| TECHNICAL DETAILS: Recently, scientists have begun to understand the visual cortex of small mammals. This understanding has led to the creation of new algorithms that are achieving new levels of sophistication in electronic image processing. With the advent of such biologically inspired approaches, in particular with respect to neural networks, scientists have taken another step towards the aforementioned goals. The Pulse Coupled Neural Network is a neural network algorithm that produces a series of binary pulse images when stimulated with a grey scale or color image. In this context, the thesis will address the development of an unsupervised urban change detection scheme for very-high spatial resolution optical imagery (about 60 cm).
MORE DETAILS
FRAMEWORK: Understanding growth factors is critical for urban planning, environmental studies, and resource management. Accurate and up-to-date information on the status and trends of urban ecosystems is needed to develop strategies for sustainable development and to improve the livelihood of cities. OFFERED BENEFITS: The selected student will learn to analyze satellite imagery over urban areas and to interpret the changes occurred. Moreover, he/she will work in an international context, acquiring good knowledge of the IDL programming language.
|