Max Mignotte

Sonar image segmentation using an unsupervised hierarchical MRF model

This paper is concerned with hierarchical Markov random field (MRP) models and their application to sonar image segmentation. We present an original hierarchical segmentation procedure devoted to images given by a high-resolution sonar. The sonar image is segmented into two kinds of regions: shadow (corresponding to a lack of acoustic reverberation behind each object lying on the sea-bed) and sea-bottom reverberation. The proposed unsupervised scheme takes into account the variety of the laws in the distribution mixture of a sonar image, and it estimates both the parameters of noise distributions and the parameters of the Markovian prior. For the estimation step, we use an iterative technique which combines a maximum likelihood approach (for noise model parameters) with a least-squares method (for MRF-based prior). In order to model more precisely the local and global characteristics of image content at different scales, we introduce a hierarchical model involving a pyramidal label field. It combines coarse-to-fine causal interactions with a spatial neighborhood structure. This new method of segmentation, called the scale causal multigrid (SCM) algorithm, has been successfully applied to real sonar images and seems to be well suited to the segmentation of very noisy images. The experiments reported in this paper demonstrate that the discussed method performs better than other hierarchical schemes for sonar image segmentation.

3D/2D registration and segmentation of scoliotic vertebrae using statistical models

We propose a new 3D/2D registration method for vertebrae of the scoliotic spine, using two conventional radiographic views (postero-anterior and lateral), and a priori global knowledge of the geometric structure of each vertebra. This geometric knowledge is efficiently captured by a statistical deformable template integrating a set of admissible deformations, expressed by the first modes of variation in Karhunen-Loeve expansion, of the pathological deformations observed on a representative scoliotic vertebra population. The proposed registration method consists of fitting the projections of this deformable template with the preliminary segmented contours of the corresponding vertebra on the two radiographic views. The 3D/2D registration problem is stated as the minimization of a cost function for each vertebra and solved with a gradient descent technique. Registration of the spine is then done vertebra by vertebra. The proposed method efficiently provides accurate 3D reconstruction of each scoliotic vertebra and, consequently, it also provides accurate knowledge of the 3D structure of the whole scoliotic spine. This registration method has been successfully tested on several biplanar radiographic images and validated on 57 scoliotic vertebrae. The validation results reported in this paper demonstrate that the proposed statistical scheme performs better than other conventional 3D reconstruction methods.

Segmentation by Fusion of Histogram-Based

This paper presents a new, simple, and efficient segmentation approach, based on a fusion procedure which aims at combining several segmentation maps associated to simpler partition models in order to finally get a more reliable and accurate segmentation result. The different label fields to be fused in our application are given by the same and simple (K-means based) clustering technique on an input image expressed in different color spaces. Our fusion strategy aims at combining these segmentation maps with a final clustering procedure using as input features, the local histogram of the class labels, previously estimated and associated to each site and for all these initial partitions. This fusion framework remains simple to implement, fast, general enough to be applied to various computer vision applications (e.g., motion detection and segmentation), and has been successfully applied on the Berkeley image database. The experiments herein reported in this paper illustrate the potential of this approach compared to the state-of-the-art segmentation methods recently proposed in the literature.

K

Falls are one of the major risks for seniors living alone at home. Computer vision systems, which do not require to wear sensors, offer a new and promising solution for fall detection. In this work, an occlusion robust method is presented based on two features: human centroid height relative to the ground and body velocity. Indeed, the first feature is an efficient solution to detect falls as the vast majority of falls ends on the ground or near the ground. However, this method can fail if the end of the fall is completely occluded behind furniture. Fortunately, these cases can be managed by using the 3D person velocity computed just before the occlusion.

-Means Clusters in Different Color Spaces

This paper presents a new and accurate three-dimensional (3-D) reconstruction technique for the scoliotic spine from a pair of planar and conventional (postero-anterior with normal incidence and lateral) calibrated radiographic images. The proposed model uses a priori hierarchical global knowledge, both on the geometric structure of the whole spine and of each vertebra. More precisely, it relies on the specification of two 3-D statistical templates. The first, a rough geometric template on which rigid admissible deformations are defined, is used to ensure a crude registration of the whole spine. An accurate 3-D reconstruction is then performed for each vertebra by a second template on which nonlinear admissible global, as well as local deformations, are defined. Global deformations are modeled using a statistical modal analysis of the pathological deformations observed on a representative scoliotic vertebra population. Local deformations are represented by a first-order Markov process. This unsupervised coarse-to-fine 3-D reconstruction procedure leads to two separate minimization procedures efficiently solved in our application with evolutionary stochastic optimization algorithms. In this context, we compare the results obtained with a classical genetic algorithm (GA) and a recent Exploration Selection (ES) technique. This latter optimization method with the proposed 3-D reconstruction model, is tested on several pairs of biplanar radiographic images with scoliotic deformities. The experiments reported in this paper demonstrate that the discussed method is comparable in terms of accuracy with the classical computed-tomography-scan technique while being unsupervised and while requiring only two radiographic images and a lower amount of radiation for the patient.

