suffer particularly badly because they only use these spectral properties to determine a class, and no other properties of the image, such as context. This project presents the results of the classification of a deeply urban area of Dudley, West Midlands, using 4 methods: Supervised Maximum Likelihood, SMAP, ECHO and Unsupervised Maximum Likelihood. An accuracy assessment method is then developed to allow a fair representation of each procedure and a direct comparison between them. Subsequently, a classification procedure is developed that makes use of the context in the image, though a per-polygon classification. The imagery is broken up into a series of polygons extracted from the Marr-Hildreth zero-crossing edge detector. These polygons are then refined using a region-growing algorithm, and then classified according to the mean class of the fine polygons. The imagery produced by this technique is shown to be of better quality and of a higher accuracy than that of other conventional methods. Further refinements are suggested and examined to improve the aesthetic appearance of the imagery. Finally a comparison with the results produced from a previous study of the James Bridge catchment, in Darleston, West Midlands, is made, showing that the Polygon classified ATM imagery performs significantly better than the Maximum Likelihood classified videography used in the initial study, despite the presence of geometric correction errors.

Assessment of national health systems performance in the WHO African region

There is growing peer and donor pressure on African countries to utilize available resources more efficiently in a bid to support the ongoing efforts to expand coverage of health interventions with a view to achieving the health-related Millennium Development Goals. The purpose of this study was to estimate the technical and scale efficiency of national health systems in African continent. Methods The study applied the Data Envelopment Analysis approach to estimate the technical efficiency and scale efficiency among the 53 countries of the African Continent. Results Out of the 38 low-income African countries, 12 countries national health systems manifested a constant returns to scale technical efficiency (CRSTE) score of 100%; 15 countries had a VRSTE score of 100%; and 12 countries had a SE score of one. The average variable returns to scale technical efficiency (VRSTE) score was 95% and the mean scale efficiency (SE) score was 59%; meaning that while on average the degree of inefficiency was only 5%, the magnitude of scale inefficiency was 41%. Of the 15 middle-income countries, 5 countries, 9 countries and 5 countries had CRSTE, VRSTE and SE scores of 100%. Ten countries, six countries and 10 countries had CRSTE, VRSTE and SE scores of less than 100%; and thus, they were deemed inefficient. The average VRSTE (i.e. pure efficiency) score was 97.6%. The average SE score was 49.9%. Conclusion There are large unmet need for health and health-related services among countries of the African Continent. Thus, it would not be advisable for health policy-makers address NHS inefficiencies through reduction in excess human resources for health. Instead, it would be more prudent for them to leverage health promotion approaches and universal access prepaid (tax-based, insurance-based or mixtures) health financing systems to create demand for under utilised health services/interventions with a view to increasing ultimate health outputs to efficient target levels.