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 propose a novel Conditional Random Field (CRF) formulation for the semantic scene labeling problem which is able to enforce temporal consistency between consecutive video frames and take advantage of the 3D scene geometry to improve segmentation quality. The main contribution of this work lies in the novel use of a 3D scene reconstruction as a means to temporally couple the individual...
With the advent of glasses-free autostereoscopic handheld displays, a number of applications may be enhanced by 3D perception, particularly mobile video communications. On handheld devices, front-facing stereo cameras can capture the two views necessary for 3D display. However, the short distance between the user and cameras introduces large disparities and other stereoscopic challenges that have...
Visual Sonification is the process of converting visual properties of objects into sound signals. This paper describes the Michigan Visual Sonification System (MVSS) that utilizes this process to assist the visually impaired in distinguishing different objects in their surroundings. MVSS uses depth information to first segment and localize salient objects and then represents an object's appearance...
A precise event detection is a fundamental step in many applications. For instances, moving object detection is a fundamental task for a variety of traffic monitoring applications. Wavelets have been widely used for this purpose. However, The selection of the proper type of mother wavelet strongly affects the results of the analysis and processing. In this paper, the wavelets of the Daubechies family...
This study proposes an interactive multi label object segmentation method and applications on mono and stereo images. The general segmentation problem is approached by an energy minimization on a Markov Random Field (MRF). The minimum energy potential labelling is the primary goal of the multi label segmentation algorithm. User inputs are used to determine object location and geodesic prior induced...
In this paper we present a novel foreground segmentation and 3D reconstruction system for multi-view scenarios. The system achieves correct 3D object reconstruction even when foreground segmentation presents critical misses in some of the views. We introduce the spatial redundancy of the multi-view data into the foreground segmentation process by combining segmentation and the 3D reconstruction in...
This work proposes an interactive tool for creating stereo image from a mono image. The user interaction is defined as scribbling on the object of interest followed by relative depth assignment to the selected object. Initial step in the algorithm is to create structured image oversegments with intensity homogeneity and geometrical convexity constraint. The final image segmentation is realized by...
Arterial tree segmentation is a major step for pulmonary embolism analysis and detection. The present document proposes a technique applied to CT images already diagnosed as embolism positive. In order to perform the segmentation of the arterial tree, the lung's region is transformed into a mask, so that the processed volume gets reduced. Then, through thresholding, region growing, and morphological...
In this paper we present a method to combine the detection and segmentation of object categories from 3D scenes. In the process, we combine the top-down cues available from object detection technique of Implicit Shape Models and the bottom-up power of Markov Random Fields for the purpose of segmentation. While such approaches have been tried for the 2D image problem domain before, this is the first...
A visual auxiliary method for compensating binocular vision deficiency, which has problems in identifying stereoscopic presentations, is proposed in this paper to reduce the inconvenience in the daily life. To solve this defect problem, a stereo information compensation algorithm, combining the image matching, triangulation algebra, and the image segmentation algorithms, is adopted to append the distance...
2-D displays present significant visualization deficits and can hinder task performance when accurate perception of depth is required. Navigation of rugged terrain, scouting, and object detection at a distance all present limitations when viewed on traditional 2-D displays. The current investigation presents a novel use of stereo and hyperstereo image pairs to create a 3-D representation of the visual...
In this paper, a stochastic approach for extracting the articulated 3D human postures by synchronized multiple cameras in the high-dimensional configuration spaces is presented. Annealed Particle Filtering (APF) [1] seeks for the globally optimal solution of the likelihood. We improve and extend the APF with local memorization to estimate the suited kinematic postures for a volume sequence directly...
In the digital geometric technologies, Mesh segmentation is an important part and is actively researched now. We present a meaningful automatic mesh segmentation algorithm based on the minimum rule, the short-cut rule, and the part salience test from the cognitive theory. To find the candidate contours, we first extract features by using the minimum rule, and then the open contours are prioritized...
We present a statistical framework to merge the information from silhouettes segmented in multiple view images to infer the 3D shape of an object. The approach is generalising the robust but discrete modelling of the visual hull by using the concept of averaged likelihoods. One resulting advantage of our framework is that the objective function is continuous and therefore an iterative gradient ascent...
We present a novel method for 3D brain tumor volume segmentation based on a parallel cellular automata framework. Our method incorporates prior label knowledge gathered from user seed information to influence the cellular automata decision rules. Our proposed method is able to segment brain tumor volumes quickly and accurately using any number of label classifications. Exploiting the inherent parallelism...
The recent increasing demand for 3D digital contents has motivated us to develop techniques for watermarking 3D models so that we can hide copyright information behind them. However, existing methods rather focused on the robustness against possible attacks to destroy the embedded watermarks, and have not fully taken care of the associated influence on the visual quality of the target 3D models. In...
3D data collected by a laser scanner has great potential for robotic applications. Exact geometrical models of the environment surrounding the robot can be created from these point clouds. But, before creating any model, the 3D point cloud has to be segmented and depending on the size and quality of the point cloud, this can be a very challenging task. This article describes a robust 3D scan segmentation...
This paper describes a novel approach for purely vision based mobile robot navigation. The visual obstacle avoidance and corridor following behavior rely on the segmentation of the traversable floor region in the omnidirectional robocentric view. The image processing employs a supervised approach in which the segmentation optimal with respect to the appearance of the local environment is determined...
Computed tomography greatly improves the image information available to surgeons and is quickly becoming one of the most important methods to check for defects inside the patients. However, doctors must check these CT slices and again to find the exact position for the patients. This is not only of waste time but also highly inefficient. This paper presents a fast process to reconstruct 3D surfaces...
We present an improvement of the classical marker-controlled watershed approach in the direction of a better exploitation of user-defined markers. The combined action of a partial flooding and paint drops falling downwards on the gray value relief from marker locations, leads to a robust and meaningful identification of the candidate basins, which is a prerequisite for an accurate segmentation. This...
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.