Abstract: An object-based image encoding/decoding method and device of the present disclosure may include an image partition step which partitions an image to obtain a first object region, a region scaling step which scales the first object region based on a scaling factor of the first object region to obtain a second objection region, a region merging step which merges the second object region with at least one of an object region different from the second object region or a non-object region to obtain a merged image, and an image reconstruction step which reconstructs the merged image.

Abstract: An image encoding/decoding method, device and recording medium based sed on multiple compression levels disclosure may include extracting a region of interest for machine vision from an input image, determining a compression level of the region of interest, and encoding the compression level of the region of interest.

Abstract: An image encoding method includes detecting at least one attention region from an original image, acquiring a reconstructed picture for the original image, generating residual data between a first attention region in the original image and a second attention region corresponding to the first attention region in the reconstructed picture, and encoding the residual data.

Abstract: Disclosed herein is a method for image preprocessing based on an object of interest. The method includes extracting an object region of interest from an input image, adjusting the object of region of interest, and adjusting a background region excluding the object region of interest.

Abstract: Disclosed herein are an apparatus and method for sensing an image based on an event. The apparatus includes memory in which at least one program is recorded and a processor for executing the program. The program may perform acquiring at least one of brightness information and color information from an input image signal, performing conversion including at least one of filtering of at least one of the acquired brightness information and color information, color conversion, and brightness conversion, calculating a quantized difference between a first converted image converted from the currently input image signal and a second converted image converted from a previously input image signal, and generating event information for the input image signal as a bitstream based on the quantized difference.

Abstract: Disclosed herein are an image processing method and apparatus for machine vision. The image processing method for machine vision includes generating an image with machine-unrecognizable distortion based on an input image, and encoding the image with machine-unrecognizable distortion.

Abstract: Disclosed herein is a method for compressing an image for machine vision, the method including detecting objects in an input image using an object detection network, generating a foreground image including bounding boxes corresponding to the objects and a background image, which is an image acquired by excluding the bounding boxes from the input image, encoding the foreground image and the background image, and decoding the encoded foreground image and the encoded background image.

Abstract: Disclosed herein are an apparatus and method for sensing an image based on an event. The apparatus includes memory in which at least one program is recorded and a processor for executing the program. The program may perform acquiring at least one of brightness information and color information from an input image signal, performing conversion including at least one of filtering of at least one of the acquired brightness information and color information, color conversion, and brightness conversion, calculating a quantized difference between a first converted image converted from the currently input image signal and a second converted image converted from a previously input image signal, and generating event information for the input image signal as a bitstream based on the quantized difference.

Abstract: Disclosed herein are a method, an apparatus and a storage medium for image encoding/decoding using a segmentation map. A feature vector for an image may be extracted using a segmentation map. The image may be encoded using the segmentation map and the feature vector. An output stream from an encoding apparatus may include a video stream and a feature stream. An input stream to a decoding apparatus may include a video stream and a feature stream. The image may be reconstructed using a reconstructed segmentation map and a reconstructed feature vector.

Abstract: Provided is a holographic display apparatus including a motor configured to synchronize with a hologram transmitted based on user's point of view and to rotate; a spatial light modulator configured to load hologram data generated based on the user's point of view in a fixed position state and to perform a light modulation; a mirror configured to provide the hologram which is light-modulated by the spatial light modulator according to the user's point of view during the rotation by rotation operation of the motor; and a hologram correction unit configured to compensate a rotation error between the fixed spatial light modulator and the rotating mirror and to provide a corrected hologram data to the spatial light modulator.

