Abstract: A method for calibrating a camera including (a) obtaining a two-dimensional (2D) homography that maps each of parallelograms projected onto two images taken by the camera into a rectangle, wherein the 2D homography is defined as a rectification homography and wherein new cameras that have virtual images are defined as rectified cameras and a new infinite homography is generated between the two rectified cameras, the virtual images being transformed from original images by the rectification homography; (b) obtaining an original infinite homography by using the correlations among the new infinite homography, the rectification homography and the original infinite homography; and (c) obtaining intrinsic camera parameters based on the correlation between the original infinite homography and the intrinsic camera parameters, thereby calibrating the camera.

Abstract: An image composition apparatus includes a synchronization unit for synchronizing a motion capture equipment and a camera; a three-dimensional (3D) restoration unit for restoring 3D motion capture data of markers attached for motion capture; a 2D detection unit for detecting 2D position data of the markers from a video image captured by the camera; and a tracking unit for tracking external and internal factors of the camera for all frames of the video image based on the restored 3D motion capture data and the detected 2D position data. Further, the image composition apparatus includes a calibration unit for calibrating the tracked external and internal factors upon completion of tracking in all the frames; and a combination unit for combining a preset computer-generated (CG) image with the video image by using the calibrated external and internal factors.

Abstract: Provided is an apparatus for targeted advertising based on images of passersby. A passerby image extraction unit extracts an image of a passerby. A trait information extraction unit extracts trait information regarding the passerby from the extracted image. A targeted advertisement obtainment unit obtains a targeted advertisement to be displayed based on the trait information. A targeted advertisement display unit displays the targeted advertisement.

Abstract: The present invention relates to a device and a method for allowing a user to reproduce new 3-D scene from one or two or more given 2-D video frames that already exist. The present invention provides a device and a method for automating post-image processing requiring a lot of manual work, thereby making it possible to produce and edit new 3-D representation from the existing 2-D video.

Abstract: Provided are a camera tracking system and method and a live video compositing system using the same, which track a main camera with a sub-camera attached to the main camera and thus stably calculate the motion of the main camera even in a dynamic case where most of a static background is occluded by a moving foreground object. The camera tracking system and the live video compositing system can connect feature point tracks that are cut by a foreground object which dynamically moves in an image. Accordingly, the camera tracking system and the live video compositing system can perform the more accurate and quick tracking of a camera even in a case where a foreground object occludes background by dynamically moving.

Abstract: An apparatus for calibrating images between cameras, includes: a detector for detecting dynamic markers from images taken by a motion capture camera and a video camera; a 3D position recovery unit for recovering 3D position data of the dynamic markers obtained by the motion capture camera; a 2D position tracking unit for tracking 2D position data of the dynamic markers obtained by the video camera; a matching unit for matching the 3D position data and the 2D position data of the dynamic markers; and a calibrating unit for converting the 3D position of the dynamic markers on a spatial coordinate system into image coordinates on an image coordinate system of the video camera to calculate intrinsic parameters and extrinsic parameters of the video camera to minimize a difference between coordinates of the 2D position data and the image coordinates.

Abstract: A camera tracking apparatus for calculating in real time feature information and camera motion information based on an input image includes a global camera tracking unit for computing a global feature map having feature information on entire feature points; a local camera tracking unit for computing in real time a local feature map having feature information on a part of the entire feature points; a global feature map update unit for receiving the computed feature information from the global and local camera tracking units to update the global feature map; and a local feature selection unit for receiving the updated feature information from the global feature map update unit to select in real time the feature points contained in the local feature map. The local camera tracking unit computes the local feature map for each frame, while the global camera tracking unit computes the global feature map over frames.

Abstract: A method for restoration of building structure using infinity homographies calculated based on parallelograms includes: calculating, using two or more parallelograms, an infinity homography between those cameras which refer to an arbitrary camera; restoring cameras and the building structure on an affine space using the computed infinity homography and homologous points between images; and transforming the restored result onto the metric space using constraints on orthogonality of vectors joining the restored three-dimensional points, the ratio of lengths of the vectors and intrinsic camera parameters. As a result, intrinsic camera parameters, camera positions on the metric space and the structure of the building are restored. All the restoration is possible even when intrinsic camera parameters corresponding to all the images are not constant.

Abstract: A multi-core multi-thread based Kanade-Lucas-Tomasi (KLT) feature tracking method includes subdividing an input image into regions and allocating a core to each region; extracting KLT features for each region in parallel and in real time; and tracking the extracted features in the input image. Said extracting the features is carried out based on single-region/multi-thread/single-core architecture, while said tracking the features is carried out based on multi-feature/multi-thread/single-core architecture.

Abstract: A method for calibrating a camera including (a) obtaining a two-dimensional (2D) homography that maps each of parallelograms projected onto images taken by two arbitrary cameras into a rectangle, wherein the 2D homography is defined as a rectification homography and wherein new cameras that have virtual images are defined as rectified cameras and a new infinite homography is generated between the two rectified cameras, the virtual images being transformed from original images by the rectification homography; (b) obtaining an original infinite homography by using the correlations among the new infinite homography, the rectification homography and the original infinite homography; and (c) obtaining intrinsic camera parameters based on the correlation between the original infinite homography and the intrinsic camera parameters, thereby calibrating the camera.

Abstract: A system and method for supporting augmented reality in an ocean scene is provided. According to the system and method, camera rotation information is extracted from horizontal line information of a sea extracted from an original image including a focal length and at least two first natural feature point tracking data existing on a sea plane and a plane parallel to the sea plane, using long-distance background features; camera movement is sequentially calculated from the camera rotation information and at least two natural feature point tracking data existing on the sea plane of the original image; and a computer graphics object is placed on a ground plane by importing camera position data, and a rendering is performed as moving the camera.

Abstract: Provided is a mouse interface apparatus using a camera, and system and method using the mouse interface apparatus. The mouse interface apparatus detects image coordinates (xi, yi) of a plurality of points existing on edges of a camera-photographing computer window image from the camera-photographing computer window image, obtains a homography using the detected image coordinates (xi, yi) and plane coordinates (Xi, Yi) of the plurality of preset points on a plane of a real computer window, the homography converting the detected image coordinates (xi, yi) into the plane coordinates (Xi, Yi) on the real computer window, converts an arbitrary coordinate on the camera-photographing image into the plane coordinate on the computer window according to a movement of the camera using the obtained homography, and positions a cursor on the plane coordinate to move the position of the cursor according to the movement of the camera.