PROJECT TITLE :
Optimizing Panchromatic Image Change Detection Based on Change Index Multiband Image Analysis
This work proposes an optimization of a semisupervised Amendment Detection methodology primarily based on a mix of Amendment Indices (CI) derived from a picture multitemporal data set. For this purpose, SPOT five Panchromatic images with 2.five m spatial resolution have been used, from that three Change Indices have been calculated. Two of them are usually known indices; however the third one has been derived considering the Kullbak-Leibler divergence. Then, these 3 indices have been combined forming a multiband image that has been utilized in as input for a Support Vector Machine (SVM) classifier where four totally different discriminant functions have been tested so as to differentiate between amendment and no_amendment categories. The performance of the urged procedure has been assessed applying completely different quality measures, reaching in each case highly satisfactory values. These results have demonstrated that the simultaneous combination of basic amendment indices with others more sophisticated just like the Kullback-Leibler distance, and the applying of non-parametric discriminant functions like those workers in the SVM technique, allows solving efficiently a change detection problem.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here