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 address the problem of estimating dense motion fields related to a stratified atmosphere which is observed through satellite imagery. Estimating the evolving vertical distribution of horizontal wind fields from satellite image time series is of great importance for the study of atmospheric dynamics. Because of the sparse 3D nature of observations, classical correlation-based techniques...
Based on the triangulation method, the 3D motion of an object can be completely recognized by a stereo camera. However, the question whether or not the 3D motion of an object can be completely recognized by a motionless/fixed monocular camera is the yet-unanswered question. In this paper we propose a method using a motionless monocular camera of which the focus is changed in cycle to recognize the...
This paper presents a comparative study of robust diffusion algorithms when used for smoothing structural fields applied in volumetric image interpolation. The input data consists of a set of parallel and equidistant slices which are considered sparsely located along a central axis. The structural flows are constructed using the dual directional block matching algorithm (DBMA). Two vectorial flows...
A novel stereo matching algorithm is proposed that utilizes color segmentation on the reference image and a self-adapting matching score that maximizes the number of reliable correspondences. The scene structure is modeled by a set of planar surface patches which are estimated using a new technique that is more robust to outliers. Instead of assigning a disparity value to each pixel, a disparity plane...
In this paper, we propose a successive method for adoptively estimating background components using Kalman filters, and a novel method for detecting objects using margined sign cross correlation (MSC). MSC is a natural extension of sign cross correlation, in other words, peripheral increment sign correlation. MSC has a margin to deal with observation noise. By applying MSC to our adaptive background...
We set out an object localization scheme based on a convex programming matching method. The proposed approach is designed to match general objects, especially objects with very little texture, and in strong background clutter; traditional methods have great difficulty in such situations. We propose a convex quadratic programming (CQP) relaxation method to solve the problem more robustly. The CQP relaxation...
When we recognize the objects, it is effective to use the relational dependency that several different objects co-exist each other. This paper proposes a real-time object recognition using the relational dependency among the objects that is represented by the graphical model. Experiment results validate that the proposed method is a fast and effective way of recognizing the objects in terms of high...
In this paper, we use a general Mth order tensor discriminant analysis approach (Tao et al. 2005) for view based object recognition. This method is an extension of the 2D image coding technique (Shashua and Levin, 2001) to general Mth order tensors for discriminant analysis, and has good convergence property. We demonstrate the performance advantages of this approach over existing techniques using...
We propose a novel framework for tracking non-rigid objects via pixel classification and integration (PCI). Given a new input frame, the tracker first performs object classification on each pixel and then finds the region that has the highest integral of scores. There are several key advantages of the proposed approach: it is computationally very efficient; it finds a global, instead of local (e.g...
The selection of the appropriate colorspace for tracking applications has not been an issue previously considered in the literature. Many color representations have been suggested, based on the invariance to illumination changes. Nevertheless, none of them is invariant enough to deal with general and unconstrained environments. In tracking tasks, we might prefer to represent image pixels into a colorspace...
An appearance-based approach to track an object that may undergo appearance change is proposed. Unlike recent methods that store a detailed representation of object's appearance, this method allows an appearance feature with a reduced dimension to be used. Through the use of a sparse Bayesian classifier, high classification and detection accuracy can be maintained even if a reduced feature vector...
This paper introduces a multiple human objects tracking system to detect and track multiple objects in the crowded scene in which occlusions occur. Our method assign each pixel to different human object based on its relative distance to that object and the corresponding color model. If no occlusion, we easily track each object independently based on each segmented object region and optical flow. With...
We present a computer vision based system that enables multiple people to interact naturally with a large display table using their own bare-hand gestures. The display presents and supports a particular multimedia application that can be used at the same time even by remote users. Finally we describe two different applications designed for didactic and entertainment scenarios
In this contribution maximum likelihood (ML) based approaches are presented which track an a-priori known surface and texture in monocular video streams. In contrast to established tracking algorithms based on homographies the surface is not modeled as planar or piecewise planar but as a collection of 3D surface points and surface normals. Thus, any free-form surface can be modeled. This paper introduces...
This paper presents a novel technique to fill in missing background and moving foreground of a video captured by a static or moving camera. Different from previous efforts which are typically based on processing in the 3D data volume, we slice the volume along the motion manifold of the moving object, and therefore reduce the search space from 3D to 2D, while still preserve the spatial and temporal...
Image matching plays an important role in visual mapping, a critical task of vision based mobile robot navigation. Based on the observation that the visual content in these video sequences generally changes in a slow and continuous mode, a concept of "video local pattern" is proposed to model each video frame, which is defined as a set of frames that are visually-similar and temporally-adjacent...
This paper presents a method for synchronizing multiple cameras from only the images captured by the cameras, assuming that they are not connected to an external clock signal source. It is assumed that The cameras are stationary and take the images of the same scene from various viewpoints, in which there are moving objects such as human in motion. The method uses the appearance changes in an image...
In this paper, we propose a novel and robust method for extracting motion layers in video sequences. Taking advantage of temporal continuity, our framework considers both the visible and the hidden parts of each layer in order to increase robustness. Moreover, the hidden parts of the layers are recovered, which could be of great help in many high level vision tasks. Modeling the problem as a labeling...
Tracking multiple interacting objects represents a challenging area in computer vision. The tracking problem in general can be formulated as the task of recovering the spatio-temporal trajectories for an unknown number of objects appearing and disappearing at arbitrary times. Observations are noisy, their origin is unknown, generated by true detections or false alarms. Data association and the estimation...
Varying illumination and partial occlusion are two main difficulties in visual tracking. Existing methods based on appearance information cannot solve these problems effectively since appearance is sensitive to lighting and the appearances under occlusions are quite different. In this paper, we propose a descriptor-based dynamic tracking approach that can track objects under partial occlusions and...
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.