Abstract:
Provided is a method and apparatus for modeling a human body using a depth image and a color image. An image processing apparatus may extract a body area from a color image based on a depth value of a depth image, may match a boundary of the extracted body area and a boundary of a generic body mesh model, and may deform a mesh of the generic body mesh model based on a depth value of a pixel positioned within the boundary of the extracted body area.
Abstract:
A method of controlling an electronic device having a transparent display. The method includes controlling the electronic device to provide a first image through an optical display mode operation of the transparent display in which light incident from an object is transmitted, controlling the electronic device to acquire a second image through a video display mode operation of the transparent display in which an image captured from the object is displayed, and selectively displaying the first and second images using the transparent display by a mixing, by the electronic device, of the first and second images. The mixing may be dependent on a distance between the electronic device and the object or a display ratio between the first and second images. An image for an object may be displayed in a region of interest and an image for another object in a remaining region.
Abstract:
An apparatus for estimating a camera pose includes an image acquisition unit to acquire a photographed image, a motion sensor to acquire motion information of the apparatus for estimating the camera pose, a static area detector to detect a static area of the photographed image based on the photographed image and the motion information, and a pose estimator to estimate a camera pose based on the detected static area.
Abstract:
An interactive method includes displaying image content received through a television (TV) network, identifying an object of interest of a user among a plurality of regions or a plurality of objects included in the image content, and providing additional information corresponding to the object of interest.
Abstract:
A method and an apparatus search an image using a feature point. The image search method extracts at least one feature point from an image and describes the extracted at least one feature point in stages, thereby generating a hierarchical feature point descriptor. In addition, the method may search for information matching the feature point descriptor from a local database (DB) included in a terminal or a remote DB included in a server.
Abstract:
An interactive method includes displaying image content received through a television (TV) network, identifying an object of interest of a user among a plurality of regions or a plurality of objects included in the image content, and providing additional information corresponding to the object of interest.
Abstract:
A method and system for generating an augmented reality (AR) scene may include obtaining real world information including multimedia information and sensor information associated with a real world, loading an AR locator representing a scheme for mixing the real world information and at least one virtual object content and the real world information onto an AR container, obtaining the at least one virtual object content corresponding to the real world information using the AR locator from a local storage or an AR contents server, and visualizing AR information by mixing the real world information and the at least one virtual object content based on the AR locator.
Abstract:
Provided is a camera pose estimation apparatus that estimates an initial camera pose using one of an input depth image and an input color image, and refines the initial camera pose using the other image. When the initial camera pose is estimated using the input depth image, the radius of a first area, in which color information is matched for refinement, can be adaptively set according to the distribution of the depth value of at least one first point that is subject to matching.
Abstract:
Provided is an image processing apparatus for performing photon mapping, and the image processing apparatus may perform ray tracing for photon mapping, sample a ray space based on a result of the ray tracing, and perform pseudo photon mapping using the sampled ray space.
Abstract:
A plane detection apparatus for detecting at least one plane model from an input depth image. The plane detection apparatus may include an image divider to divide the input depth image into a plurality of patches, a plane model estimator to calculate one or more plane models with respect to the plurality of patches including a first patch and a second patch, and a patch merger to iteratively merge patches having a plane model a similarity greater than or equal to a first threshold by comparing plane models of the plurality of patches. When a patch having the plane model similarity greater than or equal to the first threshold is absent, the plane detection apparatus may determine at least one final plane model with respect to the input depth image using previously merged patches.