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 propose a mathematical model for optimizing pixel aspect ratio for the best 3D estimation in both stereo-based 3D reconstruction and 3D viewing applications. We analyze the 3D reconstruction through a 3D display medium and reduce the whole process to a single stereo system so that a unified model can be applied to both direct reconstruction from stereo images and indirect reconstruction through...
There are several representations for 3D scene that are used for 3DTV and free viewpoint imaging systems. A well-known representation is sparse view-plus-depth. Based on view-plus-depth, layered depth video (LDV), and FTV data Unit (FDU) were proposed. The represented images by them are based on residual values. For view data in view-plus-depth, we propose a novel representation; consist of original...
Content production for stereoscopic 3D-TV displays has become mature in the past years. The content is usually shot using two cameras as the glasses-based target devices require two views as input. Beside stereoscopic 3D-TVs, huge progress has also been achieved in the improvement of the image quality of glasses-free auto-stereoscopic displays and light-field displays. Concerning the latter two display...
This work describes a novel approach to improving accuracy of optical wafer pre-align systems especially for thin, warped, bonded or carrierless-ultrathin wafers. Using 3D wafer modeling, provided by innovative Ranging Edge Detectors (RED, RE-Detector), the proposed signal processing enables maximum likelihood parameter estimation for best wafer alignment results. Additionally the sensor principle...
Most automatic face recognition algorithms try to normalize facial images in order to remove variations caused by anything but the identity of the person. Lighting conditions being less problematic since the introduction of reliable and affordable depth sensors, head pose is the other great source of un-desired variations in facial images. In this paper, we describe recent state-of-the-art methods...
This paper presents the implementation of 3D perceptual parameter estimation in robot texture images using multi-core Graphic Processing Units (GPUs) connected into a cloud computing environment. The paper discusses the architecture of the system and its benefits in providing real time estimation of parameter estimation to get an approximation of the change in position of robot from a certain position...
A novel scene recognition method that utilizes local appearance descriptions together with geometrical invariants for multiview scene matching is presented in this paper. The rationale behind this effort is to complement the lowered discriminative capacity of local features, with invariant geometric descriptions. Presented method is evaluated by comparison with a prominent baseline method, which utilizes...
This paper describes our method to fit a 3D skeleton to the human hand using depth images. The human hand is represented by a 3D skeleton with 21 parts. This model is used to generate synthetic depth images, that are used to train Random Decision Forests (RDF), which are used to assign each pixel to a hand part. Mean-shift method is used on the classification results and joint locations are estimated...
Traditional depth from defocus (DFD) algorithms assume that the camera and the scene are static during acquisition time. In this paper, we examine the effects of camera and scene motion on DFD algorithms. We show that, given accurate estimates of optical flow (OF), one can robustly warp the focal stack (FS) images to obtain a virtual static FS and apply traditional DFD algorithms on the static FS...
This paper presents the estimation of the vergence region, which is defined by the set of zero disparity points on the stereo images, in the form of the best border line separating the positive and negative disparities, by using a sparse disparity map. Sparse disparities are summed along radiating directions and the best direction to separate the sparse map is found by means of the metrics defined...
Real-time 3D motion capture for the human hand opens many avenues for HCI. This work describes our framework for fitting a 3D skeleton to the human hand using depth images. We represent a human hand by a 3D skeleton with 15 joints. Using this model, various synthetic depth images are generated. Random Decision Forests (RDF) are trained and used to assign each pixel to a hand part. A mean-shift method...
Ego-motion estimation based on images from a stereo camera has become a common function for autonomous mobile systems and is gaining increasing importance in the automotive sector. Unlike general robotic platforms, vehicles have a suspension adding degrees of freedom and thus complexity to their dynamics model. Some parameters of the model, such as the vehicle mass, are non-static as they depend on...
In this present work, we propose to define a novel surface registration approach using the generalized Hausdorff distance in the shape space. It is based on the selection of local and invariant points under the transformations of the 3D motion group. These points are selected from two level sets extracted from geodesic local coordinates with respect to a given reference. The optimal number of invariant...
As a distributed underwater network with wireless sensors, Underwater Wireless Sensor Networks (UWSNs) can provide the means for real-time, accurate and extensive monitoring, it is considered as an ideal system for extensive aqueous environment surveillance. Although localization has been widely studied for terrestrial WSNs, the adverse aqueous environments and harsh acoustic communications all bring...
Crowd-sourcing tools such as Mechanical Turk are popular for annotation of large scale image data sets. Typically, these annotations consist of bounding boxes or coarse outlines of objects, in order to keep the interface as simple as possible and to respect browser constraints. However, as most browsers now contain functionality to quickly process images and render shapes to the browser through JavaScript,...
Even though the sampling grid of a digital camera is uniform and rectangular, the depth information reconstructed from multi-camera samples is neither uniform nor rectangular due to the rotations and translations of the camera coordinate systems with respect to each other. In order to facilitate further processing, e.g. compression of multi camera depth data, resampling of non-uniform multi-camera...
This paper presents a 2D to 3D conversion system from multiple views based on the computation of a sparse depth map. This method is able to deal with the multiple views obtained from uncalibrated hand-held cameras without prior knowledge of the camera parameters or scene geometry. The obtained reconstructed sparse depth maps of feature points in 3D scenes provide accurate relative depth information...
Since the very beginning of space exploration, cosmonauts have suffered from weight losses which need to be particularly monitored during long term missions in space stations to insure their health and well being. In 1965–6 Thornton successfully built a device able to measure the body mass of cosmonauts in the micro-gravity space environment using passive linear spring-mass oscillators. Since then,...
We have proposed a 3D object tracking framework with a Coarse-to-Fine combination strategy for robot vision applications. In the coarse step, compared with those edge-based only methods, the convergence range of initial camera pose estimation has been enlarged in our system by a template-based matching between a series of template images rendered from Computer Graphics (CG) and a current image. In...
The release of a gaseous substance into the atmosphere can pose a significant risk, whether intentional or accidental. The tracking and localization of the tracer as it moves throughout the domain in real time can provide information on how to minimize subsequent harm. This work investigates the state estimation and real time detection of a continuous source in a 3D environment through a Lyapunov...
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.