AmirAbbas Davari
Dr.-Ing. AmirAbbas Davari
Department of Computer Science
Chair of Computer Science 5 (Pattern Recognition)
Martensstr. 3
91058 Erlangen
- Phone number: +49 9131 85-27882
- Fax number: +49 9131 85-27270
- Email: amir.davari@fau.de
- Website: https://lme.tf.fau.de/person/davari/
[researchgate=”LINK” scholar=”LINK“]
Projects
2016
-
Development of Vector-Based Mathematical Morphology for Hyper-spectral Remote Sensing Image Description and Classification
(Non-FAU Project)
Term: since March 1, 2016Remote 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.
Publications
2023
Journal Articles
- , , , , :
Bayesian Convolutional Neural Networks for Limited Data Hyperspectral Remote Sensing Image Classification
In: IEEE Geoscience and Remote Sensing Letters 20 (2023), Article No.: 5506305
ISSN: 1545-598X
DOI: 10.1109/LGRS.2023.3287504
BibTeX: Download
2022
Journal Articles
- , , , , , :
How to Get the Most Out of U-Net for Glacier Calving Front Segmentation
In: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (2022)
ISSN: 1939-1404
DOI: 10.1109/JSTARS.2022.3148033
BibTeX: Download - , , , , , :
Pixel-wise Distance Regression for Glacier Calving Front Detection and Segmentation
In: IEEE Transactions on Geoscience and Remote Sensing 60 (2022), p. 1-10
ISSN: 0196-2892
DOI: 10.1109/TGRS.2022.3158591
URL: https://arxiv.org/pdf/2103.05715
BibTeX: Download
Thesis
- :
Hyperspectral Image Analysis using Limited Data (Dissertation, 2022)
URL: https://opus4.kobv.de/opus4-fau/frontdoor/index/index/docId/18583
BibTeX: Download
2021
Journal Articles
- , , , , , , :
On Mathews Correlation Coefficient and Improved Distance Map Loss for Automatic Glacier Calving Front Segmentation in SAR Imagery
In: IEEE Transactions on Geoscience and Remote Sensing (2021), p. 1-12
ISSN: 0196-2892
DOI: 10.1109/TGRS.2021.3115883
URL: https://arxiv.org/abs/2102.08312
BibTeX: Download
Conference Contributions
- , , , , , :
Bayesian U-Net for Segmenting Glaciers in Sar Imagery
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS (Brussels, July 11, 2021 - July 16, 2021)
DOI: 10.1109/IGARSS47720.2021.9554292
URL: https://arxiv.org/abs/2101.03249
BibTeX: Download - , , , , , :
Glacier Calving Front Segmentation Using Attention U-Net
2021 IEEE International Symposium on Geoscience and Remote Sensing (IGARSS) (Brussels, July 11, 2021 - July 16, 2021)
DOI: 10.1109/IGARSS47720.2021.9555067
URL: https://arxiv.org/abs/2101.03247
BibTeX: Download - , , , , , , :
Synthetic Glacier SAR Image Generation from Arbitrary Masks Using Pix2Pix Algorithm
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS (Brussels, July 11, 2021 - July 16, 2021)
DOI: 10.1109/IGARSS47720.2021.9553853
URL: https://arxiv.org/abs/2101.03252
BibTeX: Download - , , , , , :
Tapping the Potential of Earth Observation - Calving Front Detection in SAR Images using Deep Learning Techniques
EGU General Assembly 2021 (, April 19, 2021 - May 30, 2021)
DOI: 10.5194/egusphere-egu21-11280
BibTeX: Download
2019
Journal Articles
- , , , :
Fast and Efficient Limited Data Hyperspectral Remote Sensing Image Classification via GMM-Based Synthetic Samples
In: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 12 (2019), p. 2107-2120
ISSN: 1939-1404
DOI: 10.1109/JSTARS.2019.2916495
URL: https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2019/Davari_JSTARS_2019.pdf
BibTeX: Download
2018
Journal Articles
- , , , , :
GMM-based Synthetic Samples for Classification of Hyperspectral Images with Limited Training Data
In: IEEE Geoscience and Remote Sensing Letters 15 (2018), p. 942-946
ISSN: 1545-598X
DOI: 10.1109/LGRS.2018.2817361
URL: https://arxiv.org/pdf/1712.04778.pdf
BibTeX: Download
Conference Contributions
- , , , :
Fast Sample Generation with Variational Bayesian for Limited Data Hyperspectral Image Classification
IEEE International Geoscience and Remote Sensing Symposium (Valencia, July 22, 2018 - July 27, 2018)
In: IEEE International Geoscience and Remote Sensing Symposium 2018
DOI: 10.1109/IGARSS.2018.8517643
URL: https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Davari18-FSG.pdf
BibTeX: Download - , , , , :
Classification of Breast Cancer Histology Images Using Transfer Learning
International Conference Image Analysis and Recognition (, June 12, 2018)
In: ICIAR 2018: Image Analysis and Recognition 2018
DOI: 10.1007/978-3-319-93000-8_92
BibTeX: Download - , , , , , , :
Hyper-Hue and EMAP on Hyperspectral Images for Supervised Layer Decomposition of Old Master Drawings
International Conference on Image Processing (ICIP) (Athens, Greece, October 7, 2018 - October 10, 2018)
In: International Conference on Image Processing (ICIP) 2018
DOI: 10.1109/ICIP.2018.8451768
URL: http://arxiv.org/abs/1801.09472
BibTeX: Download
(Techreport)
2017
Conference Contributions
- , , , , :
GMM Supervectors for Limited Training Data in Hyperspectral Remote Sensing Image Classification
17th International Conference on Computer Analysis of Images and Patterns (Ystad, August 22, 2017 - August 24, 2017)
In: Proceedings of the 17th International Conference on Computer Analysis of Images and Patterns Part II 2017
DOI: 10.1007/978-3-319-64698-5_25
BibTeX: Download - , , , , , :
Semi-Automatic Algorithm for Breast MRI Lesion Segmentation Using Marker-Controlled Watershed Transformation
IEEE Nuclear Science Symposium and Medical Imaging Conference Record (NSS/MIC) (Atlanta, Georgia, USA)
In: 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference Record (NSS/MIC) 2017
URL: https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Vesal17-SAF.pdf
BibTeX: Download - , , :
Sketch Layer Separation in Multi-Spectral Historical Document Images
International Symposium on Digital Humanities
In: International Symposium on Digital Humanities: Book of Abstracts 2017
Open Access: https://journals.lnu.se/index.php/isdh/article/download/431/378
URL: https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Davari17-IDHS-TR.pdf
BibTeX: Download
Miscellaneous
- , , , , , :
Image Registration for the Alignment of Digitized Historical Documents
abs/1712.04482 (2017)
Open Access: https://arxiv.org/abs/1712.04482
URL: http://arxiv.org/abs/1712.04482
BibTeX: Download
(Techreport)