Abstract: In the present invention, by providing an apparatus for displaying a hologram including: a beam source configured to output a plurality of beams, a spatial light modulator configured to include a plurality of SLM (spatial light modulator) regions, display a hologram, and diffract the plurality of beams; a plurality of front lenses each corresponding to the plurality of SLM regions, and configured to refract the plurality of beams diffracted from each of the plurality of SLM regions; a plurality of filters each corresponding to the plurality of SLM regions, and configured to filter a part of the plurality of refracted beams; and a plurality of back lenses each corresponding to the plurality of SLM regions, and configured to display an interference image corresponding to the hologram using the filtered part beam, the beam path of the hologram displaying apparatus can be drastically reduced, and an entire size of the hologram displaying apparatus can be reduced, so that it is possible to down-size the digital ho

Abstract: Provided is an apparatus for measuring a quality of a holographic image. The apparatus includes: a hologram image reconstruction unit configured to perform a hologram image; a superimposed focus image generation unit configured to collect an area that is in focus from reconstructed images and superimpose into a single image; and a hologram image quality measurement unit configured to perform an image quality evaluation for the superimposed focus image.

Abstract: Provided are an apparatus and a method for displaying a hologram image based on pupil tracking, wherein a hologram image display apparatus includes a location determiner to determine a location of a user using a captured image of the user and a hologram information reconstructor to reconstruct first hologram information as second hologram information optimized for the location of the user to reproduce the hologram image.

Abstract: Disclosed are a method and apparatus for providing a three-dimensional (3D) broadcast service using images with asymmetric aspect ratios and a method and apparatus for reproducing a 3D broadcast service. The method of providing the 3D broadcast service includes adjusting a second viewpoint image to be composed with a first viewpoint image into a 3D form with respect to the first viewpoint image and the second viewpoint image for 3D broadcasting, encoding the first viewpoint image and the adjusted second viewpoint image, and generating a broadcast stream of the first viewpoint image and a broadcast stream of the second viewpoint image by multiplexing the first viewpoint image and the second viewpoint image.

Abstract: Disclosed is an apparatus and method for digital holographic table top display. The digital holographic table top display apparatus includes: a camera array configured to capture a plurality of channel images in an omni-directional range from a table by using a plurality of cameras; a controller configured to detect an observer from the plurality of channel images and to track a position of pupils of the observer in at least one channel image from which the observer is detected; and a display configured to reproduce a digital holographic image in a three-dimensional (3D) space according to the tracked position of the pupils.

Abstract: Provided is a video providing method and a video playing method for a three-dimensional (3D) video, and an apparatus for performing the methods. The video providing method may transmit a reconstruction mode for reconstructing a low-resolution additional video having lower resolution than a high-resolution reference video.

Abstract: A method of switching a transport stream, (TS) such as an MPEG-2 TS, receives a plurality of input streams, receives a switching command for a first input stream, among the plurality of input streams, that is currently being output, searches for an out-point of the first input stream and an in-point of a second input stream to be newly output, in response to the switching command, inserts a virtual P picture stream between the out-point and the in-point, and switches from the first input stream into the second input stream based on the out-point and the in-point.

Abstract: A boundary information providing apparatus may include a boundary information generation unit to generate boundary information of a video, the boundary information through which a switching point between a 2D video and a 3D video is recognized, based on a switching mode between the 2D video and the 3D video, and a stream transmission unit to transmit a stream including the boundary information to a video receiving apparatus.

Abstract: Provided is an apparatus for measuring a quality of a holographic image. The apparatus includes: a hologram image reconstruction unit configured to perform a hologram image; a superimposed focus image generation unit configured to collect an area that is in focus from reconstructed images and superimpose into a single image; and a hologram image quality measurement unit configured to perform an image quality evaluation for the superimposed focus image.

Abstract: Provided is a holographic display apparatus including a motor configured to synchronize with a hologram transmitted based on user's point of view and to rotate; a spatial light modulator configured to load hologram data generated based on the user's point of view in a fixed position state and to perform a light modulation; a mirror configured to provide the hologram which is light-modulated by the spatial light modulator according to the user's point of view during the rotation by rotation operation of the motor; and a hologram correction unit configured to compensate a rotation error between the fixed spatial light modulator and the rotating mirror and to provide a corrected hologram data to the spatial light modulator.