| INVESTIGATING THE IMPACT OF ENDMEMBER EXTRACTION METHODS ON MULTIPLE CHANGE DETECTION |
| Paper ID : 1136-SMPR |
| Authors: |
|
Hamid Jafarzadeh *, Mahdi Hasanlou School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, Iran |
| Abstract: |
| Endmember extraction is a process to identify the hidden pure source signals from the mixture. Endmember finding has become increasingly important in hyperspectral data exploitation because endmembers can be used to specify unknown particular spectral classes. This paper evaluates the change detection problem in multi-temporal hyperspectral remote sensing images using the unmixing process. Endmember extraction is a vital step in spectral unmixing of hyperspectral images. Hyperspectral change detection by unmixing has the potential to provide subpixel information from hyperspectral images. Four methods including Simplex Identification via variable Splitting and Augmented Lagrangian (SISAL), N-finder algorithm (N-FINDR), Vertex Component Analysis (VCA), and Fast algorithm for linearly Unmixing (FUN) are used to produce multiple change detection maps. This paper explores the impact of these methods on the output of multiple change detection. The empirical results reveal the superiority of the FUN method in providing multiple change map with an overall accuracy of 87% and a kappa coefficient of 0.70. |
| Keywords: |
| Change Detection, Hyperspectral Images, Unmixing, Endmember, Remote Sensing |
| Status : Conditional Accept (Oral Presentation) |
