Search

International audience; We present a multi-object tracking (MOT) approach to track small moving targets in satellite images. Our objects of interest span few pixels, do not present a defined texture, and are easily lost in cluttered environments. We propose a patchbased convolutional neural network (CNN) that focuses on specific regions to detect and discriminate nearby small objects. We use the object motion information to drive the patch selection and detect objects using a region-based CNN. In addition, we present a direct MOT data-association approach by using an improved Gaussian mixture-probability hypothesis density (GM-PHD) filter. The GM-PHD filter offers an efficient yet robust MOT formulation that takes into account clutter, misdetection, and target appearance and disappearance. We are able to detect and track blob-like moving objects and demonstrate an improvement over competing state-of-the-art tracking approaches.

International audience; In this paper, a novel method to deal with the semantic segmentation of very high resolution remote sensing data is presented. Recent advances in deep learning (DL), especially convolutional neural networks (CNNs) and fully convolutional networks (FCNs), have shown outstanding performances in this task. However, the map accuracy depends on the quantity and quality of ground truth (GT) used to train them. At the same time, probabilistic graphical models (PGMs) have sparked even more interest in the past few years, because of the ever-growing need for structured predictions. The novel method proposed in this paper combines DL and PGMs to perform remote sensing image classification. FCNs can be exploited to deal with multiscale data through the integration with a hierarchical Markov model. The marginal posterior mode (MPM) criterion for inference is used in the proposed framework. Experimental validation is conducted on the ISPRS 2D Semantic Labeling Challenge Vaihingen dataset. The results are significant, as the proposed method has a higher recall than the standard FCNs considered and allows mitigating the impact of incomplete or suboptimal GT, especially with regard to the discrimination of minoritary classes.

We develop a novel method based on Deep Convolutional Networks (DCN) to automate the identification and mapping of fracture and fault traces in optical images. The method employs two DCNs in a two players game: a first network, called Generator, learns to segment images to make them resembling the ground truth; a second network, called Discriminator, measures the differences between the ground truth image and each segmented image and sends its score feedback to the Generator; based on these scores, the Generator improves its segmentation progressively. As we condition both networks to the ground truth images, the method is called Conditional Generative Adversarial Network (CGAN). We propose a new loss function for both the Generator and the Discriminator networks, to improve their accuracy. Using two criteria and a manually annotated optical image, we compare the generalization performance of the proposed method to that of a classical DCN architecture, U-net. The comparison demonstrates the suitability of the proposed CGAN architecture. Further work is however needed to improve its efficiency.

International audience; Commission III, WG III/6 KEY WORDS: Multiresolution and multisensor fusion, causality, hierarchical Markov random models, Markov chain, semantic image segmentation. ABSTRACT: In this paper, a multiscale Markov framework is proposed in order to address the problem of the classification of multiresolution and multisensor remotely sensed data. The proposed framework makes use of a quadtree to model the interactions across different spatial resolutions and a Markov model with respect to a generic total order relation to deal with contextual information at each scale in order to favor applicability to very high resolution imagery. The methodological properties of the proposed hierarchical framework are investigated. Firstly, we prove the causality of the overall proposed model, a particularly advantageous property in terms of computational cost of the inference. Secondly, we prove the expression of the marginal posterior mode criterion for inference on the proposed framework. Within this framework, a specific algorithm is formulated by defining, within each layer of the quadtree, a Markov chain model with respect to a pixel scan that combines both a zigzag trajectory and a Hilbert space-filling curve. Data collected by distinct sensors at the same spatial resolution are fused through gradient boosted regression trees. The developed algorithm was experimentally validated with two very high resolution datasets including multispectral, panchromatic and radar satellite images. The experimental results confirm the effectiveness of the proposed algorithm as compared to previous techniques based on alternate approaches to multiresolution fusion.

International audience; Retinal vessel extraction and segmentation is essential for supporting diagnosis of eye-related diseases. In recent years, deep learning has been applied to vessel segmentation and achieved excellent performance. However, these supervised methods require accurate hand-labeled training data, which may not be available. In this paper, we propose an unsuper-vised segmentation method based on our previous connected tube marked point process (MPP) model. The vessel network is extracted by the connected-tube MPP model first. Then a new tube-based segmentation method is applied to the extracted tubes. We test this method on STARE and DRIVE databases and the results show that not only do we extract the retina vessel network accurately, but we also achieve high G-means score for vessel segmentation, without using labeled training data.

