AbstractÐWe describe a new method of matching statistical models of appearance to images. A set of model parameters control modes of shape and gray-level variation learned from a training set. We construct an efficient iterative matching algorithm by learning the relationship between perturbations in the model parameters and the induced image errors. Index TermsÐAppearance models, deformable templates, model matching. 1

Active contour and surface models, also known as deformable models, are powerful image segmentation techniques. Geometric deformable models implemented using level set methods have advantages over parametric models due to their intrinsic behavior, parameterization independence, and ease of implementation. However, a long claimed advantage of geometric deformable models—the ability to automatically handle topology changes—turns out to be a liability in applications where the object to be segmented has a known topology that must be preserved. In this paper, we present a new class of geometric deformable models designed using a novel topology-preserving level set method, which achieves topology preservation by applying the simple point concept from digital topology. These new models maintain the other advantages of standard geometric deformable models including subpixel accuracy and production of nonintersecting curves or surfaces. Moreover, since the topology-preserving constraint is enforced efficiently through local computations, the resulting algorithm incurs only nominal computational overhead over standard geometric deformable models. Several experiments on simulated and real data are provided to demonstrate the performance of this new deformable model algorithm.

We address the problem of moving object segmentation using active contours. As far as segmentation of moving objects is concerned, region-based terms must be incorporated in the evolution equation of the active contour, in addition to classical boundary-based terms. In this paper, we propose a general framework for region-based active contours. Novel aspects of the segmentation method include a new Eulerian proof to compute the evolution equation of the active contour from the minimization of a criterion, and the introduction of functions named "descriptors" of the regions. In this proof, the dynamical scheme is directly introduced in the criterion before differentiation. With such a method, the case of descriptors depending on the evolution of the curve, i.e. depending upon features globally attached to the region, can readily be taken into account. The variation of these descriptors upon the evolution of the curve induces additional terms in the evolution equation of the active contour. The proof ensures the fastest decrease of the active contour towards a minimum of the criterion. Inside this theoretical framework, a set of descriptors is evaluated on real sequences for the detection of moving objects. 1.

Tracking objects using multiple cues yields more robust results. The well-known hidden Markov model (HMM) provides a powerful framework to incorporate multiple cues by expanding its observation. However, a plain HMM does not capture the inter-correlation between measurements of neighboring states when computing the transition probabilities. This can seriously damage the tracking performance. To overcome this difficulty, in this paper, we propose a new HMM framework targeted at contour-based object tracking. A joint probability data association filter (JPDAF) is used to compute the HMM's transition probabilities, taking into account the intercorrelated neighboring measurements. To ensure real-time performance, we have further developed an efficient method to calculate the data association probability via dynamic programming, which allows the proposed JPDAF-HMM to run comfortably at 30 frames/sec. This new tracking framework not only can easily incorporate various image cues (e.g., edge intensity, foreground region color and background region color), but also offers an on-line learning process to adapt to changes in the scene. To evaluate its tracking performance, we have applied the proposed JPDAF-HMM in various realworld video sequences. We report promising tracking results in complex environments. 1.

We present in this paper the design of an interactive tool for selecting objects using simple freehand sketches. The objective is to extract object boundaries precisely while requiring little skill and time from the user. The tool proposed achieves this objective by integrating user input and image computation in a two-phase algorithm. In the first phase, the input sketch is used along with a coarse global segmentation of the image to derive an initial selection and a triangulation of the region around the boundary. The triangles are used to formulate subproblems of local finer-grained segmentation and selection. Each of the subproblems is processed independently in the second phase, where a linear approximation of the local boundary as well as a local, finer-grained segmentation are computed. The approximate boundary is then used with the local segmentation to compute a final selection, represented with an alpha channel to fully capture diffused object boundaries. Experimental results show that the tool allows very simple sketches to be used to select objects with complex boundaries. Therefore, the tool has immediate applications in graphics systems for image editing, manipulation, synthesis, retrieval, and processing. 1

