
D.S. Ly, C. Demonceaux, P. Vasseur, C. Pégard (2014): Extrinsic calibration of heterogeneous cameras by line images. Machine Vision and Applications 25(6) 1601—1614.
The extrinsic calibration refers to determining the relative pose of cameras. Most of the approaches for cameras with nonoverlapping fields of view (FOV) are based on mirror reflection, object tracking or rigidity constraint of stereo systems whereas cameras with overlapping FOV can be calibrated using structure from motion solutions. We propose an extrinsic calibration method within structure from motion framework for cameras with overlapping FOV and its extension to cameras with partially nonoverlapping FOV. Recently, omnidirectional vision has become a popular topic in computer vision as...
S. Morales, V. Naranjo, J. Angulo, F. LópezMir, M. Alcañiz (2014): DETERMINATION OF RETINAL NETWORK SKELETON THROUGH MATHEMATICAL MORPHOLOGY. 22nd European Signal Processing Conference (EUSIPCO'2014), Lisbon (Portugal).
This paper describes a new approach to determine vascular skeleton in retinal images. This approach is based on mathematical morphology along with curvature evaluation. In particular, a variant of the watershed transformation, the stochastic watershed, is applied to extract the vessel centerline. Its goal is to obtain directly the skeleton of the retinal tree avoiding a previous stage of vessel segmentation in order to reduce the dependence between stages and the computational cost. Experimental results show qualitative improvements if the proposed method is compared with other...
F. LópezMir, V. Naranjo, S. Morales, J. Angulo (2014): Probability density function of object contours using regional regularized stochastic watershed. IEEE International Conference on Image Processing (ICIP'2014 ), Paris (France) 4762 — 4766.
In this paper, a probability density function of object contours based on the stochastic watershed transform is carried out. The watershed transform produces an oversegmentation of the image due to noise, illumination problems, low contrast, etc., because each regional minimum of the image gives place to a region in the output image. To solve this problem, the efforts are focused on the definition of markers to impose new minima in the image, and enhancing the gradient image. The stochastic watershed performs a probability density function (pdf) of the object contours based on a MonteCarlo...
J. Angulo, S. VelascoForero (2014): Riemannian mathematical morphology. Pattern Recognition Letters 47 93–101.
This paper introduces mathematical morphology operators for realvalued images whose support space is a Riemannian manifold. The starting point consists in replacing the Euclidean distance in the canonic quadratic structuring function by the Riemannian distance used for the adjoint dilation/erosion. We then extend the canonic case to a most general framework of Riemannian operators based on the notion of admissible Riemannian structuring function. An alternative paradigm of morphological Riemannian operators involves an external structuring function which is parallel transported to each point...
G. Franchi, J. Angulo (2014): Comparative study on morphological principal component analysis of hyperspectral images. Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 6th Workshop on, Lausanne (Switzerland).
This paper deals with a problem of reducing the dimension of hyperspectral images using the principal component analysis. Since hyperspectral images are always reduced before any process, we choose to do this reduction by adding spatial information that can be useful then for classification process; to do it we choose to project our data in new spaces thanks mathematical morphology.
T. Prill (2014): Characterization and modeling of nanoporous carbon structures.
The aim of the work presented here is to optimize nanoporous carbon materials by means of 'virtual material design'. On this length scale (~ 10nm) Focused Ion Beam – Scanning Electron Microscopy Nanotomography (FIBSEM) is the only imaging technique providing three dimensional geometric information. Yet, for the optimization, the pore space of the materials must be reconstructed from the resulting image data, which was a generally unsolved problem so far.To overcome this problem, a simulation method for FIBSEM images was developed. The resulting synthetic FIBSEM images could then be used...
A.F. Serna Morales (2014): Semantic analysis of 3D point clouds from urban environments : ground, facades, urban objects and accessibility.
Most important cities in the world have very detailed 2D urban plans of streets and public spaces.These plans contain information about roads, sidewalks, facades and urban objects such as lampposts, traffic signs, bollards, trees, among others.Nowadays, several local authorities, national mapping agencies and private companies have began to consider justifiable including 3D information, navigation options and accessibility issues into urban maps.Compared to the first 3D scanning systems 30 years ago, current laser scanners are cheaper, faster and provide more accurate and denser 3D point...
V. Machairas, E. Decencière, T. Walter (2014): Waterpixels: Superpixels based on the watershed transformation. IEEE International Conference On Image Processing, Paris (France).
