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.
This paper implements four interpolation methods to modify the adaptive support weight (ASW) algorithm in multiresolution image representation. The disparity values at lower resolution level are used to determine disparity values of undetermined pixels at higher level during the interpolation procedure. The first interpolation method fills an undetermined pixel (a gap) with the averaged disparities...
The state-of-the-art SIFT flow has been widely adopted for the general image matching task, especially in dealing with image pairs from similar scenes but with different object configurations. However, the way in which the dense SIFT features are computed at a fixed scale in the SIFT flow method limits its capability of dealing with scenes of large scale changes. In this paper, we propose a simple,...
Image diffusion is the underlying machine vision research method, and is frequently used to remove image noise. In this paper, we propose a new kernel function for image diffusion by combining the intervening contour (IC) and the color (C) component, called ICC kernel function, which can smooth inner messy texture while maintaining image structure. The intervening contour is used to ensure the diffusion...
Human visual system (HSV) puts more attentions to color and edge orientation. The repeat pattern between color and edge orientation covers on rich of visual information, it plays an important role in visual attention and image understanding. This paper presents a novel image feature representation method, called Two-Tuples Histogram (TTH), for image retrieval. The Two-Tuples Histogram has taken advantages...
Image segmentation is a hard task and many methods have been developed to alleviate its difficulties. A common preprocessing step designed for this purpose is to compute an over-segmentation of the image, often referred to as superpixels. In this paper, we propose a new approach to superpixels computation. In a first step, a hypergraph-based representation of the image is built. Then, a coarsening...
Illumination change usually results in challenging problems for many computer vision applications such as recognition, tracking and motion analysis. In this paper, an illumination invariant object tracking approach is proposed. Video feature information is captured using a monogenic scale space representation. From this representation, multiscale phase information, which has the advantage of being...
A system for fast multi-view 3D model reconstruction of object sequences is composed of a number of hardware and software components: the multiple simultaneous image acquisition subsystems, the computation platform, the object/background segmentation algorithm, and in this case, a volumetric carving procedure based on the silhouettes of the objects from each view that generates a volumetric representation...
The synergistic combination of single standing methods for the efficient and effective solution of complex problems represent the next level of research the last two decades in the area of computer vision and image understanding, due to their complicated challenges. Many of these combinations are based on the human researcher's experimental studies and most recently on a semi-automated or automated...
Horizon detection is a pre-cursor to vision processing in air and water robotics. This paper makes three contributions to horizon detection. First, a theoretical framework for generating pseudo spectra images (PSI), from spectrum analysis of XYZ color-space is presented. Second, wavelengths in the visible spectrum are identified, at which the PSI has similar intensities for sky and clouds. Generating...
Recently, scene recognition is becoming an additional function in digital camera. Automatic scene understanding is a highest-level operation in computer vision, and it is a very difficult and largely unsolved problem. The conventional methods usually use global features (such as color histogram, texture, edge) for image representation and recognize scene types with some classifiers (such as Bayesian,...
In this paper, the study for computer vision in motion capturing and motion replication is developed. A single web-cam is employed for motion capture, the 3D virtual character model mimicked the user movements, and some specific user's movement can trigger different animations (such as aggressive and defensive). Several proposed methods for motion capture and motion representation are described in...
Hybrid, generative-discriminative, techniques have proven to be valuable approaches in tackling difficult object or scene recognition problems. In general, a generative model over the available data for each image class is first learned providing a relatively comprehensive statistical multi-level representation. In this way, new meaningful image features become available, which encode the degree of...
The human eye is able to locate objects or regions of importance in its field of vision. Many visual saliency models have been proposed to replicate the human visual system (HVS) in detecting salient objects in a visual scene. A colour space transformation from the RGB space is assumed to increase the detection performance, given the reason that the transformed colour space would allow a better representation...
Object tracking using vision technology is one of the important and complex functions in computer vision. It should become more challenge in case of there are partial occlusions and significant clutter. A mean shift procedure embedded approach for vehicle and pedestrian tracking under real road scenes is presents. A combined hue and saturation of HSI color model and local orientation information are...
We study the problem of object classification when training and test classes are disjoint, i.e. no training examples of the target classes are available. This setup has hardly been studied in computer vision research, but it is the rule rather than the exception, because the world contains tens of thousands of different object classes and for only a very few of them image, collections have been formed...
Shadow image edge detection by using an adaptive background model is a critical component for many vision-based applications. Most background models were maintained in pixel-based forms, while some approaches began to study block-based representations which are more robust to non-stationary backgrounds. In this paper, a novel method that combines edge growing and granular computing approaches into...
In a wide range of color-related computer vision applications, researchers tried to select one of the conventional color spaces as the optimum one. This paper, however, addresses the problem of how to learn an optimum color space from the given training sample set. We seek a set of optimal coefficients to combine the R, G and B components based on a discriminant criterion and then gain one discriminant...
Mean-shift tracker plays an important role in computer vision applications due to its efficiency in mode seeking. By encoding the spatial information appropriately, the robustness of tracking could be greatly enhanced. However, to account for the deformation and other sources of variation of the tracking object, the spatial configuration should not be fixed apriori and it is more suitable to be adapted...
Recent researches show that the benefits of image segmentation have been exploited in object categorization and recognition approaches. In most of these works, objects are segmented from the background around to increase recognition accuracy. However, it is generally hard to find a segmentation that captures all correct object boundaries in images of real world scene. So some researches begin to choose...
A novel color correlogram based particle filter was proposed for an object tracking in visual surveillance. By using the color correlogram as object feature, spatial information is incorporated into object representation, which yields a reliable likelihood description of the observation and prediction for tracking the objects accurately. The capability of the tracker to tolerate appearance changes...
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.