Abstract—This paper deals with fast image and video segmentation using active contours. Region-based active contours using level sets are powerful techniques for video segmentation, but they suffer from large computational cost. A parametric active contour method based on B-Spline interpolation has been proposed in [26] to highly reduce the computational cost, but this method is sensitive to noise. Here, we choose to relax the rigid interpolation constraint in order to robustify our method in the presence of noise: by using smoothing splines, we trade a tunable amount of interpolation error for a smoother spline curve. We show by experiments on natural sequences that this new flexibility yields segmentation results of higher quality at no additional computational cost. Hence, real-time processing for moving objects segmentation is preserved. I.

Object recognition and localization methods in RoboCup work on color segmented camera images. Unfortunately, color labeling can be applied to object recognition tasks only in very restricted environments, where different kinds of objects have different colors. To overcome these limitations we propose an algorithm named the Contracting Curve Density (CCD) algorithm for fitting parametric curves to image data. The method neither assumes object specific color distributions, nor specific edge profiles, nor does it need threshold parameters. Hence, no training phase is needed. In order to separate adjacent regions we use local criteria which are based on local image statistics. We apply the method to the problem of localizing the ball and show that the CCD algorithm reliably localizes the ball even in the presence of heavily changing illumination, strong clutter, specularity, partial occlusion, and texture.

Abstract—Parametric active contour models are one of the preferred approaches for image segmentation because of their computational efficiency and simplicity. However, they have a few drawbacks which limit their performance. In this paper, we identify some of these problems and propose efficient solutions to get around them. The widely-used gradient magnitude-based energy is parameter dependent; its use will negatively affect the parametrization of the curve and, consequently, its stiffness. Hence, we introduce a new edge-based energy that is independent of the parameterization. It is also more robust since it takes into account the gradient direction as well. We express this energy term as a surface integral, thus unifying it naturally with the region-based schemes. The unified framework enables the user to tune the image energy to the application at hand. We show that parametric snakes can guarantee low curvature curves, but only if they are described in the curvilinear abscissa. Since normal curve evolution do not ensure constant arc-length, we propose a new internal energy term that will force this configuration. The curve evolution can sometimes give rise to closed loops in the contour, which will adversely interfere with the optimization algorithm. We propose a curve evolution scheme that prevents this condition. Index Terms—Active contour, curve, segmentation, snake, spline.

A common problem in most active contour methods is that the recursive searching scheme can only return a local optimal solution. Furthermore, the internal energy of the snake is not strong enough to control the shape of the contour. To overcome these difficulties, in this paper, we develop a causal internal energy term based on a radial contour representation to encode the smooth constraint of the contour, and develop a global shape priori to control contour's shape and position based on object's dynamics. The causality nature of the representation allows us to efficiently find global optimal solution using dynamic programming. To validate the efficacy and robustness of the proposed approach, we apply this approach to track people in bad illumination and cluttered environments. We report promising results in the paper. 1.

While level sets have demonstrated a great potential for 3D medical image segmentation, their usefulness has been limited by two problems. First, 3D level sets are relatively slow to compute. Second, their formulation usually entails several free parameters which can be very difficult to correctly tune for specific applications. The second problem is compounded by the first. This paper describes a new tool for 3D segmentation that addresses these problems by computing level-set surface models at interactive rates. This tool employs two important, novel technologies. First is the mapping of a 3D level-set solver onto a commodity graphics card (GPU). This mapping relies on a novel mechanism for GPU memory management. The interactive rates level-set PDE solver give the user immediate feedback on the parameter settings, and thus users can tune free parameters and control the shape of the model in real time. The second technology is the use of region-based speed functions, which allow a user to quickly and intuitively specify the behavior of the deformable model. We have found that the combination of these interactive tools enables users to produce good, reliable segmentations. To support this observation, this paper presents qualitative results from several different datasets as well as a quantitative evaluation from a study of brain tumor segmentations.