Hyperspectral data analysis with nonlinear unmixing algorithms – HYPANEMA

In a supervised mode, which means that the ground truth is available, identification of endmembers can be performed empirically by an operator. In particular, for terrestrial hyperspectral imaging, it is sufficient to define some regions in the image where the presence of these materials is proven. Unmixing is then limited to the inversion step, which leads to the spatial distribution of endmembers with their local abundance. Unfortunately, such a ground truth is not available within the context of astronomical hyperspectral imaging. In this unsupervised case, the analysis of hyperspectral images consists both of identifying endmember spectra and estimating their local abundance fraction from a single image. Like most blind estimation problems, without further assumptions, unsupervised unmixing may not have unique solution. Exploiting constraints inherent in the physical modeling of collected data can then reduce the class of admissible solutions, or even completely eliminate uncertainties. A special case is when the spectrum of an endmember is known, even partially. Unmixing can then consist of extracting this single source.

The literature gives clear evidence that significant progress can be made by using nonlinear models for hyperspectral data unmixing. Despite some methodological difficulties in attempting to analyze and implement them, they would be more likely to reflect the complexity of the underlying physical phenomena. In developing such models for ensuring better fit, taking both spatial and spectral information into account appears very promising. The proposed project aims to develop methods for hyperspectral unmixing based on statistical machine learning framework and Bayesian inference. This class of tools is broad and includes formalisms and algorithms that seem to be particularly appropriate.

The sciences of observation generally contribute to the development of advanced technological equipments. Number of major equipments in the field of the Sciences for the Universe already offer large-field spectrographs, often coupled with an adaptive optics system. This technique should continue to grow with, in the next few years, the deployment of imaging spectrometer MUSE that will equip the VLT. The airborne hyperspectral imagers, or on board of satellites, and dedicated to Earth observation also provide more and more resolved images. Missions are underway or planned by various space agencies: Proba (ESA 2011), EnMAP (Germany, 2014), Prisma (Italy, 2013), HyspIRI (USA, 2013), etc. This technology, with its ability to provide extremely detailed information about the spectral properties of the observed scene, offers numerous opportunities for detection and identification in both civilian and military domains of application.

The development of original algorithms whose functionality and performance are consistent with the high resolution of hyperspectral devices is an issue with high added value. Whatever the application, one of the major problems in analysis and processing of hyperspectral images is that it is extremely difficult to extract relevant information from the mass of generated data. It is therefore necessary to propose to the experimenter, a set of specific tools that can facilitate the work of interpretation regardless of the number of frequency bands of observation.

Processing large hyperspectral cubes is a big data challenge. Thus, skills developed within the context of the HYPANEMA should be easily exploited in other big-data applications, such as radio interferometry with LOFAR and SKA instruments.

Scientific results of the project are published in international journals of reference such as:
IEEE Signal Processing Magazine
IEEE Transactions onSignal Processing
IEEE Transactions on Geoscience and Remote Sensing
IEEE Transactions on Image Processing

In addition, the team is involved in the organization of conferences and workshops such as:

MAHI workshop : Methodological aspects of hyperspectral imaging (2012, 2013)
www-n.oca.eu/aferrari/MAHI/index.html

IEEE WHISPERS : Workshop on hyperspectral image and signal processing - Eolution in remote sensing (2012, 2013, ...)
www.ieee-whispers.com

The Hypanema project belongs to the wide framework dealing with exploitation of large-scale data coming from hyperspectral imagery. This research field has emerged as an important and rapidly growing area of interest within the remote sensing area, for both civil and military applications. Among the open questions, data cube segmentation, which aims to identifying the objects of interest, is one of the crucial issues and still a technological barrier. The natural overlapping of areas of interest in the image leads one to address the problem of spectral unmixing, which consists of estimating the number of reference materials, their spectral signatures and their relative mixing contributions. The Hypanema project proposes to formulate this problem as a blind separation problem of spectral sources, which are statistically dependent and non-linearly mixed. The underlying non-linear mixing process, combined with the high dimensionality of the data, relegates this problem out of the scope of most of the BSS algorithms of the literature. Moreover, very few existing approaches combine spectral and spatial information, although this ambivalence is a relevant a priori knowledge that should be exploited. The team, which is internationally recognized for expertise in signal processing, intends to fill this gap by developping a new class of models and the corresponding identification methods within two directions : the statistical learning approach and the Bayesian inference. Two major and complementary applications with high added value will be handled: astronomy and remote sensing. The team will interact with french and european agencies to define application-specific requirements, and to validate the proposed models and the identification methods. The Hypanema project plans to disseminate the results of research via publications, a structured software product, and the organization of special sessions in international conferences. Finally, part of the research material will be used for teaching graduate courses.