International audience; Road detection in high-resolution satellite images is an important and popular research topic in the field of image processing. In this paper, we propose a novel road extraction and tracking method based on road segmentation results from a convolutional network, providing improved road detection. The proposed method incorporates our previously proposed connected-tube marked point process (MPP) model and a post-tracking algorithm. We present experimental results on the Massachusetts roads dataset to show the performance of our method on road detection in remotely-sensed images.

International audience; In this paper, the problem of the classification of multireso-lution and multisensor remotely sensed data is addressed by proposing a multiscale Markov mesh model. Multiresolution and multisensor fusion are jointly achieved through an explicitly hierarchical probabilistic graphical classifier, which uses a quadtree structure to model the interactions across different spatial resolutions, and a symmetric Markov mesh random field to deal with contextual information at each scale and favor applicability to very high resolution imagery. Differently from previous hierarchical Markovian approaches, here, data collected by distinct sensors are fused through either the graph topology itself (across its layers) or decision tree ensemble methods (within each layer). The proposed model allows taking benefit of strong analytical properties, most remarkably causality, which make it possible to apply time-efficient non-iterative inference algorithms.

International audience; In this paper, we address the problem of the joint classifica-tion of multiple images acquired on the same scene at different spatial resolutions. From an application viewpoint, thisproblem is of importance in several contexts, including, mostremarkably, satellite and aerial imagery. From a methodolog-ical perspective, we use a probabilistic graphical approachand adopt a hierarchical Markov mesh framework that we have recently developed and models the spatial-contextual classification of multiresolution and possibly multisensor images. Here, we focus on the methodological properties of this framework. First, we prove the causality of the model, a highly desirable property with respect to the computationa lcost of the inference. Then, we prove the expression of the marginal posterior mode criterion for this model and discuss the related assumptions. Experimental results with multi-spectral and panchromatic satellite images are also presented.

International audience; In this paper we address the problem of unsuper-vised change detection on two or more coregistered images of the same object or scene at several time instants. We propose a novel empirical-Bayesian approach that is based on a false discovery rate formulation for statistical inference on local patch-based samples. This alternative error metric allows to efficiently adjust the family-wise error rate in case of the considered large-scale testing problem. The designed change detector operates in an un-supervised manner under the assumption of the limited amount of changes in the analyzed imagery. The detection is based in the use of various statistical features, which enable the detector to address application-specific detection problems provided an appropriate ad hoc feature choice. In particular, we demonstrate the use of the rank-based statistics: Wilcoxon and Cramér-von Mises for image pairs, and multisample Levene statistic for short image sequences. The experiments with remotely sensed radar, dermatological, and still camera surveillance imagery demonstrate accurate performance and flexibility of the proposed method.

International audience; In this paper, we propose a connected-tube model based on a Marked Point Process (MPP) for strip feature extraction in images. This model incorporates a connection prior that favors certain connections between tubes based on their mutual positional relationship. Moreover, this model can easily be combined with other geometric models to form a mixed MPP model for more complex detection tasks. The proposed tube model is applied to fiber detection in microscopy images by combining connected-tube and ellipse models. The ellipse model is used for detecting short fibers, while the longer fibers are detected by tube model. We also test the model on road and building detection in remotely sensed images.

International audience; This book maximizes reader insights into the field of mathematical models and methods for the processing of two-dimensional remote sensing images. It presents a broad analysis of the field, encompassing passive and active sensors, hyperspectral images, synthetic aperture radar (SAR), interferometric SAR, and polarimetric SAR data. At the same time, it addresses highly topical subjects involving remote sensing data types (e.g., very high-resolution images, multiangular or multiresolution data, and satellite image time series) and analysis methodologies (e.g., probabilistic graphical models, hierarchical image representations, kernel machines, data fusion, and compressive sensing) that currently have primary importance in the field of mathematical modelling for remote sensing and image processing. Each chapter focuses on a particular type of remote sensing data and/or on a specific methodological area, presenting both a thorough analysis of the previous literature and a methodological and experimental discussion of at least two advanced mathematical methods for information extraction from remote sensing data. This organization ensures that both tutorial information and advanced subjects are covered. With each chapter being written by research scientists from (at least) two different institutions, it offers multiple professional experiences and perspectives on each subject. The book also provides expert analysis and commentary from leading remote sensing and image processing researchers, many of whom serve on the editorial boards of prestigious international journals in these fields, and are actively involved in international scientific societies. Providing the reader with a comprehensive picture of the overall advances and the current cutting-edge developments in the field of mathematical models for remote sensing image analysis, this book is ideal as both a reference resource and a textbook for graduate and doctoral students as well as for remote sensing scientists and practitioners.

