Korea University Research and Business Foundation

Samsung Techwin Co., Ltd.

Hanwha Techwin Co., Ltd.

Korea University Industrial Academic Collaboration Foundation

Han-Seok Ko

Bon-Hwa Ku

Bong-hyup Kang

Chang-won Jeon

Tae-yup Song

Du-Bok Park

Young-hyun Lee

Min-Jae Kim

Seung-In Noh

Han-Jun Kim

Dae-sung Chung

Hyun-hak Shin

Jeong-min Bae

Jae-Yong Ju

Provided is a method of merging or fusing a visible image captured by a visible camera and an infrared (IR) image captured by an IR camera. The method includes: providing a first image of a subject captured by a first camera and a second image of the subject captured by a second camera; converting brightness of the second image based on brightness of the first image; and merging the first image and the second image having the converted brightness.

Apparatus and method for fusing images

An image processing apparatus and method for restoring an image which is expected to be when there is no fog from a foggy image, the image processing method including: generating a pixel depth image of the foggy image by estimating a plurality of pixel depths of a plurality of pixels, respectively, included in the foggy image based on a channel difference between at least two of red (R), green (G), and blue (B) channels of the foggy image; processing the pixel depth image; obtaining an optical model parameter with respect to the foggy image; and restoring an image, which is expected to be when the foggy image does not include the fog, by using the processed pixel depth image and the optical model parameter.

Apparatus and method of processing image

An image processing method of separating an input image into a foreground image and a background image, the method including determining a pixel of the input image as a pixel of the foreground image if a foreground probability value of the pixel of the foreground image determined by using the Gaussian mixture model or the pixel determined to be included in a motion region is greater than a setting threshold.

Image processing method using foreground probability

A method and system of generating a super-resolution image is provided. fusing The method includes inputting an image; and generating an estimated high-resolution image of a current time by fusing an input image and an estimated high-resolution image of a previous time corresponding to the input image.

Method and system of reconstructing super-resolution image

Provided are method and apparatus of pre-processing in WDR (wide dynamic range) image processing, the method of pre-processing of WDR image processing including: (a) receiving luminance and chrominance signals having different exposure times, and analyzing the correlation between a luminance signal having a first exposure time and a luminance signal having a second exposure time that is longer than the first exposure time; (b) based on the result of the analysis, dividing each of the luminance signal having the first exposure time and the luminance signal having the second exposure signal, into at least one of a bright region, a transition region, and a dark region; and (c) normalizing the regions of the luminance signal having the first exposure time to respectively correspond to the regions of the luminance signal having the second exposure times.

Pre-processing method and apparatus for wide dynamic range image processing

Growing community of inventors

Seoul, South Korea

Han-Seok Ko