Abstract:
본 발명은 광학식 모션 캡쳐 시스템에서 동적 마커를 기반으로 모션 캡쳐 카메라와 고해상도 비디오 촬영 카메라를 보정(calibration)하는 방법에 관한 것으로, 별도의 카메라 보정 장치의 사용이나 보정용 마커를 카메라 혹은 배경에 부착함이 없이 모션 캡쳐 대상 물체 상에 부착된 동적 마커만을 이용하여 현장에서 촬영에 사용된 고해상도 비디오 촬영 카메라를 정확하게 보정을 할 수 있도록 한다. 즉, 본 발명은 광학식 모션 캡쳐 카메라를 통하여 복원되는 동적 마커의 3차원 모션 캡쳐 데이터를 3차원 보정 데이터로 저장하고, 현장에서 동시에 녹화된 고해상도 비디오에서 동적 마커의 위치를 추적(tracking)하여 이를 2차원 보정 데이터로 저장하여, 이를 일대일 대응시켜 보정을 수행시킴으로써, 촬영 카메라의 공간상 이동과 회전에 관련된 외부 인자뿐만 아니라 고해상도 카메라 렌즈와 관련된 내부 인자들도 동시에 보정되도록 하여, 광학식 모션 캡쳐 시스템에서 3차원 모션 캡쳐 데이터와 고해상도 촬영 비디오의 합성을 통한 HD 방송 및 영화에 사용 가능한 고해상도 3D 콘텐츠 제작에 필요한 고해상도 비디오 촬영 카메라 보정의 정확성과 안정성을 확보할 수 있다. 모션 캡쳐, 합성, 촬영 카메라, 보정, 마커, 추적, 고해상도, HD, 3D 콘텐츠
Abstract:
PURPOSE: A structure of a camcorder for tracking of a photographing position in a 3D space is provided to easily compose a real image and CG(Computer Graphics). CONSTITUTION: A main lens(110) takes a photograph of a real image. A sub lens(120) takes a photograph of a sub image for a fixed object. In order that the main lens and the sub lens are synchronized, a synchronizing signal generator(130) offers a reference signal. An image output unit(160) outputs a main image or the sub image to the outside or outputs the stored main image or sub image of each storage unit(140,150) to the outside.
Abstract:
본 발명은 실시간 카메라 트래킹을 이용한 실사 영상 합성 시스템 및 그 방법에 관한 것으로, 2차원 특징점 추적 데이터에서 적합한 특징점들을 선별하여 상태(state) 예측기를 통해 카메라의 위치, 각도를 실시간으로 예측할 수 있다. 그리고 특징점들을 3차원으로 복원시킨 공간좌표를 DB의 도심 모델정보와 비교하여 도심모델 공간의 절대좌표계에서 카메라의 위치와 각도를 실시간으로 추정함으로써, 차량용 네비게이터에서 길안내 및 주변정보를 실사영상과 실시간으로 합성하여 출력할 수 있어 정확도와 실시간성을 보장할 수 있다. 합성, 카메라, 움직임, 예측
Abstract:
A method and a device for estimating motion in a real-time motion estimation system by using a Kalman filter are provided to improve correctness of a camera motion estimation value by updating configuration while increasing a state vector of the Kalman filter according to an extracted feature point. A feature extractor(102) extracts features of each frame from an image sequence of an image captured and received from a camera. A candidate feature selecting and storing unit(104) compares the extracted features with a current state vector. The candidate feature selecting and storing unit selects a candidate feature to be added and stores the candidate feature in a structure body. A state vector updater(106) updates the state vector when a predetermined condition is satisfied. A motion estimator(108) estimates motion of the camera in real-time by applying a Kalman filter to the updated state vector.
Abstract:
A mouse interface device using a camera, a system and a method using the same, and a computer-readable recording medium thereof are provided to control a position of a mouse cursor in a screen without any additional device by using homography converting a coordinate system of a camera into a planar coordinate system of the screen. An image coordinate detecting module(310) detects image coordinates, which are positions of at least four points found on an edge of a screen from a camera image, from the screen captured by a camera(100). A homography processing module(320) finds homography by using the detected image coordinates and planar coordinates, which are the planar coordinates formed by the screen for the predetermined points. The homography comprises a 3X3 matrix converting a coordinate system of the camera into a planar coordinate system of the screen. A cursor coordinate outputting module(330) outputs screen coordinates for the predetermined point of the camera image by using the homography and determines the screen coordinates as the position of the cursor. A mouse driver(400) moves the position of the cursor according to a change of the determined coordinates.
Abstract:
Disclosed is an interactive content display device connected to a heterogeneous display, in which a plurality of displays with various characteristics is not used independently, and which can visualize an object intimately connected between the displays and can move the object. The disclosed device includes: a multiple dual display visualization unit which includes a heterogeneous display with different characteristics; a rendering synchronization unit which performs rendering synchronization for the frames of an interactive content image respectively provided to the heterogeneous display with different characteristics in order to represent the same virtual space and object such that a user can view the same virtual space and object on the heterogeneous display with different characteristics; a user gesture recognition unit which recognizes a gesture of a user; and an interactive content visualization unit which supplies, to the heterogeneous display with different characteristics, the interactive content image rendering-synchronized by the rendering synchronization unit, and enables the connection and movement of an object between the heterogeneous display with different characteristics, according to the gesture of the user recognized by the user gesture recognition unit.
Abstract:
PURPOSE: An augmented reality output device using front objects and a method thereof are provided to supply realistic augmented reality corresponding to distance change without interrupting safety driving through outputting augmented reality. CONSTITUTION: An augmented reality output device using front objects comprises a distance measuring unit(100), a contents setting unit(200), a location compensation unit(300), and a display unit(400). The distance measuring unit receives the video information and depth information of the front of a vehicle and measures the distance to a front object from a driver. The contents setting unit sets the size and synthesis position of the augmented reality contents offered to a driver. The location compensation unit compensates the video error between the view of a driver and video information. The display unit indicates the compensated augmented reality contents.