TY - JOUR

T1 - An iterative search in end-member fraction space for spectral unmixing

AU - Shoshany, Maxim

AU - Kizel, Fadi

AU - Netanyahu, Nathan S.

AU - Goldshlager, Naftali

AU - Jarmer, Thomas

AU - Even-Tzur, Gilad

PY - 2011/7

Y1 - 2011/7

N2 - A novel unmixing methodology is presented, searching for a fraction combination of end-members (EMs) that reconstructs the integrated source signal. The search starts with computing an initially estimated unmixing solution and then assesses combinations selected at random within an envelope surrounding this estimated solution. From each of these combinations, it then progresses iteratively along a path of neighboring combinations, so as to minimize the spectral angle between the corresponding (integrated) signatures and the source signal, until reaching a satisfactory solution. The new iterative fraction combination search (IFCS) was compared to the standard least squares unmixing (LSU). An assessment of both methods was conducted with a real Airborne Visible/Infrared Imaging Spectrometer image and nine synthetic images generated by randomly selecting fractions for two up to ten EMs derived from this real image. Considering all these EMs for the unmixing solution (not knowing specifically which or how many of them are actually mixed at each pixel), the IFCS method performed considerably better than LSU.

AB - A novel unmixing methodology is presented, searching for a fraction combination of end-members (EMs) that reconstructs the integrated source signal. The search starts with computing an initially estimated unmixing solution and then assesses combinations selected at random within an envelope surrounding this estimated solution. From each of these combinations, it then progresses iteratively along a path of neighboring combinations, so as to minimize the spectral angle between the corresponding (integrated) signatures and the source signal, until reaching a satisfactory solution. The new iterative fraction combination search (IFCS) was compared to the standard least squares unmixing (LSU). An assessment of both methods was conducted with a real Airborne Visible/Infrared Imaging Spectrometer image and nine synthetic images generated by randomly selecting fractions for two up to ten EMs derived from this real image. Considering all these EMs for the unmixing solution (not knowing specifically which or how many of them are actually mixed at each pixel), the IFCS method performed considerably better than LSU.

KW - Hyperspectral imagery

KW - unmixing

UR - http://www.scopus.com/inward/record.url?scp=79959742180&partnerID=8YFLogxK

U2 - 10.1109/lgrs.2010.2101578

DO - 10.1109/lgrs.2010.2101578

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:79959742180

SN - 1545-598X

VL - 8

SP - 706

EP - 709

JO - IEEE Geoscience and Remote Sensing Letters

JF - IEEE Geoscience and Remote Sensing Letters

IS - 4

M1 - 5710030

ER -