Laurent Guigues

Amazon · Go

The present invention relates to a method for tracking at least one object in a sequence of frames, each frame comprising a pixel array, wherein a depth value is associated to each pixel. The method comprises grouping at least some of said pixels of each frame into several regions, grouping said regions into clusters (B1, . . . , B5) of interconnec...

The paper presents a collaborative project that offers stand-alone software applications for end-users and a complete open-source platform to rapidly develop/prototype medical image processing work-flows with sophisticated visualization and user interactions. It builds on top of a flexible cross-platform framework (Linux, Windows and MacOS) develop...

Initiated at CREATIS lab, CreaTools is a collaborative project with los Andes and Javeriana universities from Colombia. It offers stand-alone applications for end users and a complete open-source platform to rapidly develop/prototype medical image processing workflows with sophisticated visualization and user interactions. It builds on top of BBTK...

The present invention relates to a computer-implemented method for tracking at least one object in a sequence of frames, each frame comprising a pixel array, wherein a depth value is associated to each pixel 5. A method according to the invention comprises the steps of grouping, in a computer memory, at least some of said pixels 5 of each frame int...

ABSTRACT: An important aspect of marine research is to quantify the areal coverage of benthic communities. It is technically feasible to efficiently obtain images of marine environments at different depths and benthic habitats over large spatial and temporal scales. Currently, there is a large and growing library of digital images to analyze, repre...

GATE (Geant4 Application for Emission Tomography) is a Monte Carlo simulation platform developed by the OpenGATE collaboration since 2001 and first publicly released in 2004. Dedicated to the modelling of planar scintigraphy, single photon emission computed tomography (SPECT) and positron emission tomography (PET) acquisitions, this platform is wid...

An important aspect of marine research is to quantify the areal coverage of benthic communities. It is technically feasible to efficiently obtain images of marine environments at different depths and benthic habitats over large spatial and temporal scales. Currently, there is a large and growing library of digital images to analyze, representing a...

This paper deals with evaluation of image segmentation methods. We start with a state-of-the art of the evaluation criteria, involving a reference segmentation or not. Based on an analysis of the main existing criteria, we propose new criteria, when no ground-truth is available. These criteria, based on an energetic formalism, take into account bot...

The proposed Virtual Radiological Platform (VRP) project aims at providing realistic multi-modal medical images with 'ground- truth' knowledge. It relies on medical image simulators which often represent heterogeneous and computing demanding applications dealing with large amounts of medical images. In this context, computer grids are interesting a...

We propose a new method for efficient particle transportation in voxelized geometry for Monte Carlo simulations. We describe its use for calculating dose distribution in CT images for radiation therapy. The proposed approach, based on an implicit volume representation named segmented volume, coupled with an adapted segmentation procedure and a dist...

Our group at the “Institut de Physique Nucléaire de Lyon” (IPNL) is working on physics and detectors for medical imaging. We are presently developing a small animal Positron Emission Tomograph (PET) scanner prototype with an innovative slow control and data acquisition features, for a demonstration purpose and within the crystal clear international...

This paper addresses the problem of multi-scale region-oriented image analysis. It first deals with a representational issue : how to represent all the solutions of a multi-scale partitioning algo- rithm, i.e. of an algorithm returning ordered partitions with res- pect to a one-dimensional 'scale' parameter ? To achieve this, we propose the scale-s...

This paper is dedicated to evaluation criteria for image segmentation when there is no ground truth. New criteria based on a formulation of the image segmentation as a piecewise modeling problem are proposed. These criteria take into account both the complexity of the segmented image, through the total boundary length and the goodness-of-fit throug...

Ce papier s'intéresse à la définition de nouveaux critères d'évaluation de la segmentation, dans le cas où l'on ne dispose pas de vérité-terrain. L'avantage de ces critères est de pouvoir comparer des images segmentées en fonction du niveau de détail recherché. Ces critères sont comparés aux principaux critères existants : les critères de Levine-Na...

In this paper, we present a general framework for multiscale segmentation of range images in planar facets. We propose a formulation of the problem as the minimization of a multiscale separable energy, which involves two terms: a goodness-of-fit term and a regularization term, the scale parameter being the relative weight between the two terms. We...

This paper addresses the problem of multiscale region-oriented image analysis. It first deals with a representational issue: how to represent all the solutions of a multiscale partitioning algorithm, i.e. of an algorithm returning ordered partitions with respect to a one-dimensional 'scale' parameter? To achieve this, we propose the scale-sets repr...

A set of particular subgraphs of a valued graph, called cocoons, is introduced. Within the image segmentation framework, the cocoons represent a model of contrasted regions. It is shown that the cocoons are organized into a hierarchy which is a sub-hierarchy of the one produced by the standard clustering algorithm of complete linkage. This result t...

The French cadastral map consists of over 500,000 map sheets that cover the whole territory. The raster digitisation of these paper maps is in progress. In order to exploit them, we have to assemble and geo-reference the set of maps to make them superimposable on other geographic information in a GIS. The problem can be seen as a complex jigsaw puz...

Nous proposons une méthodologie originale pour la segmentation en régions des images qui repose sur la complémentarité de deux familles d'approches : les approches hiérarchiques (ou pyramidales) issues de la théorie des graphes et les approches par minimisation de fonctionnelles énergétiques globales. L'idée fondamentale est que les fonctionnelles...

We present a road extraction system from aerial imagery guided by an imprecise road network. After a general discussion on road extraction strategies, we focus on the road recognition module we propose. It relies on two principal elements : a general purpose parallel structures detector in images, which uses a simulation of light ray propagation an...

We describe here a vehicle detection method on aerial images. This method exploits a hierarchical modelling of our data. Among the different recognition methods that we have considered we choose a connectionist approach because of its generalization property. This paper justifies the choice of such an approach, and brings the proof of the efficienc...

This paper deals with evaluation of image segmentation methods.We start with a state-of-the art of the evaluation criteria, involving a reference segmentation or not. Based on an analysis of the main exiting criteria, we propose new criteria, when no ground-truth is available. These criteria, based on an energetical formalism, take into account bot...

- Cet article propose une approche multi-échelles de la segmentation d'image qui s'appuie sur un principe d'optimisation. Notre objectif est de calculer une séquence complète de partitions monotones qui approxime les minima d'une fonctionnelle dépendant d'un paramètre réel qui se comporte comme un paramètre d'échelle. Pour pouvoir manipuler toutes...