Remote sensing is nowadays of paramount importance for
several application fields, including environmental
monitoring, urban planning, ecosystem-oriented natural
resources management, urban change detection and
agricultural region monitoring. Majority of the
aforementioned monitoring and detection applications
requires at some stage a label map of the remotely sensed
images, where individual pixels are marked as members of
specific classes, e.g. water, asphalt, grass, etc. In
other words, classification is a crucial step for several
remote sensing applications. It is widely acknowledged
that exploiting both the spectral as well as spatial
properties of pixels, improves classification performance
with respect to using only spectral based features.In this regard, morphological profiles (MP) are one of
the popular and powerful image analysis techniques that
enable us to compute such spectral-spatial pixel
descriptions. They have been studied extensively in the
last decade and their effectiveness has been validated
repeatedly.
The characterization of spatial information obtained by
the application of a MP is particularly suitable for
representing the multi-scale variations of image
structures, but they are limited by the shape of the
structuring elements. To avoid this limitation,
morphological attribute profiles (AP) have been
developed. By operating directly on connected components
instead of pixels, not only we are able to employ
arbitrary region descriptors (e.g. shape, color, texture,
etc) but it paves the way for object based image analysis
as well. In addition, APs can be implemented efficiently
by means of hierarchical image representations, e.g.
Max-/Min-tree and alpha-tree.
The aforementioned proposed techniques for hyper-spectral
remote sensing image analysis are basically based on
marginal processing of the image, i.e. analyzing each
spectral channel individually and not simultaneously.
Therefore, the channels’ correlation is neglected in the
conventional marginal approaches.
Motivated from that, our project focuses on extending the
mathematical morphology to the field of hyper-spectral
image processing and applying morphological content based
operators, e.g. MP and AP, on all of the spectral bands
simultaneously rather than marginally in order to take
the spectral channels’ correlation into account.