International audience; Current and forthcoming sensor technologies and space missions are providing remote sensing scientists and practitioners with an increasing wealth and variety of data modalities. They encompass multisensor, multiresolution, multiscale, multitemporal, multipolarization, and multifrequency imagery. While they represent remarkable opportunities for the applications, they pose important challenges to the development of mathematical methods aimed at fusing the information conveyed by the input multisource data. In this framework, the present chapter continues the discussion of remote sensing data fusion, which was opened in the previous chapter. Here, the focus is on data fusion for image classification purposes. Both methodological issues of feature extraction and supervised classification are addressed. On both respects, the focus is on hierarchical image models rooted in graph theory. First, multilevel feature extraction is addressed through the latest advances in Mathematical Morphology and attribute profile theory with respect to component trees and trees of shapes. Then, joint supervised classification of multisensor, multiscale, multiresolution, and multitemporal imagery is formulated through hierarchical Markov random fields on quad-trees. Examples of experimental results with data from current VHR optical and SAR missions are shown and analysed.

International audience; Visual assessment is the most common clinical investigation of skin reactions in radiotherapy. Due to the subjective nature of this method, additional noninvasive techniques are needed for more accurate evaluation. Our goal is to evaluate the effectiveness of hyperspectral image analysis for that purpose. In this pilot study, we focused on detection and grading of skin Erythema. This paper reports our proposed processing pipeline and experimental findings. Experiments have been performed to demonstrate the efficacy of the proposed approach for (1) reproducing clinical assessments, and (2) outperforming RGB imaging data.

This letter proposes two methods for the supervised classification of multisensor optical and synthetic aperture radar images with possibly different spatial resolutions. Both the methods are formulated within a unique framework based on hierarchical Markov random fields. Distinct quad-trees associated with the individual information sources are defined to jointly address multisensor, multiresolution, and possibly multifrequency fusion, and are integrated with finite mixture models and the marginal posterior mode criterion. Experimental validation is conducted with Pleiades, COSMO-SkyMed, RADARSAT-2, and GeoEye-1 data.

International audience; In this paper, we propose a novel method for the joint classification of both multidate and multiresolution remote sensing imagery, which represents an important and relatively unexplored classification problem. The proposed classifier is based on an explicit hierarchical graph-based model that is sufficiently flexible to address co-registered time series of images collected at different spatial resolutions. Within this framework, a novel element of the proposed approach is the use of multiple quad-trees in cascade, each associated with the images available at each observation date in the considered time series. For each date, the input images are inserted in a hierarchical structure on the basis of their resolutions, whereas missing levels are filled in with wavelet transforms of the images embedded in finer-resolution levels. This approach is aimed at both exploiting multiscale information, which is known to play a crucial role in high resolution image analysis, and supporting input images acquired at different resolutions in the input time series. The experimental results are shown for multitemporal and multiresolution optical data. Index Terms— Satellite image time series, multitemporal classification, hierarchical multiresolution Markov random fields.

Marked point processes provide a rigorous framework to describe a scene by an unordered set of objects. The efficiency of this modeling has been shown on line network extraction with models manipulating interacting segments. In this paper, we extend this previous modeling to polylines composed of an unknown number of segments. Optimization is done via simulated annealing using a Reversible Jump Markov Chain Monte Carlo (RJMCMC) algorithm. We accelerate the convergence of the algorithm by using appropriate proposal kernels. Results on aerial and satellite images show that this new model outperforms the previous one.

International audience; We present a new approach for building reconstruction from a single Digital Surface Model (DSM). It treats buildings as an assemblage of simple urban structures extracted from a library of 3D parametric blocks (like a LEGO set). First, the 2D-supports of the urban structures are extracted either interactively or automatically. Then, 3D-blocks are placed on the 2D-supports using a Gibbs model which controls both the block assemblage and the fitting to data. A Bayesian decision finds the optimal configuration of 3D-blocks using a Markov Chain Monte Carlo sampler associated with original proposition kernels. This method has been validated on multiple data set in a wide-resolution interval such as 0.7 m satellite and 0.1 m aerial DSMs, and provides 3D representations on complex buildings and dense urban areas with various levels of detail.

