报告题目1：Deep Auto-Encoder Network for Hyperspectral Image Unmixing
报告人单位：University of Extremadura
Prof. Antonio Plaza is the Head of the Hyperspectral Computing Laboratory at the Department of Technology of Computers and Communications, University of Extremadura. His main research interests comprise hyperspectral data processing and parallel computing. He has authored more than 600 publications, including 245 JCR journal papers (more than 160 in IEEE journals). Prof. Plaza is a Fellow of IEEE. He is a recipient of the Best Column Award of the IEEE Signal Processing Magazine in 2015, the 2013 Best Paper Award of the JSTARS journal, and the most highly cited paper (2005-2010) in the Journal of Parallel and Distributed Computing. He served as the Editor-in-Chief of the IEEE TGRS journal for five years (2013-2017). He is included in 2018 Highly Cited Researchers List (Clarivate Analytics).
Spectral unmixing is a technique for image interpretation that expresses each (possibly mixed) pixel as a combination of pure spectral signatures (endmembers) and their fractional abundances. In this presentation, we describe a new technique for unsupervised unmixing which is based on a deep autoencoder network (DAEN). Our newly developed DAEN consists of two parts. The first part of the network adopts stacked autoencoders (SAEs) to learn spectral signatures, so as to generate a good initialization for the unmixing process. In the second part of the network, a variational autoencoder (VAE) is employed to perform blind source separation, aimed at obtaining the endmember signatures and abundance fractions simultaneously. By taking advantage from the SAEs, the robustness of the proposed approach is remarkable as it can unmix data sets with outliers and low signal-to-noise ratio. Moreover, the multihidden layers of the VAE ensure the required constraints (nonnegativity and sum-to-one) when estimating the abundances. The effectiveness of the proposed method is evaluated using both synthetic and real hyperspectral data. When compared with other unmixing methods, the proposed approach demonstrates very competitive performance.
报告题目2：3-D Gabor Filtering and its Application on Hyperspectral Image Classification
李军，教授、博导、青千。2007年毕业于北京大学，获硕士学位；2011年于葡萄牙里斯本技术大学获得博士学位；2011-2013于西班牙埃斯特雷马杜拉大学从事博士后研究。发表SCI论文50多篇、8篇被收录为ESI高被引论文（1篇连续5年高被引），主要成果发表在Proceedings of the IEEE等刊物上。李军博士为现任IEEE JSTARS的副编辑（Associate Editor），Proceedings of the IEEE 特邀编辑(Guest Editor)。
In this talk, we will present our recent developments on 3-D Gabor filtering. First of all, a fast discriminative low-rank Gabor filtering, which is able to decompose the standard 3-D spectral-spatial Gabor filter into eight subfilters. Aiming at preserving the structure/textural information, a variation including the range information will furthermore be presented. Finally, a naive Gabor network will be introduced. Applications on hyperspectral classification evaluates the effectiveness of the proposed developments.
邀请人：杜博 教授、张乐飞 教授