In remote sensed images, mixed pixels will always be present. Sub-pixel mapping is a technique to farther make
sure the spatial distribution of all classes. The present sub-pixel mapping techniques always have a limit to the accuracy
since they are based only on the soft-classified proportion data at the pixel level. In fact, supplementary information at
the sub-pixel level can be used to enhance precision. In this paper, a proposed method aims to use fused imagery as
supplementary information sources for the traditional sub-pixel mapping model development. The fused image with high
resolution is obtained using a Gram-Schmidt spectral sharpening method, then new abundance images can replace the
original data and provide more details through the Linear Mixing Model (LMM) and Fully Constrained Least Squares
(FCLS) method, finally the prepared data are incorporated in a Fuzzy ARTMAP neural network. The completed
algorithm is tested on a synthetic SPOT5 MS image, PAN image should be taken as a reference image. The result
suggested that fine spatial resolution fused imagery can be used as a supplementary data for sub-pixel mapping, and it
can get better performance than directly ANN method.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.