Road networks play an important role in a number of geospatial applications, such as cartographic, infrastructure planning and traffic routing software. Automatic and semi-automatic road network extraction techniques have significantly increased the extraction rate of road networks. Automated processes still yield some erroneous and incomplete results and costly human intervention is still required to evaluate results and correct errors. With the aim of improving the accuracy of road extraction systems, three objectives are defined in this thesis: Firstly, the study seeks to develop a flexible semi-automated road extraction system, capable of extracting roads from QuickBird satellite imagery. The second objective is to integrate a variety of algorithms within the road network extraction system. The benefits of using each of these algorithms within the proposed road extraction system, is illustrated. Finally, a fully automated system is proposed by incorporating a number of the algorithms investigated throughout the thesis. Copyright / Dissertation (MSc)--University of Pretoria, 2010. / Computer Science / unrestricted

abstract: Deforestation is a common phenomenon in Bangladesh, leaving the country under a great threat of losing its natural habitat. The increasing rate of natural habitat loss has raised questions regarding the country’s forest resource management practices. These practices were originally adopted to protect the forest ecosystem and secure the livelihood of the people dependent on forest resources. Despite the support from development partners like the United States Agency for International Development (USAID), the country is still struggling to protect its forest resources from human encroachment. One of the major problems is the lack of inconclusiveness in current approaches. Most initiatives are not evidence-based and are project-based for only a certain period of time. This has failed to ensure sustainable outcomes. This study looks at Bangladesh’s Himchari National Park forest management system to generate evidence regarding deforestation from 1991-2018 and highlight existing gaps. To identify and analyze the gaps, the study uses a social-ecological system (SES) lens. Results reveal deforestation across different time periods, articulates the overall governance structure regarding forest resource management, and provides an overview of the major gaps within the system. The study also offers a set of recommendations for improving the existing management system and policy implications. / Dissertation/Thesis / Masters Thesis Urban and Environmental Planning 2020