Many sophisticated segmentation algorithms rely on a first lowlevel segmentation step where an image is partitioned into homogeneous regions with enforced compactness and adherence to object boundaries. These regions are called " superpixels ". While the marker controlled watershed transformation should in principle be well suited for this type of application , it has never been seriously tested in this setup, and comparisons to other methods were not made with the best possible settings. Here, we provide a scheme for applying the watershed transform for superpixel generation, where we use...
S. Beucher (2014): MATHEMATICAL MORPHOLOGY EXERCISES With MAMBA (Release 1).
Exercises book in mathematical morphology using the Mamba software library (This release does not contain solutions).
S. Beucher (2014): Labelling Operators.
This note describes implementations in MAMBA of some particle or region labellings. These operators are used to quickly label each connected component of an image with the result of a measure applied on it.
J. Angulo (2014): Lipschitz Regularization of Images supported on Surfaces using Riemannian Morphological Operators.
Dierent imaging modalities produce nowadays images on smooth surfaces, represented by images painted on meshes or point clouds. These Riemannian images are often nonsmooth and their regularization can be needed in many applications. This paper deals with the approximation of a bounded nonsmooth image painted on a surface by a sequence of more regular functions, having in particular Lipschitz gradient, and without any hypothesis of dierentiability. We adopt here a geometric framework known as LasryLions regularization. The aim of the present contribution is to consider the extension of...
F. Meyer (2014): Watersheds on weighted graphs. Pattern Recognition Letters 47 72—79.
The watershed is an efficient and versatile segmentation tool, as it partitions the images into disjoint catchment basins. We study the watershed on node or edge weighted graphs. We do not aim at constructing a partition of the nodes but consider the catchment zones, i.e. the attraction zone of a drop of water. Often, such zones largely overlap. In a first part we show how to derive from a node or edge weighted graph a ooding graph with the same trajectories of a drop of water, whether one considers its node weights alone or its edge weights alone. In a second part we show how to reduce the...
B. Figliuzzi, W.H.R. Chan, J. Moran, C.R. Buie (2014): Nonlinear electrophoresis of ideally polarizable particles. Physics of Fluids 102002.
We focus in this paper on the nonlinear electrophoresis of ideally polarizable particles. At high applied voltages significant ionic exchange occurs between the electric double layer which surrounds the particle and the bulk solution. In addition steric effects due to the finite size of ions drastically modify the electric potential distribution in the electric double layer. In this situation the velocity field the electric potential and the ionic concentration in the immediate vicinity of the particle are described by a complicated set of coupled nonlinear partial differential equations. In...
H. Altendorf, F. Latourte, D. Jeulin, M. Faessel, L. Saintoyant (2014): 3D reconstruction of a multiscale microstructure by anisotropic tessellation models. Image Analysis and Stereology 33(2) 121—130.
In the area of tessellation models, there is an intense activity to fully understand the classical models of Voronoi, Laguerre and JohnsonMehl. Still, these models are all simulations of isotropic growth and are therefore limited to very simple and partly convex cell shapes. The here considered microstructure of martensitic steel has a much more complex and highly non convex cell shape, requiring new tessellation models. This paper presents a new approach for anisotropic tessellation models that resolve to the wellstudied cases of Laguerre and JohnsonMehl for spherical germs. Much better...
D. Jeulin (2014): Random tessellations generated by Boolean random functions. Pattern Recognition Letters 47(1) 139—146.
Generalizations of various random tessellation models generated by Poisson point processes are introduced, and their functional probability P(K) is given. They are obtained from Boolean random function models, and alternatively from a geodesic distance, providing a generic way of simulation of a wide range of random tessellations, as illustrated in the paper.
L. Gueguen, S. VelascoForero, P. Soille (2014): Local Mutual Information for DissimilarityBased Image Segmentation. Journal of Mathematical Imaging and Vision 48(3) 625—644.
Connective segmentation based on the definition of a dissimilarity measure on pairs of adjacent pixels is an appealing framework to develop new hierarchical segmentation methods. Usually, the dissimilarity is fully determined by the intensity values of the considered pair of adjacent pixels, so that it is independent of the values of the other image pixels. In this paper, we explore dissimilarity measures depending on the overall image content encapsulated in its local mutual information and show its invariance to information preserving transforms. This is investigated in the framework of the...
