Séminaire : Hierarchical analysis of hyperspectral images

Jocelyn Chanussot, professeur de traitement du signal et de l'image au GIPSA-Lab,  fera une présentation de ses travaux de recherche le lundi 30 juin 2014 à 14h30 dans la salle C218 au Pôle API d’Illkirch.

Titre : Hierarchical analysis of hyperspectral images

Résumé : After decades of use of multispectral remote sensing, most of the major space agencies now have new programs to launch hyperspectral sensors, recording the reflectance information of each point on the ground in hundreds of narrow and contiguous spectral bands. The spectral information is instrumental for the accurate analysis of the physical component present in one scene. But, every rose has its thorns: most of the traditional signal and image processing algorithms fail when confronted to such high dimensional data (each pixel is represented by a vector with several hundereds of dimensions). In this talk, we will start by a general presentation of the challenges and opportunities offered by hyperspectral imaging systems in a number of applications.We will then explore these issues with a hierarchical approach, briefly illustrating the problem of spectral unmixing and of super-resolution, then moving on to pixel-wise classification (purely spectral classification and then including contextual features). Eventually, we will focus on the extension to hyperspectral data of a very powerful image processing analysis tool: the Binary Partition Tree (BPT). It provides a generic hierarchical representation of images and consists of the two following steps: - construction of the tree : one starts from the pixel level and merge pixels/regions progressively until the top of the hierarchy (the whole image is considered as one single region) is reached. To proceed, one needs to define a model to represent the regions (for instance: the average spectrum - but this is not a good idea) and one also needs to define a similarity measure between neighbouring regions to decide which ones should be merged first (for instance the euclidean distance between the model of each region - but this is not a good idea either). This step (construction of the tree) is very much related to the data. - the second step is the pruning of the tree: this is very much related to the considered application. The pruning of the tree leads to one segmentation. The resulting segmentation might not be any of the result obtained during the iterative construction of the tree. This is where this representation outperforms the standard approaches. But one may also perform classification, or objet detection (assuming an object of interest will appear somewhere as one noode of the tree, the game is to define a suitable criterion, related to the application, to find this node). Results are presented on various hyperspectral images.