This paper addresses the problem of updating digital road maps in dense urban areas by extracting the main road network from very high resolution (VHR) satellite images. Building on the work of Rochery et al. (2005), we represent the road region as a ldquophase fieldrdquo. In order to overcome the difficulties due to the complexity of the information contained in VHR images, we propose a multiscale statistical data model. It enables the integration of segmentation results from coarse resolution, which furnishes a simplified representation of the data, and fine resolution, which provides accurate details. Moreover, an outdated GIS digital map is introduced into the model, providing specific prior knowledge of the road network. This new term balances the effect of the generic prior knowledge describing the geometric shape of road networks (i.e., elongated and of low-curvature) carried by a ldquophase field higher order active contourrdquo term. Promising results on QuickBird panchromatic images and comparisons with several other methods demonstrate the effectiveness of our approach.

International audience; In this paper, we present an automatic building extraction method from Digital Elevation Models based on an object approach. First, a rough approximation of the building footprints is realized by a method based on marked point processes: the building footprints are modeled by rectangle layouts. Then, these rectangular footprints are regularized by improving the connection between the neighboring rectangles and detecting the roof height discontinuities. The obtained building footprints are structured footprints: each element represents a specific part of an urban structure. Results are finally applied to a 3D-city modeling process.

International audience; This paper presents image-based quantitative evaluation of subtle variations in facial wrinkles for the same subject in response to a dermatological treatment. This is a novel application because the time series images of the same subject over a shorter time period of weeks are analyzed as compared to more prevalent inter-person analysis of facial skin/marks. We propose image features based on Gabor filter bank for an accurate quantitative evaluation of variations in facial wrinkles. Since variations in Gabor features are very small on a time period of weeks, we propose a framework to compare image features in key wrinkle sites only while excluding the noise introduced by non-wrinkle sites. The framework consists of finer registration of images using Large Deformation Diffeo-morphic Metric Mapping (LDDMM) and detection of wrinkle sites using Gabor filter bank and morphological image processing. Preliminary experiments show that the framework is useful in calculating variations in Gabor features at detected sites and indicating trends in the response of facial wrinkles to the dermatological treatment.

In this paper, we develop a novel classification approach for multiresolution, multisensor (optical and synthetic aperture radar), and/or multiband images. Accurate and time-efficient classification methods are particularly important tools to support rapid and reliable assessment of the ground changes. Given the huge amount and variety of data available currently from last-generation satellite missions, the main difficulty is to develop a classifier that can take benefit of multiband, multiresolution, and multisensor input imagery. The proposed method addresses the problem of multisensor fusion of SAR with optical data for classification purposes, and allows input data collected at multiple resolutions and additional multiscale features derived through wavelets to be fused.

International audience; In this paper, we present a novel approach based on spatio-temporal marked point processes to detect and track moving objects in a batch of high resolution images. Batch processing techniques are applicable to and desirable for a large class of applications such as offline scene and video analysis, and provide better overall detection and data as-sociation accuracy than sequential methods. We develop a new, intuitive energy based model consisting of several terms that take into account both the image evidence and physical constraints such as target dynamics, track persis-tence and mutual exclusion. We construct a suitable op-timization scheme that allows us to find strong local min-ima of the proposed highly non-convex energy. We test our model on three batches of 25 synthetic biological images with different levels of noise. Our main application however consists of two batches of 14 remotely sensed high resolu-tion optical images of boats which are particularly hard to analyze due to the different angles at which the images were taken and the low temporal frequency.

International audience; The presence of illumination variation in dermatological images has a negative impact on the automatic detection and analysis of cutaneous lesions. This paper proposes a new illumination modeling and chromophore identication method to correct lighting variation in skin lesion images, as well as to extract melanin and hemoglobin concentrations of human skin, based on an adaptive bilateral decomposition and a weighted polynomial curve tting, with the knowledge of a multi-layered skin model. Different from state-of-the-art approaches based on the Lambert law, the proposed method, considering both specular reection and diffuse reection of the skin, enables us to address highlight and strong shading effects usually existing in skin color images captured in an uncontrolled environment. The derived melanin and hemoglobin indices, directly relating to the pathological tissue conditions, tend to be less inuenced by external imaging factors and are more efcient in describing pigmentation distributions. Experiments show that the proposed method gave better visual results and superior lesion segmentation, when compared to two other illumination correction algorithms, both designed specically for dermatological images. For computer-aided diagnosis of melanoma, sensitivity achieves 85.52% when using our chromophore descriptors, which is 8~20% higher than those derived from other color descriptors. This demonstrates the benet of the proposed method for automatic skin disease analysis.