S. VelascoForero, J. Angulo (2014): Vector ordering and multispectral morphological image processing. Vector Ordering and Multispectral Morphological Image Processing 11 223—239.
This chapter illustrates the suitability of recent multivariate ordering approaches to morphological analysis of colour and multispectral images working on their vector representation. On the one hand, supervised ordering renders machine learning notions and image processing techniques, through a learning stage to provide a total ordering in the colour/multispectral vector space. On the other hand, anomalybased ordering, automatically detects spectral diversity over a majority background, allowing an adaptive processing of salient parts of a colour/multispectral image. These two...
A. Serna, B. Marcotegui, E. Decencière, T. Baldeweck, A.M. Pena, S. Brizion (2014): Segmentation of elongated objects using attribute profiles and area stability: application to melanocyte segmentation. Pattern Recognition Letters 10.1016/j.patrec.2014.03.014.
In this paper, a method to segment elongated objects is proposed. It is based on attribute profiles and area stability. Images are represented as component trees using a threshold decomposition. Then, some attributes are computed on each node of the tree. Finally, the attribute profile is analyzed to identify important events useful for segmentation tasks. In this work, a new attribute, combining geodesic elongation and area stability is defined. This methodology is successfully applied to the segmentation of cells in multiphoton fluorescence microscopy images of engineered skin....
J. Angulo, S. VelascoForero (2014): Morphological processing of univariate Gaussian distributionvalued images based on Poincaré upperhalf plane representation. Geometric Theory of Information 331—366.
Mathematical morphology is a nonlinear image processing methodology based on the application of complete lattice theory to spatial structures. Let us consider an image model where at each pixel is given a univariate Gaussian distribution. This model is interesting to represent for each pixel the measured mean intensity as well as the variance (or uncertainty) for such measurement. The aim of this work is to formulate morphological operators for these images by embedding Gaussian distribution pixel values on the Poincaré upperhalf plane. More precisely, it is explored how to endow this...
J. Angulo (2014): Riemannian L p Averaging on Lie Group of Nonzero Quaternions. Advances in Applied Clifford Algebras 24(2) 355—382.
This paper discusses quaternion $L^p$ geometric weighting averaging working on the multiplicative Lie group of nonzero quaternions $\mathbb{H}^{*}$, endowed with its natural biinvariant Riemannian metric. Algorithms for computing the Riemannian $L^p$ center of mass of a set of points, with $1 \leq p \leq \infty$ (i.e., median, mean, $L^p$ barycenter and minimax center), are particularized to the case of $\mathbb{H}^{*}$. Two different approaches are considered. The first formulation is based on computing the logarithm of quaternions which maps them to the Euclidean tangent space at the...
J. Angulo (2014): Structure Tensor Image Filtering using Riemannian L_1 and L_∞ CenterofMass. Image Analysis and Stereology 33(2) 95—105.
Structure tensor images are obtained by a Gaussian smoothing of the dyadic product of gradient image. These images give at each pixel a n×n symmetric positive definite matrix SPD(n), representing the local orientation and the edge information. Processing such images requires appropriate algorithms working on the Riemannian manifold on the SPD(n) matrices. This contribution deals with structure tensor image filtering based on Lp geometric averaging. In particular, L1 centerofmass (Riemannian median or FermatWeber point) and L∞ centerofmass (Riemannian circumcenter) can be obtained for...
M. Brédif, B. Vallet, A. Serna, B. Marcotegui, N. Paparoditis (2014): TERRAMOBILITA/IQMULUS URBAN POINT CLOUD CLASSIFICATION BENCHMARK. Workshop on Processing Large Geospatial Data, Cardiff (United Kingdom).
The object of the TerraMobilita/iQmulus 3D urban analysis benchmark is to evaluate the current state of the art in urban scene analysis from mobile laser scanning (MLS). A very detailed semantic tree for urban scenes is proposed (cf Figure 1). We call analysis the capacity of a method to separate the points of the scene into these categories (classification), and to separate the different objects of the same type for object classes (detection). The ground truth is produced manually in two steps using advanced editing tools developed especially for this benchmark. Base on this ground truth,...
S. Bancelin, E. Decencière, V. Machairas, C. Albert, T. Coradin, M.C. SchanneKlein, Aimé (2014): Fibrillogenesis from nanosurfaces: multiphoton imaging and stereological analysis of collagen 3D selfassembly dynamics. Soft Matter 6651—6657.
