The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper we present a novel volumetric shape from silhouette algorithm based on a centripetal pentahedron model. The algorithm first partitions the space with a set of infinite triangular pyramids derived from a geodesic sphere. Then the pyramids are cut by silhouettes into a set of pentahedrons, which together constitute the centripetal pentahedron model of the visual hull. This process is accelerated...
In this paper, a model is proposed for partitioning of 3D objects based on Reeb graphs. The model is motivated by perceptual principles and supports identification of the main protrusions of an object. Experimental results are presented to demonstrate the effectiveness of the proposed solution with respect to ground-truth data represented by manually segmented objects
This paper presents a new approach to solve the problem of stereo correspondence. In order to extract visible surfaces with similar texture from two different images, our method encodes input images to a series of so-called stripe adjacency graphs (SAG). A stripe is a connected region with only one segment on each scan-line and a SAG is a group of stripes with neighbourhood relationships. The algorithm...
This paper describes an approach to constructing a 3D paper-made object from hand-written sketches. This approach consists of two phases. One is the phase that constitutes a crease pattern based on a sketch. Another is the phase that constructs a virtual origami model from the obtained crease pattern. The crease pattern is a set of line segments in an unfolded sheet of paper and often designed by...
This paper proposes an approach to the segmentation of lung fields in the severe acute respiratory syndrome (SARS) infected radiographic images, which is the first step towards a computer-aided diagnosis system. To overcome the segmentation difficulty of highly atypical property of SARS in the lung images, our algorithm first uses morphological operations to obtain the initial estimation of the regions...
This paper proposes a new object movie (OM) segmentation method that incorporates shape priors into the segmentation algorithm. The shape prior introduced into every image of the OM is learned from the 3D model reconstructed by the volumetric graph cuts. Here, the constraint derived from the discrete medial axis is used to improve the reconstruction algorithm. Our segmentation method requires only...
High-level semantic understanding of vehicle motion behaviors is often based on vehicle motion trajectory clustering. In this paper, we propose an effective trajectory clustering framework in which a coarse-to-fine strategy is taken. Our framework consists of four stages: trajectory smoothing, feature extraction, trajectory coarse clustering and trajectory fine clustering. Wavelet decomposition is...
We present a novel multi-object tracking algorithm based on multiple hypotheses about the trajectories of the objects. Our work is inspired by Reid's multiple hypothesis tracking algorithm which is an optimal solution to the motion correspondence that occurs in multi-object tracking. Unfortunately, the exponential growth of the hypotheses tree precludes practical applications. To restrict this growth,...
We present a dynamic inference algorithm in a globally parameterized nonlinear manifold and demonstrate it on the problem of visual tracking. An appearance manifold is usually nonlinear, embedded in a high dimensional space, and can be approximated by a mixture of locally linear models. Existing methods for nonlinear dimensionality reduction, which map an appearance manifold to a single low dimensional...
Because of variable dependence, high dimensional data typically have much lower intrinsic dimensionality than the number of its variables. Hence high dimensional data can be expected to lie in (nonlinear) lower dimensional manifold. In this paper, we describe a nonlinear manifold clustering algorithm. By connecting data vectors with their neighbors in feature space, we construct a neighborhood graph...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.