CNRS Laboratory of Electronics Informatics and Images

Dijon, France

CNRS Laboratory of Electronics Informatics and Images

Dijon, France
Time filter
Source Type

Shen K.-K.,CSIRO | Shen K.-K.,CNRS Laboratory of Electronics Informatics and Images | Fripp J.,CSIRO | Meriaudeau F.,CNRS Laboratory of Electronics Informatics and Images | And 4 more authors.
NeuroImage | Year: 2012

The hippocampus is affected at an early stage in the development of Alzheimer's disease (AD). With the use of structural magnetic resonance (MR) imaging, we can investigate the effect of AD on the morphology of the hippocampus. The hippocampal shape variations among a population can be usually described using statistical shape models (SSMs). Conventional SSMs model the modes of variations among the population via principal component analysis (PCA). Although these modes are representative of variations within the training data, they are not necessarily discriminative on labeled data or relevant to the differences between the subpopulations. We use the shape descriptors from SSM as features to classify AD from normal control (NC) cases. In this study, a Hotelling's T 2 test is performed to select a subset of landmarks which are used in PCA. The resulting variation modes are used as predictors of AD from NC. The discrimination ability of these predictors is evaluated in terms of their classification performances with bagged support vector machines (SVMs). Restricting the model to landmarks with better separation between AD and NC increases the discrimination power of SSM. The predictors extracted on the subregions also showed stronger correlation with the memory-related measurements such as Logical Memory, Auditory Verbal Learning Test (AVLT) and the memory subscores of Alzheimer Disease Assessment Scale (ADAS). © 2011.

Cariou C.,University of Rennes 1 | Chehdi K.,University of Rennes 1 | Le Moan S.,CNRS Laboratory of Electronics Informatics and Images
IEEE Geoscience and Remote Sensing Letters | Year: 2011

We address the problem of unsupervised band reduction in hyperspectral remote sensing imagery. We propose the use of an information theoretic criterion to automatically separate the sensor's spectral range into disjoint subbands without ground truth knowledge. Our approach, named BandClust, preserves the physical sense of the spectral data and automatically provides relevant spectral subbands, i.e., of maximal informational complementarity. Experiments using real hyperspectral images are conducted to compare BandClust with four other unsupervised approaches. The comparison of the selected dimensionality reduction methods is performed via supervised classification using support vector machines and shows the potential of the proposed approach. © 2010 IEEE.

Bazin J.-C.,ETH Zurich | Li H.,Australian National University | Kweon I.S.,KAIST | Demonceaux C.,CNRS Laboratory of Electronics Informatics and Images | And 2 more authors.
IEEE Transactions on Pattern Analysis and Machine Intelligence | Year: 2013

Data correspondence/grouping under an unknown parametric model is a fundamental topic in computer vision. Finding feature correspondences between two images is probably the most popular application of this research field, and is the main motivation of our work. It is a key ingredient for a wide range of vision tasks, including three-dimensional reconstruction and object recognition. Existing feature correspondence methods are based on either local appearance similarity or global geometric consistency or a combination of both in some heuristic manner. None of these methods is fully satisfactory, especially in the presence of repetitive image textures or mismatches. In this paper, we present a new algorithm that combines the benefits of both appearance-based and geometry-based methods and mathematically guarantees a global optimization. Our algorithm accepts the two sets of features extracted from two images as input, and outputs the feature correspondences with the largest number of inliers, which verify both the appearance similarity and geometric constraints. Specifically, we formulate the problem as a mixed integer program and solve it efficiently by a series of linear programs via a branch-and-bound procedure. We subsequently generalize our framework in the context of data correspondence/grouping under an unknown parametric model and show it can be applied to certain classes of computer vision problems. Our algorithm has been validated successfully on synthesized data and challenging real images. © 1979-2012 IEEE.

Bazin J.-C.,University of Tokyo | Demonceaux C.,CNRS Laboratory of Electronics Informatics and Images | Vasseur P.,CNRS Informatics Systems Laboratory | Kweon I.,KAIST
International Journal of Robotics Research | Year: 2012

Rotation estimation is a fundamental step for various robotic applications such as automatic control of ground/aerial vehicles, motion estimation and 3D reconstruction. However it is now well established that traditional navigation equipments, such as global positioning systems (GPSs) or inertial measurement units (IMUs), suffer from several disadvantages. Hence, some vision-based works have been proposed recently. Whereas interesting results can be obtained, the existing methods have non-negligible limitations such as a difficult feature matching (e.g. repeated textures, blur or illumination changes) and a high computational cost (e.g. analyze in the frequency domain). Moreover, most of them utilize conventional perspective cameras and thus have a limited field of view. In order to overcome these limitations, in this paper we present a novel rotation estimation approach based on the extraction of vanishing points in omnidirectional images. The first advantage is that our rotation estimation is decoupled from the translation computation, which accelerates the execution time and results in a better control solution. This is made possible by our complete framework dedicated to omnidirectional vision, whereas conventional vision has a rotation/translation ambiguity. Second, we propose a top-down approach which maintains the important constraint of vanishing point orthogonality by inverting the problem: instead of performing a difficult line clustering preliminary step, we directly search for the orthogonal vanishing points. Finally, experimental results on various data sets for diverse robotic applications have demonstrated that our novel framework is accurate, robust, maintains the orthogonality of the vanishing points and can run in real-time. © SAGE Publications 2011.