International audience; This paper addresses the problem of multisensor fusion of COSMO-SkyMed and RADARSAT-2 data together with optical imagery for classification purposes. The proposed method is based on an explicit hierarchical graph-based model that is sufficiently flexible to deal with multisource coregistered images collected at different spatial resolutions by different sensors. An especially novel element of the proposed approach is the use of multiple quad-trees in cascade, each associated with a set of images acquired by different SAR sensors, with the aim to characterize the correlations associated with distinct images from different instruments. Experimental results are shown with COSMO-SkyMed, RADARSAT-2, and Pléiades data 1 .

International audience; In this paper, we give a comparative study on three Multilayer Markov Random Field (MRF) based solutions proposed for change detection in optical remote sensing images, called Multicue MRF, Conditional Mixed Markov model, and Fusion MRF. Our pur-poses are twofold. On one hand, we highlight the significance of the focused model family and we set them against various state-of-the-art approaches through a thematic analysis and quantitative tests. We discuss the advantages and drawbacks of class comparison vs. direct approaches, usage of training data, various targeted application fields and different ways of ground truth generation, meantime informing the Reader in which roles the Multilayer MRFs can be efficiently applied. On the other hand we also emphasize the differences between the three focused models at various levels, considering the model structures, feature extraction, layer interpretation, change concept definition, parameter tuning and performance. We provide qualitative and quan-titative comparison results using principally a publicly available change detection database which contains aerial image pairs and Ground Truth change masks. We conclude that the discussed models are competitive against alternative state-of-the-art solutions, if one uses them as pre-processing filters in multitemporal optical image analysis. In addition, they cover together a large range of applications, considering the different usage options of the three approaches.

This work presents an automatic algorithm for extracting vectorial land registers from altimetric data in dense urban areas. We focus on elementary shape extraction and propose a method that extracts rectangular buildings. The result is a vectorial land register that can be used, for instance, to perform precise roof shape estimation. Using a spatial point process framework, we model towns as configurations of and unknown number of rectangles. An energy is defined, which takes into account both low level information provided by the altimetry of the scene, and geometric knowledge about the disposition of buildings in towns. Estimation is done by minimizing the energy using simulated annealing. We use an MCMC sampler that is a combination of general Metropolis Hastings Green techniques and the Geyer and Moller algorithm for point process sampling. We define some original proposition kernels, such as birth or death in a neighborhood and define the energy with respect to an inhomogeneous Poisson point process. We present results on real data provided by the IGN (French National Geographic Institute). Results were obtained automatically. These results consist of configurations of rectangles describing a dense urban area.

This paper addresses the problem of unsupervised extraction of line networks (for example, road or hydrographic networks) from remotely sensed images. We model the target line network by an object process, where the objects correspond to interacting line segments. The prior model, called "Quality Candy," is designed to exploit as fully as possible the topological properties of the network under consideration, while the radiometric properties of the network are modeled using a data term based on statistical tests. Two techniques are used to compute this term: one is more accurate, the other more efficient. A calibration technique is used to choose the model parameters. Optimization is done via simulated annealing using a Reversible Jump Markov Chain Monte Carlo (RJMCMC) algorithm. We accelerate convergence of the algorithm by using appropriate proposal kernels. The results obtained on satellite and aerial images are quantitatively evaluated with respect to manual extractions. A comparison with the results obtained using a previous model, called the "Candy" model, shows the interest of adding quality coefficients with respect to interactions in the prior density. The relevance of using an offline computation of the data potential is shown, in particular, when a proposal kernel based on this computation is added in the RJMCMC algorithm.

Texture analysis has been widely investigated in the monospectral and multispectral imagery domains. At the same time, new image sensors with a large number of bands (more than ten) have been designed. They are able to provide images with both fine spectral and spatial sampling, and are called hyperspectral images. The aim of this work is to perform a joint texture analysis in both discrete spaces. To achieve this goal, we propose a probabilistic vector texture model, using a Gauss-Markov random field (MRF). The MRF parameters allow the characterization of different hyperspectral textures. A possible application of this work is the classification of urban areas. These areas are not well characterized by radiometry alone, and so we use the MRF parameters as new features in a maximum-likelihood classification algorithm. The results obtained on Airborne Visible/Infrared Imaging Spectrometer hyperspectral images demonstrate that a better classification is achieved when texture information is included in the analysis.

