Guillaume Tochon

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

The binary partition tree (BPT) is a hierarchical region-based representation of an image in a tree structure. The BPT allows users to explore the image at different segmentation scales. Often, the tree is pruned to get a more compact representation and so the remaining nodes conform an optimal partition for some given task. Here, we propose a novel BPT construction approach and pruning strategy for hyperspectral images based on spectral unmixing concepts. Linear spectral unmixing consists of finding the spectral signatures of the materials present in the image (endmembers) and their fractional abundances within each pixel. The proposed methodology exploits the local unmixing of the regions to find the partition achieving a global minimum reconstruction error. Results are presented on real hyperspectral data sets with different contexts and resolutions.

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 as a hyperspectral segmentation tool for tropical rainforests

Individual tree crown delineation in tropical forests is of great interest for ecological applications. In this paper we propose a method for hyperspectral image segmentation based on binary tree partitioning. The initial partition is obtained from a watershed transformation in order to make the method computationally more efficient. Then we use a non-parametric region model based on histograms to characterize the regions and the diffusion distance to define the region merging order. The pruning strategy is based on the discontinuity of size increment observed when iteratively merging the regions. The segmentation quality is assessed visually and appears to perform well on most cases, but tree delineation could be improved by including structural information derived from LiDAR data.

Hyperspectral Local Intrinsic Dimensionality

The intrinsic dimensionality (ID) of multivariate data is a very important concept in spectral unmixing of hyperspectral images. A good estimation of the ID is crucial for a correct retrieval of the number of endmembers (the spectral signatures of macroscopic materials) in the image, for dimensionality reduction or for subspace learning, among others. Recently, some approaches to perform spectral unmixing and superresolution locally have been proposed, which require a local estimation of the number of endmembers to use. However, the role of ID in local regions of hyperspectral images has not been properly addressed. Some important issues when dealing with small regions of hyperspectral data can seriously affect the performance of conventional hyperspectral ID estimators. We show that three factors mainly affect local ID estimation: the number of pixels in the local regions, which has to be high enough for the estimations to be relevant, the number of hyperspectral bands which complicates the estimations if the ambient space has a high dimensionality, and the noise, which can be misinterpreted as a signal when its power is important. Here, we review the hyperspectral ID estimators on the literature for local ID estimation, we show how they behave in a local setting on synthetic and real data sets, and we provide some guidelines to make proper use of these estimators in local approaches.

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.

Binary Partition Trees-based spectral-spatial permutation ordering

Mathematical Morphology (MM) is founded on the mathematical branch of Lattice Theory. Morphological operations can be described as mappings between complete lattices, and complete lattices are a type of partially-ordered sets (poset). Thus, the most elementary requirement to define morphological operators on a data domain is to establish an ordering of the data. MM has been very successful defining image operators and filters for binary and gray-scale images, where it can take advantage of the natural ordering of the sets \(\left\lbrace 0,1 \right\rbrace\) and ℝ. For multivariate data, i.e. RGB or hyperspectral images, there is no natural ordering. Thus, other orderings such as reduced orderings (R-orderings) have been proposed. Anyway, all these orderings are based solely on sorting the spectral set of values. Here, we propose to define an ordering based on both, the spectral and the spatial information, by means of a binary partition tree (BPT) representation of images. The proposed ordering aims to find a permutation of the pixel indexes, that is, a sorting of the pixels arrangement in the data matrix. Morphological operations using the proposed ordering are able to enlarge (shrink) spatial structures independently of their spectral values, as far as the spatial structures are encoded in the BPT representation. We provide examples of potential use of the proposed ordering using binary and RGB images.

Object Tracking by Hierarchical Decomposition of Hyperspectral Video Sequences: Application to Chemical Gas Plume Tracking

It is now possible to collect hyperspectral video sequences at a near real-time frame rate. The wealth of spectral, spatial, and temporal information of those sequences is appealing for various applications, but classical video processing techniques must be adapted to handle the high dimensionality and huge size of the data to process. In this paper, we introduce a novel method based on the hierarchical analysis of hyperspectral video sequences to perform object tracking. This latter operation is tackled as a sequential object detection process, conducted on the hierarchical representation of the hyperspectral video frames. We apply the proposed methodology to the chemical gas plume tracking scenario and compare its performances with state-of-the-art methods, for two real hyperspectral video sequences, and show that the proposed approach performs at least equally well.

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.