Abstract:
An object detection method includes setting a first window region and a second window region larger than the first window region that correspond to partial regions of different sizes in an input image, downsampling the second window region to generate a resized second window region, detecting a first object candidate from the first window region and a second object candidate from the resized second window region, and detecting an object included in the input image based on one or both of the first object candidate and the second object candidate.
Abstract:
A three-dimensional (3D) display apparatus and method are provided. The 3D display apparatus may include a display screen configured to display each of a plurality of sub-images included in a single frame of a 3D image using a time-division multiplexing (TDM), a polarizer configured to polarize each of the displayed sub-images by changing a polarization direction using the TDM, in synchronization with the display screen, and microlens arrays arranged in a plurality of layers and configured to sequentially refract the polarized sub-images, respectively.
Abstract:
A display device may include a plurality of display panels, and light path adjusters disposed on upper portions of the plurality of the display panels. The light path adjusters include a lens array configured to transfer different beams emitted from the plurality of display panels to each eye of a user, and a joint removal structure disposed on one side of the light path adjusters corresponding to a connecting joint that connects the plurality of display panels. The joint removal structure is configured to refract the beams emitted from the plurality of display panels.
Abstract:
An electronic device for estimating object information and generating a virtual object and a method of operating the electronic device are disclosed. The method includes obtaining an image, obtaining a class feature, a pose feature, and a relationship feature of an object included in the image, correcting each of the class feature, the pose feature, and the relationship feature using any combination of any two or more of the class feature, the pose feature, and the relationship feature of the object, and obtaining class information, pose information, and relationship information of the object based on the corrected class feature, the corrected pose feature, and the corrected relationship feature, respectively.
Abstract:
A method of determining a pose of a target object in a query image may include: obtaining a query image; obtaining a plurality of reference images corresponding to the query image; and determining a pose of a target object based on a first semantic feature corresponding to the query image and a second semantic feature corresponding to each of the plurality of reference images.
Abstract:
The present invention provides a method and device for adjusting resolution of a Head-Mounted Display (HMD) apparatus. Wherein, the method comprises the steps of: determining saliency information of display contents in multimedia information; adjusting, according to the saliency information, resolution corresponding to each display content in the multimedia information; and, displaying the resolution-adjusted multimedia information. In the present invention, by determining saliency information of display contents in multimedia information, the resolution corresponding to the display contents is adjusted, which enable the resolution of the display contents to be matched with the saliency of the display contents, and accordingly, the resolution-adjusted multimedia information is displayed without the need of displaying the complete multimedia information in a higher resolution and a higher frame rate. In this way, computation amount for a device is greatly reduced, so that requirement for device hardware is reduced and device cost is reduced, and displaying efficiency is improved whilst at the same time ensuring good displaying effect.
Abstract:
Provided is a head-mounted display (HMD) apparatus, including a light modulator and eye lens, where the light modulator is configured to perform integral imaging on an image output from a 2D display panel, to form a light field image, the eye lens are configured to magnify the light field image formed by the light modulator.
Abstract:
A three-dimensional (3D) depth sensor may include: a plurality of light sources configured to irradiate light to an object, the light having different center wavelengths; an optical shutter configured to allow reflected light reflected from the object to pass through; and an image sensor configured to filter the reflected light having passed through the optical shutter and detect the filtered light.
Abstract:
A three-dimensional (3D) display method includes generating N first visual images, N being a natural number greater than 1; generating M second visual images from each of the N first visual images, M being a natural number greater than 1; acquiring N visual image groups corresponding to the N first visual images, respectively, such that, for each one of the N visual image groups, the visual image group includes the M second visual images generated from the first visual image, from among the N first visual images, to which the visual image group corresponds; generating M elemental image array (EIA) images based on the N visual image groups; and time-share displaying the M EIA images.
Abstract:
An integrated image display, a method for operating the display, and a system including the display are provided. The integrated image display includes: a display panel including pixels; and a first lens array including a plurality of lenses, wherein each of the plurality of lenses is capable of displaying, in a beam direction, a subset of a plurality of subpixels included in at least one pixel from among the included pixels.