The assembly of proteins into fibrillar structures is an important process that concerns different biological contexts, including molecular medicine and functional biomaterials. Engineering of hybrid biomaterials can advantageously provide synergetic interactions of the biopolymers with an inorganic component to ensure specific supramolecular organization and dynamics. To this aim, we designed hybrid systems associating collagen and surfacefunctionalized silica particles and we built a new strategy to investigate fibrillogenesis processes in such multicomponents systems, working at the...
D.S. Ly, S. Beucher, M. Bilodeau (2014): COLOR CORRECTION THROUGH REGION MATCHING LEVERAGED BY POINT CORRESPONDENCES. IEEE The International Conference on Image Processing, Paris (France).
This paper addresses the problem of regionbased color correction. Our solution begins with the image segmentation by markercontrolled watershed transformation, which is faster and produces more uniform regions with better adherence to object boundaries than the segmentation in previous works. Next, regions between two images are matched using point feature correspondences which are invariant to geometric transformation and illumination changes. Finally, the colorcorrected image is generated from the color transfer functions of corresponding regions. We demonstrate the results of this...
D. Craciun, A. SernaMorales, J.E. Deschaud, B. Marcotegui, F. Goulette (2014): Scalable and DetailPreserving Ground Surface Reconstruction from Large 3D Point Clouds Acquired by Mobile Mapping Systems. PCV (Photogrammetric Computer Vision), Zurich (Switzerland) 3 73 — 80.
The currently existing mobile mapping systems equipped with active 3D sensors allow to acquire the environment with high sampling rates at high vehicle velocities. While providing an effective solution for environment sensing over large scale distances, such acquisition provides only a discrete representation of the geometry. Thus, a continuous map of the underlying surface must be built. Mobile acquisition introduces several constraints for the stateoftheart surface reconstruction algorithms. Smoothing becomes a difficult task for recovering sharp depth features while avoiding mesh...
F. Meyer, C. Tadonki, F. Irigoin (2014): Dendrogram Based Algorithm for Dominated Graph Flooding. International Conference on Computational Science (ICCS 2014), Cairns (Australia) 29 586—598.
In this paper, we are concerned with the problem of flooding undirected weighted graphs un der ceiling constraints. We provide a new algorithm based on a hierarchical structure called dendrogram, which offers the significant advantage that it can be used for multiple flooding with various scenarios of the ceiling values. In addition, when exploring the graph through its dendrogram structure in order to calculate the flooding levels, independent subdendrograms are generated, thus offering a natural way for parallel processing. We provide an efficient im plementation of our algorithm through...
A. Ambos, H. Trumel, F. Willot, D. Jeulin, M. Biessy (2014): A fast Fourier transform micromechanical upscaling method for the study of the thermal expansion of a TATBbased pressed explosive. 15th International Detonation Symposium, San Francisco (United States).
This paper presents the first phase of development of a multiscale numerical method operating at the microstructureal level for a TATBbased pressed plasticbonded explosive. It uses a virtual model of microstructure mimicking the grain size distribution of the actual material, and a Fourierbased numerical scheme. At present, the method works with simplified microstructure and linear anisotropic thermoelastic behavior for the constituents. Neglecting the intergranular binder leads to fairly overestimated values for isotropic elastic moduli and volumetric coefficient of thermal expansion....
H. Altendorf, D. Jeulin, F. Willot (2014): Influence of the fiber geometry on the macroscopic elastic and thermal properties. International Journal of Solids and Structures 51(2324) 3807—3822.
This work focuses on the linear elastic and thermal properties of real and virtual, computergenerated fibrous composites. A stochastic microstructure model is used to generate denselyassembled 3D systems of curved, non overlapping fibers with specific orientation distributions. This model is first optimized to approach the characteristics of a real fiber glass polymer by fitting geometrical and statistical parameters, such as fiber orientation, radius, length, and curvature. Second, random realizations of the stochastic models that depart from the characteristics of the fiber glass polymer...
F. Meyer, C. Tadonki, F. Irigoin (2014): Inondations dominées de Graphes Valués. Séminaire de l'Institut Carnot M.I.N.E.S, Paris (France).