Fall detection from depth map video sequences

This paper presents an original method for analyzing, in an unsupervised way, images supplied by high resolution sonar. We aim at segmenting the sonar image into three kinds of regions: echo areas (due to the reflection of the acoustic wave on the object), shadow areas (corresponding to a lack of acoustic reverberation behind an object lying on the sea-bed), and sea-bottom reverberation areas. This unsupervised method estimates the parameters of noise distributions, modeled by a Weibull probability density function (PDF), and the label field parameters, modeled by a Markov random field (MRF). For the estimation step, we adopt a maximum likelihood technique for the noise model parameters and a least-squares method to estimate the MRF prior model. Then, in order to obtain an accurate segmentation map, we have designed a two-step process that finds the shadow and the echo regions separately, using the previously estimated parameters. First, we introduce a scale-causal and spatial model called SCM (scale causal multigrid), based on a multigrid energy minimization strategy, to find the shadow class. Second, we propose a MRF monoscale model using a priori information (at different level of knowledge) based on physical properties of each region, which allows us to distinguish echo areas from sea-bottom reverberation. This technique has been successfully applied to real sonar images and is compatible with automatic processing of massive amounts of data.

A hierarchical statistical modeling approach for the unsupervised 3-D biplanar reconstruction of the scoliotic spine

Most statistical background subtraction techniques are based on the analysis of temporal color/intensity distribution. However, learning statistics on a series of time frames can be problematic, especially when no frame absent of moving objects is available or when the available memory is not sufficient to store the series of frames needed for learning. In this letter, we propose a spatial variation to the traditional temporal framework. The proposed framework allows statistical motion detection with methods trained on one background frame instead of a series of frames as is usually the case. Our framework includes two spatial background subtraction approaches suitable for different applications. The first approach is meant for scenes having a nonstatic background due to noise, camera jitter or animation in the scene (e.g.,waving trees, fluttering leaves). This approach models each pixel with two PDFs: one unimodal PDF and one multimodal PDF, both trained on one background frame. In this way, the method can handle backgrounds with static and nonstatic areas. The second spatial approach is designed to use as little processing time and memory as possible. Based on the assumption that neighboring pixels often share similar temporal distribution, this second approach models the background with one global mixture of Gaussians.

Three-Class Markovian Segmentation of High-Resolution Sonar Images

We present an original statistical classification method using a deformable template model to separate natural objects from man-made objects in an image provided by a high resolution sonar. A prior knowledge of the manufactured object shadow shape is captured by a prototype template, along with a set of admissible linear transformations, to take into account the shape variability. Then, the classification problem is defined as a two-step process: 1) the detection problem of a region of interest in the input image is stated as the minimization of a cost function; and 2) the value of this function at convergence allows one to determine whether the desired object is present or not in the sonar image. The energy minimization problem is tackled using relaxation techniques. In this context, we compare the results obtained with a deterministic relaxation technique and two stochastic relaxation methods: simulated annealing and a hybrid genetic algorithm. This latter method has been successfully tested on real and synthetic sonar images, yielding very promising results.

Statistical Background Subtraction Using Spatial Cues

This paper presents a novel segmentation approach based on a Markov random field (MRF) fusion model which aims at combining several segmentation results associated with simpler clustering models in order to achieve a more reliable and accurate segmentation result. The proposed fusion model is derived from the recently introduced probabilistic Rand measure for comparing one segmentation result to one or more manual segmentations of the same image. This non-parametric measure allows us to easily derive an appealing fusion model of label fields, easily expressed as a Gibbs distribution, or as a nonstationary MRF model defined on a complete graph. Concretely, this Gibbs energy model encodes the set of binary constraints, in terms of pairs of pixel labels, provided by each segmentation results to be fused. Combined with a prior distribution, this energy-based Gibbs model also allows for definition of an interesting penalized maximum probabilistic rand estimator with which the fusion of simple, quickly estimated, segmentation results appears as an interesting alternative to complex segmentation models existing in the literature. This fusion framework has been successfully applied on the Berkeley image database. The experiments reported in this paper demonstrate that the proposed method is efficient in terms of visual evaluation and quantitative performance measures and performs well compared to the best existing state-of-the-art segmentation methods recently proposed in the literature.

Hybrid genetic optimization and statistical model based approach for the classification of shadow shapes in sonar imagery

Abstract: We present a new approach to shape-based segmentation and tracking of deformable anatomical structures in medical images, and validate this approach by detecting and tracking the endocardial contour in an echocardiographic image sequence. To this end, some global prior shape knowledge of the endocardial boundary is captured by a prototype template with a set of predefined global and local deformations to take into account its inherent natural variability over time. In this deformable model-based Bayesian segmentation, the data likelihood model relies on an accurate statistical modelling of the grey level distribution of each class present in the ultrasound image. The parameters of this distribution mixture are given by a preliminary iterative estimation step. This estimation scheme relies on a Markov Random Field prior model, and takes into account the imaging process as well as the distribution shape of each class present in the image. Then the detection and the tracking problem is stated in a Bayesian framework, where it ends up as a cost function minimisation problem for each image of the sequence. In our application, this energy optimisation problem is efficiently solved by a genetic algorithm combined with a steepest ascent procedure. This technique has been successfully applied on synthetic images, and on a real echocardiographic image sequence.