M. Dalla Mura

A new extended linear mixing model to address spectral variability

Spectral variability is a phenomenon due, to a grand extend, to variations in the illumination and atmospheric conditions within a hyperspectral image, causing the spectral signature of a material to vary within a image. Data spectral fluctuation due to spectral variability compromises the linear mixing model (LMM) sum-to-one constraint, and is an important source of error in hyperspectral image analysis. Recently, spectral variability has raised more attention and some techniques have been proposed to address this issue, i.e. spectral bundles. Here, we propose the definition of an extended LMM (ELMM) to model spectral variability and we show that the use of spectral bundles models the ELMM implicitly. We also show that the constrained least squares (CLS) is an explicit modelling of the ELMM when the spectral variability is due to scaling effects. We give experimental validation that spectral bundles (and sparsity) and CLS are complementary techniques addressing spectral variability. We finally discuss on future research avenues to fully exploit the proposed ELMM.

Hyperspectral image segmentation using a new spectral mixture-based binary partition tree representation

The Binary Partition Tree (BPT) is a hierarchical region-based representation of an image in a tree structure. BPT allows users to explore the image at different segmentation scales, from fine partitions close to the leaves to coarser partitions close to the root. Often, the tree is pruned so the leaves of the resulting pruned tree conform an optimal partition given some optimality criterion. Here, we propose a novel BPT construction approach and pruning strategy for hyperspectral images based on spectral unmixing concepts. The proposed methodology exploits the local unmixing of the regions to find the partition achieving a global minimum reconstruction error. We successfully tested the proposed approach on the well-known Cuprite hyperspectral image collected by NASA Jet Propulsion Laboratorys Airborne Visible/Infrared Imaging Spectrometer (AVIRIS). This scene is considered as a standard benchmark to validate spectral unmixing algorithms.

Gas plume detection and tracking in hyperspectral video sequences using Binary Partition Trees

Thanks to the fast development of sensors, it is now possible to acquire sequences of hyperspectral images. Those hyperspectral video sequences are particularly suited for the detection and tracking of chemical gas plumes. However, the processing of this new type of video sequences with the additional spectral diversity, is challenging and requires the design of advanced image processing algorithms. In this paper, we present a novel method for the segmentation and tracking of a chemical gas plume diffusing in the atmosphere, recorded in a hyperspectral video sequence. In the proposed framework, the position of the plume is first estimated, using the temporal redundancy of two consecutive frames. Second, a Binary Partition Tree is built and pruned according to the previous estimate, in order to retrieve the real location and extent of the plume in the frame. The proposed method is validated on a real hyperspectral video sequence and compared with a state-of-the-art method.

Binary partition tree-based local spectral unmixing

The linear mixing model (LMM) is a widely used methodology for the spectral unmixing (SU) of hyperspectral data. In this model, hyperspectral data is formed as a linear combination of spectral signatures corresponding to macroscopically pure materials (endmembers), weighted by their fractional abundances. Some of the drawbacks of the LMM are the presence of multiple mixtures and the spectral variability of the endmembers due to illumination and atmospheric effects. These issues appear as variations of the spectral conditions of the image along its spatial domain. However, these effects are not so severe locally and could be at least mitigated by working in smaller regions of the image. The proposed local SU works over a partition of the image, performing the spectral unmixing locally in each region of the partition. In this work, we first introduce the general local SU methodology, then we propose an implementation of the local SU based on a binary partition tree representation of the hyperspectral image and finally we give an experimental validation of the approach using real data.

Analysis of Multitemporal Classification Techniques for Forecasting Image Time Series

The classification of an annual time series by using data from past years is investigated in this letter. Several classification schemes based on data fusion, sparse learning, and semisupervised learning are proposed to address the problem. Numerical experiments are performed on a Moderate Resolution Imaging Spectroradiometer image time series and show that while several approaches have statistically equivalent performances, a support vector machine with I1 regularization leads to a better interpretation of the results due to their inherent sparsity in the temporal domain.

Thermal sharpening of VIIRS data

Thermal Sharpening (TS) is usually referred to techniques widely used in several Earth Observation applications in order to increase the spatial resolution of thermal images. Profiting from the particular design of the Visible Infrared Imaging Radiometer Suite (VIIRS) sensor mounted on board of the Suomi National Polar-orbiting Partnership (NPP) satellite, we propose here a new approach for obtaining synthetic thermal data with increased spatial resolution and spectral diversity. The method exploits classical Pansharpening algorithms, which are very popular in the field of Visible and Near-InfraRed (VNIR) image fusion, for combining the VIIRS thermal bands with partially overlapping spectral responses. We evaluate the effectiveness of several algorithms by performing a Reduced Resolution (RR) assessment on VIIRS real data, showing the importance of an adequate knowledge of the sensor characteristics.

Multispectral and hyperspectral data fusion based on SAM minimization band assignment approach

The sharpening of hyperspectral (HS) images introduces novel questions that have never been faced by classical pansharpening, which deals with the fusion of multispectral and panchromatic images. In this paper, we focus on the fusion of high resolution MultiSpectral (MS) and low resolution HS data, namely tackling the problem of assigning the optimal MS channel for each HS band through the minimization of the Spectral Angle Mapper (SAM) metric. The performance is assessed on two datasets, both composed by a HS and a MS image acquired by the Hyperion and the ALI sensors, respectively. Several MultiResolution Analysis pansharpening approaches are used for evaluating the performance improvements with respect to existing methods.

From local to global unmixing of hyperspectral images to reveal spectral variability

The linear mixing model is widely assumed when unmixing hyperspectral images, but it cannot account for endmembers spectral variability. Thus, several workarounds have arisen in the hyperspectral unmixing literature, such as the extended linear mixing model (ELMM), which authorizes endmembers to vary pixelwise according to scaling factors, or local spectral unmixing (LSU) where the unmixing process is conducted locally within the image. In the latter case however, results are difficult to interpret at the whole image scale. In this work, we propose to analyze the local results of LSU within the ELMM framework, and show that it not only allows to reconstruct global endmembers and fractional abundances from the local ones, but it also gives access to the scaling factors advocated by the ELMM. Results obtained on a real hyperspectral image confirm the soundness of the proposed methodology.

Hyperspectral pansharpening using convex optimization and collaborative total variation regularization

Hyperspectral pansharpening is a challenging research area and several methods have been recently developed to fuse low resolution hyperspectral and high resolution panchromatic images. In this paper we focus on a recent regularization method, called Collaborative Total Variation, exploiting a convex optimization algorithm. We evaluate the effectiveness of this novel approach in comparison to existing methods, and assess the performances on two datasets: a synthetic scene mimicking the characteristics of the Hyperion and ALI sensors and the Pavia University dataset.

Using time series to improve endmembers estimation on multispectral images for snow monitoring

We propose to use the temporal coherence of a time series to extract using Vertex Component Analysis (VCA) the suitable set of endmembers for each scene. The reconstruction error computed on the two previous scenes for each date is used to constrain the selection of the set of endmembers produced by VCA. Snow cover estimation is considered as application. We tested different approaches for abundance estimation (FCLSU, SUnSAL, ELMM) over the French Alps from Moderate Resolution Imaging Spectroradiometer (MODIS) images. Results shows a decrease of the false positive rate with the proposed approach.