E. Decencière, X. Zhang, G. Cazuguel, B. Laÿ, B. Cochener, C. Trone, P. Gain, J.R. OrdóñezVarela, P. Massin, A. Erginay, B. Charton, J.C. Klein (2014): FEEDBACK ON A PUBLICLY DISTRIBUTED IMAGE DATABASE: THE MESSIDOR DATABASE. Image Analysis and Stereology 231—234.
The Messidor database, which contains hundreds of eye fundus images, has been publicly distributed since 2008. It was created by the Messidor project in order to evaluate automatic lesion segmentation and diabetic retinopathy grading methods. Designing, producing and maintaining such a database entails significant costs. By publicly sharing it, one hopes to bring a valuable resource to the public research community. However, the real interest and benefit of the research community is not easy to quantify. We analyse here the feedback on the Messidor database, after more than 6 years of...
X. Zhang (2014): Image processing methods for computeraided screening of diabetic retinopathy.
Diabetic retinopathy is the main cause of blindness among the middleaged population. An early detection and adapted treatment considerably reduce the risk of sight loss. Medical authorities recommend an annual examination to diabetic patients. Several diabetic retinopathy screening programs have been deployed to enforce this recommendation. The aim of the TeleOphta project was to automatically detect normal examinations in a diabetic screening system, in order to reduce the burden on readers, and therefore serve more patients. This thesis proposes several methods to extract information...
V. Morard, P. Dokládal, E. Decencière (2014): Parsimonious Path Openings and Closings. IEEE Transactions on Image Processing 23(4) 1543 — 1555.
Path openings and closings are morphological tools used to preserve long, thin and tortuous structures in gray level images. They explore all paths from a defined class, and filter them with a length criterion. However, most paths are redundant, making the process generally slow. Parsimonious path openings and closings are introduced in this paper to solve this problem. These operators only consider a subset of the paths considered by classical path openings, thus achieving a substantial speedup, while obtaining similar results. Moreover, a recently introduced one dimensional (1D) opening...
X. Zhang, G. Thibault, E. Decencière, B. Marcotegui, B. Laÿ, R. Danno, G. Cazuguel, G. Quellec, M. Lamard, P. Massin, A. Chabouis, Z. Victor, A. Erginay (2014): Exudate detection in color retinal images for mass screening of diabetic retinopathy. Medical Image Analysis 18(7) 1026 — 1043.
The automatic detection of exudates in colour eye fundus images is an important task in applications such as diabetic retinopathy screening. The presented work has been undertaken in the framework of the TeleOphta project, whose main objective is to automatically detect normal exams in a teleophthalmology network, thus reducing the burden on the readers. A new clinical database, eophtha EX, containing precisely manually contoured exudates, is introduced. As opposed to previously available databases, eophtha EX is very heterogeneous. It contains images gathered within the OPHDIAT...
S. Bancelin, A. Nazac, B.H. Ibrahim, P. Dokládal, E. Decencière, B. Teig, H. Haddad, H. Fernandez, M.C. SchanneKlein, A. De Martino (2014): Determination of collagen fiber orientation in histological slides using Mueller microscopy and validation by second harmonic generation imaging. Optics Express 22(19) 22561—22574.
We studied the azimuthal orientations of collagen fibers in histological slides of uterine cervical tissue by two different microscopy techniques, namely Mueller polarimetry (MP) and Second Harmonic Generation (SHG). SHG provides direct visualization of the fibers with high specificity, which orientations is then obtained by suitable image processing. MP provides images of retardation (among other polarimetric parameters) due to the optical anisotropy of the fibers, which is enhanced by Picrosirius Red staining. The fiber orientations are then assumed to be those of the retardation slow axes....
B. Marcotegui (2014): RESIDUAL APPROACH ON A HIERARCHICAL SEGMENTATION. IEEE International Conference on Image Processing, Paris (France).
Residual operators analyze the evolution of an image subject to the application of a series of transformations, for example a series of openings of increasing size. When a significant object is filtered out by a transformation corresponding to its size, an important residue is observed. Maximal residues are kept for each pixel, indicating the most significant objects present in the image. Different families of operators have been used in the literature: morphological openings or closings, attribute openings or openings by reconstruction. In this paper we propose to compute residues on a...
