|
|
Contents
|
|
| Week 1: |
Classification approaches employed in remotely sensed imagery. Unsupervised vs. supervised, pixel based vs. object based, hard vs. fuzzy classification techniques. |
| Week 2: |
Principles of conventional supervised classification methods. Nearest neighbor classifier, Mahalanobis distance classifier, Maximum likelihood classifier. |
| Week 3: |
Application of conventional supervised classification methods. Classification of a sample image using digital image processing software. |
| Week 4: |
Classification using artificial neural networks. Multi-layer perceptron, recurrent networks, learning vector quantization (LVQ), Hopfield Networks, Self Organizing Maps (SOM). |
| Week 5: |
Application of neural networks for a sample satellite image. In the application multi-layer perceptron with backpropagation learning algorithm will be applied. |
| Week 6: |
Introduction to support vector machines. The working principles of support vector machines for linear and non-linear cases. |
| Week 7: |
Mid term exam |
| Week 8: |
Importance of kernel functions in support vector machines. The most widely used kernel functions. Determination of optimum parameters of kernel functions. |
| Week 9: |
Image classification using support vector machines: an application. |
| Week 10: |
Basic principles of image classification using decision trees. Top-down and bottom-up strategies. Feature selection in decision trees. Gini index and Towing rule. |
| Week 11: |
Image classification using decision trees. An application will be conducted. |
| Week 12: |
Ensemble learning algorithms. The use of boosting, bagging, random forest, rotation forest, Decorate etc. in decision trees. |
| Week 13: |
Performance analysis of ensemble learning methods using sample imagery. |
| Week 14: |
Principles of object based image classification. Multi-resolution segmentation. Application of object-based image classification using very high resolution and hyperspectral imagery. |
| Week 15*: |
. |
| Week 16*: |
Final exam. |
| Textbooks and materials: |
|
| Recommended readings: |
Mather, PM, Tso, B., 2009, Classification Methods for Remotely Sensed Data, CRC Press.
Camps-Vallsy, G., Bruzzone, L 2009, Kernel Methods for Remote Sensing Data Analysis, John Wiley & Sons.
Blashke, T., Lang, S. Hay, G.J., 2008, Object-Based Image Analysis: Spatial Concepts for Knowledge-Driven Remote Sensing Applications (Lecture Notes in Geoinformation and Cartography), Springer. |
|
|
* Between 15th and 16th weeks is there a free week for students to prepare for final exam.
|
|