In this paper we propose a new method for the extraction of roads from remotely sensed images. Under the assumption that roads form a thin network in the image, we approximate such a network by connected line segments. To perform this task, we construct a point process able to simulate and detect thin networks. The segments have to be connected, in order to form a line-network. Aligned segments are favored whereas superposition is penalized. These constraints are enforced by the interaction model (called the Candy model). The specific properties of the road network in the image are described by the data term. This term is based on statistical hypothesis tests. The proposed probabilistic model can be written within a Gibbs point process framework. The estimate for the network is found by minimizing an energy function. In order to avoid local minima, we use a simulated annealing algorithm, based on a Monte Carlo dynamics (RJMCMC) for finite point processes. Results are shown on SPOT, ERS and aerial images.

In this article, we consider the marked point process framework for image analysis. We first show that marked point processes are more adapted than Markov random fields (MRFs) including some geometrical constraints in the solution and dealing with strongly correlated noise. Then, we consider three applications in remote sensing: road network extraction, building extraction, and image segmentation. For each of them, we define a prior model, incorporating geometrical constraints on the solution. We also derive a reversible jump Monte Carlo Markov chains (RJMCMC) algorithm to obtain the optimal solution with respect to the defined models. Results show that this approach is promising and can be applied to a broad range of image processing problems.

International audience; In this paper, we propose a novel method for the joint classification of multidate, multiresolution and multisensor remote sensing imagery, which represents a vital and fairly unexplored classification problem. The proposed classifier is based on an explicit hierarchical graph-based model sufficiently flexible to deal with multisource coregistered time series of images collected at different spatial resolutions. An especially novel element of the proposed approach is the use of multiple quad-trees in cascade, each associated with each new available image at different dates, with the aim to characterize the temporal correlations associated with distinct images in the input time series. Experimental results are shown with multitemporal and multiresolution Pléiades data

International audience; In this paper, we propose a novel method to fuse multidate, multiresolution, and multiband remote sensing imagery for multitemporal classification purposes. The proposed method is based on an explicit hierarchical graph-based model that is sufficiently flexible to deal with multisource coregistered time series of images collected at different spatial resolutions. An especially novel element of the proposed approach is the use of multiple quad-trees in cascade, each associated with an image acquired at a different date, with the aim to characterize the temporal correlations associated with distinct images in an input time series. Experimental results are shown with multitemporal and multiresolution Pléiades data.

International audience; In this paper we develop a novel classification approach for multi-resolution, multi-sensor (optical and synthetic aperture radar, SAR) and/or multi-band images. This challenging image processing problem is of great importance for various remote sensing monitoring applications and has been scarcely addressed so far. To deal with this classification problem, we propose a two-step explicit statistical model. We first design a model for the multivariate joint class-conditional statistics of the co-registered input images at each resolution by resorting to multivariate copulas. Such copulas combine the class-conditional marginal probability density functions of each input channel that are estimated by finite mixtures of well-chosen parametric families. We consider different distribution families for the most common types of remote sensing imagery acquired by optical and SAR sensors. We then plug the estimated joint probability density functions into a hierarchical Markovian model based on a quad-tree structure, where each tree-scale corresponds to the different input image resolutions and to corresponding multi-scale decimated wavelet transforms, thus preventing a strong resampling of the initial images. To obtain the classification map, we resort to an exact estimator of the marginal posterior mode. We integrate a prior update in this model in order to improve the robustness of the developed classifier against noise and speckle. The resulting classification performance is illustrated on several remote sensing multi-resolution datasets including very high resolution and multi-sensor images acquired by COSMO-SkyMed and GeoEye-1.

Markovian approaches to early vision processes need a huge amount of computing power. These algorithms can usually be implemented on parallel computing structures. Herein, we show that the Markovian labeling approach can be implemented in fully parallel cellular network architectures, using simple functions and data representations. This makes possible to implement our model in parallel imaging VLSI chips.As an example, we have developed a simplified statistical image segmentation algorithm for the Cellular Neural/Nonlinear Networks Universal Machine (CNN-UM), which is a new image processing tool, containing thousands of cells with analog dynamics, local memories and processing units. The Modified Metropolis Dynamics (MMD) optimization method can be implemented into the raw analog architecture of the CNN-UM. We can introduce the whole pseudo-stochastic segmentation process in the CNN architecture using 8 memories/cell. We use simple arithmetic functions (addition, multiplication), equality-test between neighboring pixels and very simple nonlinear output functions (step, jigsaw). With this architecture, the proposed VLSI CNN chip can execute a pseudo-stochastic relaxation algorithm of about 100 iterations in about 100 ?s.In the suggested solution the segmentation is unsupervised, where a pixel-level statistical estimation model is used. We have tested different monogrid and multigrid architectures.In our CNN-UM model several complex preprocessing steps can be involved, such as texture-classification or anisotropic diffusion. With these preprocessing steps, our fully parallel cellular system may work as a high-level image segmentation machine, using only simple functions based on the close-neighborhood of a pixel.