J. Angulo, S. VelascoForero (2014): Riemannian mathematical morphology. Pattern Recognition Letters 47 93—101.
This paper introduces mathematical morphology operators for realvalued images whose support space is a Riemannian manifold. The starting point consists in replacing the Euclidean distance in the canonical quadratic structuring function by the Riemannian distance used for the adjoint dilation/erosion. We then extend the canonical case to a most general framework of Riemannian operators based on the notion of admissible Riemannian structuring function. An alternative paradigm of morphological Riemannian operators involves an external structuring function which is parallel transported to each...
J.C. MuñozGarcía, M.J. GarcíaJiménez, P. Carrero, A. Canales, J. JiménezBarbero, M. MartínLomas, A. Imberty, J.L. De Paz, J. Angulo, H. LortatJacob, P.M. Nieto (2014): Importance of the polarity of the glycosaminoglycan chain on the interaction with FGF1. Glycobiology 24(11) 1004—1009.
Heparinlike saccharides play an essential role in binding to the fibroblast growth factor (FGF)1 and to their membrane receptors fibroblast growth factor receptor forming a ternary complex that is responsible of the internalization of the signal, via the dimerization of the intracellular regions of the receptor. In this study, we report the binding affinities between five synthetic hexasaccharides with human FGF1 obtained by surface plasmon resonance experiments, and compare with the induced mitogenic activity previously obtained. These five oligosaccharides differ in the sulfation pattern...
J.C. Bricola, M. Bilodeau, S. Beucher (2014): A topdown methodology to depth map estimation controlled by morphological segmentation.
Given a pair of stereo images and the transformation existing between the corresponding camera coordinate systems, the depth of a scene point can be computed from its projections on both images. Despite the difficulties related to the matching of such projections across homogeneous regions and the occlusion phenomenon, state of the art methods have already produced accurate results on classical stereo datasets. This article proposes a new way of approaching depth estimation. Instead of searching for dense pixel correspondences, a gross estimation of the disparities is initially performed at...
F. Willot, B. Abdallah, Y.P. Pellegrini (2014): Fourierbased schemes with modified Green operator for computing the electrical response of heterogeneous media with accurate local fields. International Journal for Numerical Methods in Engineering 98(7) 518—533.
A modified Green operator is proposed as an improvement of Fourierbased numerical schemes commonly used for computing the electrical or thermal response of heterogeneous media. Contrary to other methods, the number of iterations necessary to achieve convergence tends to a finite value when the contrast of properties between the phases becomes infinite. Furthermore, it is shown that the method produces much more accurate local fields inside highlyconducting and quasiinsulating phases, as well as in the vicinity of the phases interfaces. These good properties stem from the discretization of...
F. Delloro, M. Faessel, H. Proudhon, D. Jeulin, M. Jeandin, E. Meillot, L. Bianchi (2014): Xray microtomography and modeling of cold sprayed coated powders. ITSC 2014 International Thermal Spray Conference and Exhibition 886—891.
F. Delloro, M. Faessel, H. Proudhon, D. Jeulin, M. Jeandin, E. Meillot, L. Bianchi (2014): A morphological approach to the modeling of the cold spray process. ITSC 2014 International Thermal Spray Conference and Exhibition 221—226.
J. FronteraPons, M.A. Veganzones, S. VelascoForero, F. Pascal, J.P. Ovarlez, J. Chanussot (2014): Robust anomaly detection in hyperspectral imaging. 2014 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2014), Québec (Canada).
Anomaly Detection methods are used when there is not enough information about the target to detect. These methods search for pixels in the image with spectral characteristics that differ from the background. The most widespread detection test, the RXdetector, is based on the Mahalanobis distance and on the background statistical characterization through the mean vector and the covariance matrix. Although nonGaussian distributions have already been introduced for background modeling in Hyperspectral Imaging, the parameters estimation is still performed using the Maximum Likelihood Estimates...
A. Serna, B. Marcotegui (2014): Detection, segmentation and classification of 3D urban objects using mathematical morphology and supervised learning. ISPRS Journal of Photogrammetry and Remote Sensing 93 243—255.
We propose an automatic and robust approach to detect, segment and classify urban objects from 3D point clouds. Processing is carried out using elevation images and the result is reprojected onto the 3D point cloud. First, the ground is segmented and objects are detected as discontinuities on the ground. Then, connected objects are segmented using a watershed approach. Finally, objects are classified using SVM with geometrical and contextual features. Our methodology is evaluated on databases from Ohio (USA) and Paris (France). In the former, our method detects 98% of the objects, 78% of them...
J.C. Bricola, M. Bilodeau, S. Beucher (2014): Depth map estimation: a regionbased approach.