Demonceaux C.,CNRS Laboratory of Electronics Informatics and Images | Vasseur P.,University of Rouen | Fougerolle Y.,CNRS Laboratory of Electronics Informatics and Images
Image and Vision Computing | Year: 2011

Because of the distortions produced by the insertion of a mirror, catadioptric images cannot be processed similarly to classical perspective images. Now, although the equivalence between such images and spherical images is well known, the use of spherical harmonic analysis often leads to image processing methods which are more difficult to implement. In this paper, we propose to define catadioptric image processing from the geodesic metric on the unitary sphere. We show that this definition allows to adapt very simply classical image processing methods. We focus more particularly on image gradient estimation, interest point detection, and matching. More generally, the proposed approach extends traditional image processing techniques based on Euclidean metric to central catadioptric images. We show in this paper the efficiency of the approach through different experimental results and quantitative evaluations. © 2011 Elsevier B.V. All rights reserved.

Lafont F.,University of Toulon | Busvelle E.,CNRS Laboratory of Electronics Informatics and Images | Gauthier J.-P.,University of Toulon
Journal of Process Control | Year: 2011

The purpose of this paper is twofold: (1) we apply the adaptive observer developed in Boizot et al. [1] to a wastewater system, following two cascade steps. First, we apply it to a simplified model of the system. Second, we use this "simplified" estimation as a measurement for the full system. (2) Although the observability analysis is trivial, the equations contain rather complicated terms. Therefore, it is not reasonable to change coordinates for those of the required observability canonical form. Hence, we have to establish and work with the "unusual" equations of the observer in natural coordinates. Let us point out that the simulations are done taking into account the small number of measurements (three) available in practice. © 2011 Elsevier Ltd. All rights reserved.

Ait-Aoudia S.,National School in Computer Science | Foufou S.,CNRS Laboratory of Electronics Informatics and Images
Advances in Engineering Software | Year: 2010

Modeling by constraints enables users to describe shapes by specifying relationships between geometric elements. These relationships are called constraints. A constraint solver derives then automatically the design intended by exploiting these constraints. The constraints solvers can be classified in four categories: symbolic, numerical, rule-oriented and graph-constructive solvers. The graph constructive approach is widely used in recent Computer Aided Design (CAD) systems. In this paper, we present a decomposition-recombination (DR) planning algorithm, called S-DR, that uses a graph reduction method to solve systems of 2D geometric constraints. Based on the key concept of skeletons, S-DR planner figures out a plan for decomposing a well constrained system into small sub-systems and recombines the solutions of these sub-systems to derive the solution of the entire system.

Shabayek A.E.R.,CNRS Laboratory of Electronics Informatics and Images | Demonceaux C.,CNRS Laboratory of Electronics Informatics and Images | Morel O.,CNRS Laboratory of Electronics Informatics and Images | Fofi D.,CNRS Laboratory of Electronics Informatics and Images
Journal of Intelligent and Robotic Systems: Theory and Applications | Year: 2012

Unmanned aerial vehicles (UAVs) are increasingly replacing manned systems in situations that are dangerous, remote, or difficult for manned aircraft to access. Its control tasks are empowered by computer vision technology. Visual sensors are robustly used for stabilization as primary or at least secondary sensors. Hence, UAV stabilization by attitude estimation from visual sensors is a very active research area. Vision based techniques are proving their effectiveness and robustness in handling this problem. In this work a comprehensive review of UAV vision based attitude estimation approaches is covered, starting from horizon based methods and passing by vanishing points, optical flow, and stereoscopic based techniques. A novel segmentation approach for UAV attitude estimation based on polarization is proposed. Our future insightes for attitude estimation from uncalibrated catadioptric sensors are also discussed. © 2011 Springer Science+Business Media B.V.

Jolivot R.,CNRS Laboratory of Electronics Informatics and Images | Vabres P.,CNRS Laboratory of Electronics Informatics and Images | Marzani F.,CNRS Laboratory of Electronics Informatics and Images
Computerized Medical Imaging and Graphics | Year: 2011

The development of an integrated MultiSpectral Imaging (MSI) system yielding hyperspectral cubes by means of artificial neural networks is described. The MSI system is based on a CCD camera, a rotating wheel bearing a set of seven interference filters, a light source and a computer. The resulting device has been elaborated for in vivo imaging of skin lesions. It provides multispectral images and is coupled with a software reconstructing hyperspectral cubes from multispectral images. Reconstruction is performed by a neural network-based algorithm using heteroassociative memories. The resulting hyperspectral cube provides skin optical reflectance spectral data combined with bidimensional spatial information. This combined information will hopefully improve diagnosis and follow-up in a range of skin disorders from skin cancer to inflammatory diseases. © 2010 Elsevier Ltd.

Baril J.-L.,CNRS Laboratory of Electronics Informatics and Images | Pallo J.-M.,CNRS Laboratory of Electronics Informatics and Images
Information Processing Letters | Year: 2014

The Tamari lattice of order n can be defined by the set Dn of Dyck words endowed with the partial order relation induced by the well-known rotation transformation. In this paper, we study this rotation on the restricted set of Motzkin words. An upper semimodular join semilattice is obtained and a shortest path metric can be defined. We compute the corresponding distance between two Motzkin words in this structure. This distance can also be interpreted as the length of a geodesic between these Motzkin words in a Tamari lattice. So, a new upper bound is obtained for the classical rotation distance between two Motzkin words in a Tamari lattice. For some specific pairs of Motzkin words, this bound is exactly the value of the rotation distance in a Tamari lattice. Finally, enumerating results are given for join and meet irreducible elements, minimal elements and coverings. © 2013 Elsevier B.V.

Loading CNRS Laboratory of Electronics Informatics and Images collaborators
Loading CNRS Laboratory of Electronics Informatics and Images collaborators