|
Development of Vector-Based Mathematical Morphology for Hyper-spectral Remote Sensing Image Description and ClassificationRemote 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. | Project manager: PD Dr.-Ing. Christian Riess
Project participants: AmirAbbas Davari, M. Sc.
Keywords: Remote Sensing; Hyper-Spectral Image; Mathematical Morphology; Content-based Image Processing Operator; Attribute Profile
Duration: 1.3.2016 - 30.9.2019
Sponsored by: Erlangen Graduate School of Heterogeneous Image Systems (Research Training Group 1773)
Contact: Davari, AmirAbbas Phone +49 9131 85 27882, Fax +49 9131 85 27270, E-Mail: amir.davari@fau.de
| Publications |
---|
Davari, AmirAbbas ; Aptoula, Erchan ; Yanikoglu, Berrin ; ; Riess, Christian: GMM-Based Synthetic Samples for Classification of Hyperspectral Images With Limited Training Data. In: IEEE Geoscience and Remote Sensing Letters 15 (2018), No. 6, pp 942-946 [doi>10.1109/LGRS.2018.2817361] | Davari, AmirAbbas ; Christlein, Vincent ; Vesal, Sulaiman ; ; Riess, Christian: GMM Supervectors for Limited Training Data in Hyperspectral Remote Sensing Image Classification. In: Felsberg, Michael (Ed.) : Computer Analysis of Images and Patterns (17th international Conference on Computer Analysis of Images and Patterns (CAIP) Ystad, Sweden 22-24.8.2017). Vol. 2. 2017, pp 296-306. | Davari, AmirAbbas ; Aptoula, Erchan ; Yanikoglu, Berrin: On the effect of synthetic morphological feature vectors on hyperspectral image classification performance. In: IEEE (Ed.) : Signal Processing and Communications Applications Conference (SIU), 2015 23th (23th Signal Processing and Communications Applications Conference (SIU) Malatya, Turkey 2015). 2015, pp 653-656. | Davari, AmirAbbas ; Oezkan, Hasan Can ; ; Riess, Christian: Fast Sample Generation with Variational Bayesian for Limited Data Hyperspectral Image Classification. In: IEEE (Ed.) : International Geoscience and Remote Sensing Symposium (IGARSS) (International Geoscience and Remote Sensing Symposium (IGARSS) Valencia, Spain 22-27.07). 2018, pp tbd. |
Institution: Chair of Computer Science 5 (Pattern Recognition)
|
|
|