This paper presents an approach to the estimation of depth from stereo images which exploits correspondences of image segments. A key motivation is to bypass pixel correspondences which are ambiguous in textureless regions. One of the main difficulty though is to come up to an equivalent partitioning of both stereo images that facilitates region matching. The reference image which the depth is estimated for is first segmented using the watershed algorithm. Regions are then transferred to the other image of the stereo pair according to a correlation analysis of region contours. This transfer...
E. Chevallier, A. Chevallier, J. Angulo (2014): Computing Histogram of Tensor Images using Orthogonal Series Density Estimation and Riemannian Metrics. 22nd International Conference on Pattern Recognition (ICPR), 2014, Stockholm (Sweden).
This paper deals with the computation of the histogram of tensor images, that is, images where at each pixel is given a n by n positive definite symmetric matrix, SPD(n). An approach based on orthogonal series density estimation is introduced, which is particularly useful for the case of measures based on Riemannian metrics. By considering SPD(n) as the space of the covariance matrices of multivariate gaussian distributions, we obtain the corresponding density estimation for the measure of both the Fisher metric and the Wasserstein metric. Experimental results on the application of such...
A. Serna, B. Marcotegui, F. Goulette, J.E. Deschaud (2014): ParisrueMadame database: a 3D mobile laser scanner dataset for benchmarking urban detection, segmentation and classification methods. 4th International Conference on Pattern Recognition, Applications and Methods ICPRAM 2014, Angers (France).
This paper describes a publicly available 3D database from the rue Madame, a street in the 6th Parisian district. Data have been acquired by the Mobile Laser Scanning (MLS) system L3D2 and correspond to a 160 m long street section. Annotation has been carried out in a manually assisted way. An initial annotation is obtained using an automatic segmentation algorithm. Then, a manual refinement is done and a label is assigned to each segmented object. Finally, a class is also manually assigned to each object. Available classes include facades, ground, cars, motorcycles, pedestrians, traffic...
G. Franchi, J. Angulo, M. Moreaud (2014): Unsupervised Morphological Multiscale Segmentation of Scanning Electron Microscopy Images.
This paper deals with a problem of unsupervised multiscale segmentation in the domain of scanning electron microscopy, which is tackled by mathematical morphology techniques. The proposed approach includes various steps. First, the image is decomposed into various compact scales of representation, where objects at each scale are homogeneous in size. Multiscale decomposition is based on a morphological scalespace followed by scale merging using hierarchical clustering and earth mover distance. Then the compact scales are segmented independently using watershed transform. Finally the segmented...
J. Dirrenberger, S. Forest, D. Jeulin (2014): Towards gigantic RVE sizes for 3D stochastic fibrous networks. International Journal of Solids and Structures 51 359—376.
The size of representative volume element (RVE) for 3D stochastic fibrous media is investigated. A statistical RVE size determination method is applied to a specific model of random microstructure: Poisson fibers. The definition of RVE size is related to the concept of integral range. What happens in microstructures exhibiting an infinite integral range? Computational homogenization for thermal and elastic properties is performed through finite elements, over hundreds of realizations of the stochastic microstructural model, using uniform and mixed boundary conditions. The generated data...
G. Franchi, J. Angulo (2014): Spatiallyvariant area openings for referencedriven adaptive contour preserving filtering. 2014 22nd International Conference on Pattern Recognition (ICPR),, Stockholm (Sweden).
Classical adaptive mathematical morphology is based on operators which locally adapt the structuring elements to the image properties. Connected morphological operators act on the level of the flat zones of an image, such that only flat zones are filtered out, and hence the object edges are preserved. Area opening (resp. area closing) is one of the most useful connected operators, which filters out the bright (resp. dark) regions. It intrinsically involves the adaptation of the shape of the structuring element parameterized by its area. In this paper, we introduce the notion of...
D. Jeulin (2014): Introduction to some basic random morphological models. Stochastic Geometry, Spatial Statistics and Random Fields.
The Boolean RF are a generalization of the Boolean RACS. Their construction based on the combination of a sequence of primary RF by the operation supremum or infimum, and their main properties (among which the supremum or infimum infinite divisibility) are given in the case of scalar RF built on a Poisson point process.
Liste complète des publications du CMM, enregistrées sur HAL ("tag":
ENSMP_CMM
).
Voir également :