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, a novel method to estimate 3D structure of a building from low altitude aerial images is proposed. Our method is based on a convectional SfM (Structure from Motion) approach, but technical image acquisition and adaptive RANSAC optimization for F, P computation are used. The experimental result shows point cloud generation of a midrise building using images captured by a general commercial...
Color discrepancy in stereoscopic images may increase an audience's sense of fatigue when it is played on a 3D display device. Proposed color correction method consists of two phases: a sample-based color matching phase that extracts sample points for color correction and uses a modified histogram mapping with the sample points, followed by an error compensation phase that estimates the quantity of...
In this paper, a novel method to generate depth map automatically from aerial video is proposed. Camera intrinsic and extrinsic parameters are estimated by a traditional Structure from Motion (SfM) approach and a post-processing for the camera path optimized for aerial video is used. Depth map is generated directly from the camera path and 3D point without making meshes in 3D space. Proposed method...
In this paper, a novel method to automatically detect mosaic masking regions in an input image is proposed. Mosaic masking region can be used as an important clue for recognizing commercial pornographic images. The proposed method is composed of three steps. The first step is to extract SRE features using a new cross-shaped feature characteristic, and the second step is to estimate the parameters...
In this paper, a novel method to automatically classify an pornographic video using fast motion features is proposed. In proposed method, predefined number of clips without a shot change are extracted from an input video and new, fast motion features are computed for each clip. Each clip is given a pornographic possibility based on motion distribution information. If the possibility is bigger than...
This work is aimed at the estimation of the skin region in pornographic images to identify and block the pornographic contents. We propose a novel method to estimate the skin region using simple operation in HSV color space and additional postprocessing to reduce the noise effects. Our method does not require any pre-process such as object detection. It is fast and its result is good enough to be...
We propose a novel method to automatically generate a depth map of static background region from 3D reconstructed points. First, camera parameters and 3D points are reconstructed by SfM technique. Next, depth values of the 3D points are computed and the values are spreaded in 2D image domain. Finally post-processing to deal with over-lapped depth informations and reduce flickering artifact is followed...
The interest in the production of stereoscopic contents is growing rapidly. High quality stereo material can be produced using vertical stereo camera rig but complex color discrepancies occur because of the optical characteristic of the half mirror. These discrepancies may severely increase an audience's sense of fatigue if s/he watches these stereoscopic contents for a long time. The color matching...
To insert a virtual object into a real image, the position of the object must appear seamlessly as the camera moves. This requires camera tracking with estimations of all internal and external parameters in each frame with an adequate degree of stability to ensure negligible visible drift between the real and virtual elements. In the post production of film, matchmoving software based on SfM is typically...
Real-time camera tracking is a system to estimate camera motion in real-time only given a image sequence in markerless background. It can be used in augmented reality application in which CG objects are inserted into live action plates by real-time. Proposed system is based on parallel processing and composed of two parts, they are feature tracking part, camera motion estimation part. In the feature...
To composite computer graphic objects and photo-real sequences we should know the camera intrinsic and extrinsic parameters. Many algorithms have been proposed for camera auto-calibration but most of them severely depend on reliable feature tracking so they cannot be applied to moving background sequences like the ocean scene. We assume that intrinsic parameters are known and propose a new method...
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.