Markovian approaches to early vision processes need a huge amount of computing power. These algorithms can usually be implemented on parallel computing structures. With the Cellular Neural Networks (CNN), a new image processing tool is coming into consideration. Its VLSI implementation takes place on a single analog chip containing several thousands of cells. Herein we use the CNN UM architecture for statistical image segmentation. The Modified Metropolis Dynamics (MMD) method can be implemented into the raw analog architecture of the CNN. We are able to implement a (pseudo) random field generator using one layer (one memory/cell) of the CNN. We can introduce the whole pseudostochastic segmentation process in the CNN architecture using 8 memories/cell. We use simple arithmetic functions (addition, multiplication), equality-test between neighboring pixels and very simple nonlinear output functions (step, jigsaw). With this architecture, a real VLSI CNN chip can execute a pseudostochastic relaxation algorithm of about 100 iterations in about 1 ms. In the proposed solution the segmentation is unsupervised. We have developed a pixel-level statistical estimation model. The CNN turns the original image into a smooth one. Then we have two gray-level values for every pixel: the original and the smoothed one. These two values are used for estimating the probability distribution of region label at a given pixel. Using the conventional first-order Markov Random Field (MRF) model, some misclassification errors remained at the region boundaries, because of the estimation difficulties in case of low SNR. By using a greater neighborhood, this problem has been avoided. In our CNN experiments, we used a simulation system with a fixed-point integer precision of 16 bits. Our results show that even in the case of the very constrained conditions of value-representations (the interval is (-64,+64), the accuracy is 0.002) can result in an effective and acceptable segmentation.

International audience; In this paper we address the problem of unsupervised change detection on image pairs. We develop a novel patch-based hypothesis testing approach that employs the false discovery rate technique for statistical hypothesis testing. The designed approach can be adopted to specific detection applications via selection of appropriate statistical features. Experiments with still camera imagery demonstrate high performance and flexibility of the proposed method.

International audience; Marked point process models have been successfully used in image analysis for feature extraction purposes in high resolution remotely sensed images. The model is usually based on two types of energy terms: a data term, which reflects the configuration's fidelity with respect to the input image, and a prior term, which reflects some knowledge about the objects to be extracted. In this paper, we deal with the problem of elliptical shape extraction. We propose new energy terms for the extraction of boats in harbors, which is a particularly difficult problem and we show results on high resolution optical images.

International audience; In this paper, we use statistical inference and muti-spectral images to quantify the evolution of skin hyper-pigmentation lesions under treatment. We show that statistical inference allows getting change maps of the disease which can be useful for dermatologists to analyze the disease evolution. Indeed, a local change map is obtained by computing the deviation between two multi-spectral images in a region of interest (ROI). Then, we normalize the obtained map and develop a statistical inference framework to quantify the changes. Finally, we propose a criterion that integrates change maps in order to quantify the treatment efficacy on a patient.

International audience; In this paper we discuss the main characteristics (that we consider to be essential) for the design of an efficient optimizer in the context of highly non-convex functions. We consider a specific model known as Marked Point Process (MPP). Given that the probability density is multimodal, and given the size of the configuration space, an exploration phase is essential at the beginning of the algorithm. Next, the fine details of the density function should be discovered. We propose efficient kernels to efficiently explore the different modes of the density, and other kernels to discover the details of each mode. We study the algorithm theoretically to express convergence speeds and to select its best parameters. We also present a simple and generic method to parallelize the optimization of a specific class of MPP models. We validate our ideas first on synthetic data of configurations of different sizes to prove the efficiency of the proposed kernels. Finally we present results on three different applications.

International audience; We combine both amplitude and texture statistics of the Synthetic Aperture Radar (SAR) images for modelbased classification purpose. In a finite mixture model, we bring together the Nakagami densities to model the class amplitudes and a 2D Auto-Regressive texture model with t-distributed regression error to model the textures of the classes. A nonstationary Multinomial Logistic (MnL) latent class label model is used as a mixture density to obtain spatially smooth class segments. The Classification Expectation-Maximization (CEM) algorithm is performed to estimate the class parameters and to classify the pixels. We resort to Integrated Classification Likelihood (ICL) criterion to determine the number of classes in the model. We present our results on the classification of the land covers obtained in both supervised and unsupervised cases processing TerraSAR-X, as well as COSMO-SkyMed data.

