Samsung Electronics Co., Ltd.

Sungkyunkwan University

Postech Academy-industry Foundation

Information & Communications University

Dusik Park

Changyeong Kim

Hoyoung Lee

Wonhee Choe

Hyunwook Ok

Seongdeok Lee

Daewon Kim

Jungwoo Kim

Hyungjun Kim

Jinseok Kim

Youngwoo Kim

Sungho Kim

Jaehyuk Choi

Yong Ju Jung

Alexey Lukin

Yulhwa Kim

Changick Kim

Minki Cho

Jaeseung Ko

Youngsik Huh

Jonghwan Ko

Jaejoon Kim

Soongdeok Lee

Cheonyong Cho

Vladimar Kim

A depth map generation apparatus includes: a sensor array including a plurality of sensors configured to detect a received light arrival time; a control circuit array; and a processor configured to divide an acquisition time of at least one of the plurality of sensors into a first time window and a second time window; based on a detection result of the at least one sensor in the first time window and the second time window, generate first sub-frame information; based on the first sub-frame information, determine in which one of the first time window and the second time window an object is detected; generate second sub-frame information from the one of the first time window and the second time window in which the object is detected; and provide the first sub-frame information and the second sub-frame information for generation of an image frame.

Apparatus and method of generating depth map

A method of performing operations on a plurality of inputs and a same kernel using a delay time by using a same processor, and a neural network device thereof are provided, the neural network device includes input data including a first input and a second input, and a processor configured to obtain a first result by performing operations between the first input and a plurality of kernels, to obtain a second result by performing operations between the second input, which is received at a time delayed by a first interval from a time when the first input is received, and the plurality of kernels, and to obtain output data using the first result and the second result. The neural network device may include neuromorphic hardware and may perform convolutional neural network (CNN) mapping.

Time-delayed convolutions for neural network device and method

A color conversion method, medium, and apparatus, converting a color temperature of an image to a user-set color temperature, on a pixel-by-pixel basis, based on the brightness of each pixel of the image. The color temperature conversion method may include determining a first information associated with a conversion range, determining whether the color temperature of the input pixel needs to be converted by determining, based on the first information, whether the input pixel is within the conversion range, calculating color coordinates of a target point if the input pixel is within the conversion range, and converting the color temperature of the input pixel by moving, in the same direction as the reference point to the target point an amount proportional to the reference point displacement so that the input pixel can be automatically moved along with the reference point of the conversion range.

Color temperature conversion method, medium, and apparatus converting a color temperature of a pixel based on brightness

A method, medium, and system generating a depth map of a video image are provided. The depth map generating method extracts the ground of a video image other than an object from the video image, classifies the video image as a long shot image or a non-long shot image based on a distribution value of the extracted ground, calculates a depth value gradually varied along a predetermined direction of the extracted ground when the video image corresponds to the long shot image and calculates a depth value based on the object when the video image corresponds to the non-long shot image. Accordingly, a sense of space and perspective can be effectively given to even a long shot image in which the ground occupies a large part of the image and a stereoscopic image recognizable by a viewer can be generated even if rapid object change is made between scenes in a video image.

Method, medium, and system generating depth map of video image

A method and apparatus for converting an m-dimensional color space comprising first through m-th input color components to an n-dimensional color space comprising first through n-th output color components. specified A method of converting an m-dimensional color space having first through m-th input color components into an n-dimensional color space having first through n-th output color components, m being less than n, includes: extracting first through nth intermediate color components by linearly combining the first through m-th input color components; determining whether m+1-th through n-th intermediate color components are within a specified dynamic range and compensating the first through n-th intermediate color components when signal values of the m+1-th through n-th intermediate color components are not within the dynamic range to obtain the first through n-th output color components.

Method and apparatus for converting color spaces and multi-color display apparatus using the color space conversion apparatus

A method and apparatus for adjusting a color of an image, the apparatus includes a unit setting at least one adjustment region shaped as an ellipse in a color space; and a unit converting colors of pixels included in the adjustment region to other colors based on a variable set.

Method and apparatus for adjusting color of image

An apparatus, medium, and method for correcting color of an image. The apparatus may includes a user interface which displays each of N reference patches, removes non-gray components from the displayed N reference patches, according to the characteristics of a user's visual system, and outputs the reference patches from which the non-gray components have been removed as adjusted reference patches, a table generator which generates at least one lookup table that has, as addresses, color component values for a current image and stores color component values of the adjusted reference patches as data, and a color corrector which addresses the at least one lookup table using the color component values of the image to read data corresponding to correction information for the color component values of the image and outputs the read data as the result of the correcting of color of the image.

Apparatus, medium, and method for correcting color of an image

An apparatus for and a method of adjusting a primary color component of an image and a computer-readable recording medium for storing a computer program for controlling the apparatus. The apparatus includes: a weight determiner which determines a weight corresponding to a hue difference between a hue of each of plural object hue components and a hue of adjustment primary color; and a component adjuster which adjusts at least one of object hue and saturation components using at least one of saturation and hue adjustment amounts of the adjustment primary color and the weight. The object hue and saturation components are components of hue and saturation components of an input image belonging to an adjustment range, the adjustment range belongs to a region of a color space in which color interference between the adjustment primary color and a neighboring primary color occurs, the adjustment primary color corresponds to a primary color to be adjusted, and the neighboring primary color corresponds to a primary color neighboring the adjustment primary color.

Apparatus and method for adjusting primary color component of image, and computer-readable recording media for storing computer program

A color temperature conversion method, medium, and apparatus converting an image from one of a plurality of basic color temperatures provided by an image display device to another color temperature other than the plurality of basic color temperatures. Also, the conversion method and apparatus enable pixels of the image with different brightnesses to have different color temperatures according to a user' preference. The color temperature conversion method includes: calculating variables for determining a conversion range; determining whether based on the calculated variables the input pixel is to be color-temperature-converted by determining whether the input pixel is within the conversion range; and converting the color temperature of the input pixel by moving in the same direction as the reference point to the target point in amount proportional to the reference point displacement so that the input pixel can be automatically moved along with the reference point of the conversion range.

Color temperature conversion method, medium, and apparatus for pixel brightness-based color correction

An apparatus and method of filtering a digital image signal. The apparatus includes: a noise reduction filter which selectively outputs one of results obtained by temporally and spatially filtering pixel values of pixels of each of frames of an image as a temporal or spatial filtering value in response to magnitudes of the results of temporal and spatial filtering; and a sharpness enhancement filter which highlights and outputs a high pass component of the temporal or spatial filtering value.

Apparatus and method for filtering digital image signal

A method converts a resolution of video signals, the method including: calculating up-sampling and down-sampling ratios based on a resolution of an input video signal and a desired resolution of an output video signal; calculating a number of filter tabs by multiplying the up-sampling and down-sampling ratios by a number of side lobes; calculating first filter coefficients of a same number of the filter tabs by multiplying a window function by a sinc function; calculating final filter coefficients by subtracting a result of a multiplication of a Gaussian function by a window function from the first filter coefficients, and then normalizing the final filter coefficients; and performing filtering in vertical and horizontal directions based on the final filter coefficients by modifying a sampling rate of an input video signal depending on the up-sampling and down-sampling ratios, to obtain clear video images.

Growing community of inventors

Suwon-si, South Korea

Dusik Park