Abstract. We propose a new visual servo approach to automatically control in real-time the full motion of a 2D ultrasound (US) probe held by a medical robot in order to reach a desired image of motionless soft tissue object in B-mode ultrasound imaging. Combinations of image moments of the observed object cross-section are used as feedback information in the visual control scheme. These visual features are extracted in realtime from the US image thanks to a fast image segmentation method. Simulations performed with a static US volume containing an egg-shaped object, and ex-vivo experiments using a robotized US probe that interacts with a motionless rabbit heart immersed in water, show the validity of this new approach and its robustness to different perturbations. This method shows promise for a variety of US-guided medical interventions that require real-time servoing. 1

We present in this paper a way to perform a fast and robust image segmentation and to track a contour along a sequence of images. Our approach is based on a dynamic deformable model. More precisely, we revisit the physics basedmodel proposed in [1] to show the benefit of using a polar description to model the contour, in particular to cope with the well-known initialization problem. Indeed, we show that this way to proceed leads to diagonal and constant matrices in the equations of the snake evolution yielding therefore to a faster algorithm. Experimental results on image segmentation and contour tracking validate the efficiency of this new formulation. Index Terms — Active contour model, polar description, segmentation, contour tracking. 1.

This paper presents an optimal parametric active contour method based on Fourier descriptors to detect and track a contour from a sequence of images in real-time. The advantage of this approach is that not only convex but also concave contours can be considered. We also propose a method to initialize the active contour using only three user’s clicks in the first image of the sequence and to automatically re-initialize it when possible topological changes are detected during the tracking. Moreover, the algorithm is implemented on GPU to ensure the real-time tracking performance. Index Terms — Active contour, Fourier descriptors, contour tracking, ultrasound image

Abstract—Studies have shown that the Weibull distribution can model accurately a wide variety of images. Its parameters index a family of distributions which includes the exponential and approximations of the Gaussian and the Raleigh models widely used in image segmentation. This study investigates the Weibull distribution in unsupervised image segmentation and classification by a variational method. The data term of the segmentation functional measures the conformity of the image intensity in each region to a Weibull distribution whose parameters are determined jointly with the segmentation. Minimization of the functional is implemented by active curves via level sets and consists of iterations of two consecutive steps: curve evolution via Euler–Lagrange descent equations and evaluation of the Weibull distribution parameters. Experiments with synthetic and real images are described which verify the validity of method and its implementation. Index Terms—Active curves, classification, image segmentation, statistical modeling, Weibull distribution.

Tracking can be achieved using region active contours based on homogeneity models (intensity, motion...). However the model complexity necessary to achieve a given accuracy might be prohibitive. Methods based on salient points may not extract enough of these for reliable motion estimation if the object is too homogeneous. Here we propose to compute the contour deformation based on its neighborhood. Motion estimation is performed at contour samples using a block matching approach. First, partial background masking is applied. Since outliers may then bias the motion estimation, a robust, nonparametric estimation using entropy as a similarity measure between blocks is proposed. Tracking results on synthetic and natural sequences are presented. Index Terms — Tracking, entropy, block matching, partial background masking

Abstract — The goal of this paper is to present a way to perform visual servoing tasks from color attributes. This approach can be seen as an extension of our previous papers based on the luminance [1], [2]. Indeed, as we did for the luminance, color attributes are directly used in the control law avoiding therefore any complex images processing as features extraction or matching. We propose in this paper several potential color features and then a way to select a priori the best choice among them with respect to the scene being observed. Experimental results validate as well the interest of using color attributes as visual features as our selection process. I.

This paper presents an optimal parametric active contour method based on Fourier descriptors to detect and track a contour from a sequence of images in real-time. The advantage of this approach is that not only convex but also concave contours can be considered. We also propose a method to initialize the active contour using only three user’s clicks in the first image of the sequence and to automatically re-initialize it when possible topological changes are detected during the tracking. Moreover, the algorithm is implemented on GPU to ensure the real-time tracking performance. Index Terms — Active contour, Fourier descriptors, contour tracking, ultrasound image

Abstract In this paper, we focus on statistical region-based active contour models where image features (e.g. intensity) are random variables whose distribution belongs to some parametric family (e.g. exponential) rather than confining ourselves to the special Gaussian case. In the framework developed in this paper, we consider the general case of regionbased terms involving functions of parametric probability densities, for which the anti-log-likelihood function is a special case. Using shape derivative tools, our effort focuses on constructing a general expression for the derivative of the energy (with respect to a domain), and on deriving the corresponding evolution speed. More precisely, we first show by an example that the estimator of the distribution parameters is crucial for the derived speed expression. On the one hand, when using the maximum likelihood (ML) estimator for these parameters, the evolution speed has a closed-form expression that depends simply on the probability density function. On the other hand, complicating additive terms appear when using other estimators, e.g. method of moments. We then proceed by stating a general result within the frame-