International audience; This letter addresses the problem of classifying synthetic aperture radar (SAR) images of urban areas by using a supervised Bayesian classification method via a contextual hierarchical approach. We develop a bivariate copula-based statistical model that combines amplitude SAR data and textural information, which is then plugged into a hierarchical Markov random field model. The contribution of this letter is thus the development of a novel hierarchical classification approach that uses a quad-tree model based on wavelet decomposition and an innovative statistical model. The performance of the developed approach is illustrated on a high-resolution satellite SAR image of urban areas.

Given a set of low resolution camera images of a Lambertian surface, it is possible to reconstruct high resolution luminance and height information, when the relative displacements of the image frames are known. We have proposed iterative algorithms for recovering high resolution albedo with the knowledge of high resolution height and vice versa. The problem of surface reconstruction has been tackled in a Bayesian framework and has been formulated as one of minimizing an error function. Markov Random Fields (MRF) have been employed to characterize the a priori constraints on the solution space. As for the surface height, we have attempted a direct computation without refering to surface orientations, while increasing the resolution by camera jittering.

International audience; This paper considers change detection with multitemporal synthetic aperture radar (SAR) images. A novel statistical approach is developed that formulates the detection of changes between two coregistered SAR images acquired at different dates as a non-parametric local-window hypothesis testing problem. This approach takes into account the simultaneous testing of a large amount of similar hypotheses (i.e., one Wilcoxon test at each pixel of the image), and is based on a likelihood ratio test to obtain a detection map at the pixel level. Some encouraging detection results are obtained on XSAR and very high resolution COSMO-SkyMed images.

International audience; In the framework of the monitoring of structures and infrastructures from environmental disasters, the COSMO-SkyMed constellation has a huge potential, thanks to up to metric spatial resolution, short revisit time, and the day/night all-weather acquisition capability ensured by SAR. This paper focuses on the scientific results of the project "Development and validation of multitemporal image analysis methodologies for multirisk monitoring of critical structures and infrastructures," funded by the Italian Space Agency. Several change-detection, data-fusion, and feature-extraction techniques, which were developed and experimentally validated in the project for COSMO-SkyMed imagery and for their integration with other data sources (including very high resolution optical data), are described and examples of processing results are discussed.

We propose an unsupervised classification algorithm for high resolution Synthetic Aperture Radar (SAR) images based on Classification Expectation-Maximization (CEM). We combine the CEM algorithm with the hierarchical agglomeration strategy and a model order selection criterion called Integrated Completed Likelihood (ICL) to get rid of the initialization and the model order selection problems of the EM algorithm. We exploit a mixture of Nakagami densities for amplitudes and a Multinomial Logistic (MnL) latent model for class labels to obtain spatially smooth class segments. We test our algorithm on TerraSAR-X data.

International audience; We implement an unsupervised classification algorithm for high resolution Synthetic Aperture Radar (SAR) images. The foundation of algorithm is based on Classification Expectation-Maximization (CEM). To get rid of two drawbacks of EM type algorithms, namely the initialization and the model order selection, we combine the CEM algorithm with the hierarchical agglomeration strategy and a model order selection criterion called Integrated Completed Likelihood (ICL). We exploit amplitude statistics in a Finite Mixture Model (FMM), and a Multinomial Logistic (MnL) latent class label model for a mixture density to obtain spatially smooth class segments. We test our algorithm on TerraSAR-X data.

International audience; In this paper we focus on the fundamental synthetic aperture radars (SAR) image processing problem of supervised classification. To address it we consider a statistical finite mixture approach to probability density function estimation. We develop a generalized approach to address the problem of mixture estimation and consider the use of several different classes of distributions as the base for mixture approaches. This allows performing the maximum likelihood classification which is then refined by Markov random field approach, and optimized by graph cuts. The developed method is experimentally validated on high resolution SAR imagery acquired by Cosmo-SkyMed and TerraSAR-X satellite sensors.

International audience; Clinical evaluation of skin treatments consists of two steps. First, the degree of the disease is measured clinically on a group of patients by dermatologists. Then, a statistical test is used on obtained set of measures to determine the treatment efficacy. In this paper, a method is proposed to automatically measure the severity of skin hyperpigmentation. After a classification step, an objective function is designed in order to obtain an optimal linear combination of bands defining the severity criterion. Then a hypothesis test is deployed on this combination to quantify treatment efficacy.