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.
We introduce an efficient method for recovering the camera parameters automatically from the cast shadows of two 3D points observed over time. Compared to previous related work, our method has less restrictions in the sense that object-to-shadow correspondences do not have to be available in the image. We demonstrate how the horizon line may be recovered from only shadow points, and how the camera...
In this paper we propose a practical and efficient method for finding the globally optimal solution to the problem of camera pose estimation for calibrated cameras. While traditional methods may get trapped in local minima, due to the non-convexity of the problem, we have developed an approach that guarantees global optimality. The scheme is based on ideas from global optimization theory, in particular,...
This paper presents a new method for planar rectification. The pattern used here contains one circle and two points with known distances to the circle. Partial rectification is introduced to calculate the trace of the mapping centers from each distance constraint. The algorithm is derived by discovering three fixed points during a matrix transformation. Complex coordinates are used to simplify this...
We propose a method to synchronize video sequences of distinct scenes captured by cameras undergoing similar motions. For the general camera motion and 3D scene, the camera ego-motions are featured by fundamental ratios obtained from the fundamental matrices. In the case of pure translation, translational magnitude features is used. These extracted features are invariant to the camera internal parameters,...
There exist various methods for stereoscopic viewing of images, most requiring some special glasses for controlling what goes to the left and the right eyes of the viewer. Recent technology developments have resulted in displays that enable 3D viewing without glasses. However, these displays demand a true stereo pair as the input, which greatly limits their practical use, as true stereoscopic media...
The fundamental matrix (FM) represents the perspective transform between two or more uncalibrated images of a stationary scene, and is traditionally estimated based on 2-parameter point-to-point correspondences between image pairs. Recent invariant correspondence techniques however, provide robust correspondences in terms of 4 to 6-parameter invariant regions. Such correspondences contain important...
This work presents a new approach based on particle filtering to directly estimate the 3D positions of humans. Our system can predict occlusions due to other movements because we track humans in a 3D space, not on a 2D image plane. In addition, we introduce a 3D environmental model as the background model for tracking. This makes it easier to handle occlusions due to fixed objects in the environment...
The shape dynamics, i.e., the spatial-temporal shape deformation of an object during its movement, provides much important information about the identity of the object, and even motions performed by the object. In this paper, we proposed a system recognizing object motions based on their shape dynamics. In the proposed system, we use Kenall's definition of shape to represent the object contour extracted...
Reliable facial expression recognition by machine is still a challenging task. We propose a framework to recognise various expressions by tracking facial features. Our method uses localized active shape models to track feature points in the subspace obtained from localized non-negative matrix factorization. The tracked feature points are used to train conditional model for recognising prototypic expressions...
Skin color is an important feature of faces. Various applications benefit from robust skin color detection. Depending on camera settings, illumination, shadows, people's tans, and ethnic groups skin color looks differently, which is a challenging aspect for detecting it automatically. In this paper, we present an approach that uses a high level vision module to detect an image specific skin color...
In this paper, we present a learning and inference framework for 3D human pose recovery using silhouettes represented by Gaussian mixtures. A Bayesian mixture of experts is learnt to conduct multimodal pose regression. The major contribution of this paper is the use of Gaussian mixtures as silhouette shape descriptor and Kullback-Leibler divergence (KLD) for silhouette distance and kernel computation...
A new affine invariant curve normalization method using independent component analysis (ICA) is presented. First, principal component analysis (PCA) is used for translation, scale and shear normalization. ICA and the third order moments are then employed for rotation and reflection normalization. It is shown that all affine transformed versions of an object have a unique or canonical representation...
Linear discriminant analysis (LDA) is a widely used technique for pattern classification. It seeks the linear projection of the data to a low dimensional subspace where the data features can be modeled with maximal discriminative power. The main computation involved in LDA is the dot product between LDA base vector and the data which is costly element-wise floating point multiplications. In this paper,...
In this paper a new method that incorporates moment-based shape information into geometric active contours is presented. As any shape may theoretically be characterized by its set of moments, the shape prior is represented based on Legendre moments. By combining the shape prior with the powerful geometric active contours proposed by Chan and Vese, the improved model can retain all the advantage of...
In this paper, we present a novel occlusion resistant shape classification scheme for hidden Markov modeled shapes. First, hidden Markov model (HMM) is built using multiple example shapes for each shape class. A reference path for each class is built from the corresponding HMM, which is nothing but optimal path followed by the most likely example shape. The reference path stores temporal information...
Skeletal representations of 2-D shape, including shock graphs, have become increasingly popular for shape matching and object recognition. However, it is well known that skeletal structure can be unstable under minor boundary deformation, part articulation, and minor shape deformation (due to, for example, small changes in viewpoint). As a result, two very similar shapes may yield two significantly...
Disparity flow depicts the 3D motion of a scene in disparity space of a given view and can be considered as view-dependent scene flow. The disparity flow map of a given view is a 2D array of 3D vectors that depicts the 3D motion observed at different pixel locations. Estimating 3D motion in form of disparity flow map limits all computations in the 2D image space and converts the 3D motion estimation...
We propose an energy-based joint motion and disparity estimation algorithm with an anisotropic diffusion operator to yield correct and dense displacement vectors. The model estimates the left and right motions simultaneously in order to increase accuracy. We use the Euler-Lagrange equation with variational methods and solve the equation with the finite difference method (FDM). Then, the method computes...
In this paper, we proposed a new method for accurate optical flow estimation. The significance of this work is twofold. First in this paper we showed that the optical flow estimation could be viewed as a diffusion-reaction process (PDE-based) instead of a variational problem of minimizing some energy functions. The minimization often need the corresponding regularizer be restricted to some forms with...
This paper proposes a novel method for estimating the geospatial trajectory of a moving camera. The proposed method uses a set of reference images with known GPS (global positioning system) locations to recover the trajectory of a moving camera using geometric constraints. The proposed method has three main steps. First, scale invariant features transform (SIFT) are detected and matched between the...
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.