Patents by Inventor Seong Dae Kim
Seong Dae Kim has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 9584723Abstract: An apparatus for creating a panorama is provided, the apparatus including an image obtainer to obtain at least two images via at least two cameras, an overlapping area analyzer to analyze an overlapping area among the at least two cameras, and extract overlapping image information, an image segmentation unit to segment the at least two images in an object unit, and generate image segmentation information, a depth value extractor to extract a depth value of an object in the at least two images, an image focus setter to set a focus value based on the depth value for the plurality of segmented objects, and a panorama creator to create panorama content of which a focus is convertible using the image segmentation information and the focus value.Type: GrantFiled: January 16, 2014Date of Patent: February 28, 2017Assignee: Electronics and Telecommunications Research InstituteInventors: Myung Seok Ki, Ji Sung Yoo, Seong Dae Kim
-
Patent number: 9185288Abstract: An apparatus and method for generating and consuming a three-dimensional (3D) data format to generate a realistic panoramic image are provided. The apparatus may include an image preprocessing unit to search for a matching point between images captured by a plurality of cameras, and to extract, as image information, at least one of a depth value, a texture value and object division information from each of the captured images, an image information structuring unit to structure 3D data to use the extracted image information to generate a realistic image, a 3D data format storage unit to store format information of the structured 3D data in a database (DB), realistic image generating unit to generate a realistic panoramic image using the stored format information of the 3D data, and a realistic image rendering unit to perform rendering on the generated realistic panoramic image.Type: GrantFiled: March 13, 2013Date of Patent: November 10, 2015Assignee: Electronics and Telecommunications Research InstituteInventors: Myung Seok Ki, Yong Ju Cho, Seong Yong Lim, Ji hun Cha, Seung Kwon Beack, Yong Ju Lee, Jin Woong Kim, Seong Dae Kim, Wook Joong Kim, Ji Sung Yoo, Sung Soo Hwang
-
Publication number: 20140240452Abstract: An apparatus for creating a panorama is provided, the apparatus including an image obtainer to obtain at least two images via at least two cameras, an overlapping area analyzer to analyze an overlapping area among the at least two cameras, and extract overlapping image information, an image segmentation unit to segment the at least two images in an object unit, and generate image segmentation information, a depth value extractor to extract a depth value of an object in the at least two images, an image focus setter to set a focus value based on the depth value for the plurality of segmented objects, and a panorama creator to create panorama content of which a focus is convertible using the image segmentation information and the focus value.Type: ApplicationFiled: January 16, 2014Publication date: August 28, 2014Applicant: Electronics and Telecommunications Research InstituteInventors: Myung Seok KI, Ji Sung YOO, Seong Dae KIM
-
Publication number: 20140063044Abstract: A navigation apparatus includes a priority information database (DB) that stores display priority of a plurality of additional images to be displayed on a map image, and a control unit configured to adjust opacity of the additional images according to the display priority when an overlap between the additional images is detected. Accordingly, a display unit displays the additional images having the adjusted opacity.Type: ApplicationFiled: December 11, 2012Publication date: March 6, 2014Applicant: HYUNDAI MNSOFT, INC.Inventor: Seong-Dae KIM
-
Patent number: 8379142Abstract: Disclosed herein is an apparatus and method for balancing the color of a flashed image using depth estimation. The apparatus includes a depth value measurement unit, a region identification unit, a color impression estimation unit, and a color balancing unit. The depth value measurement unit measures the depth values of the respective regions of an image to be captured using a camera preview image. The region identification unit identifies the regions of the preview image as a region influenced by camera flash or a region not influenced by camera flash using the depth values measured by the depth value measurement unit. The color impression estimation unit estimates the color impression of actual illumination in the region not influenced by camera flash. The color balancing unit corrects the color of the region influenced by camera flash.Type: GrantFiled: December 29, 2009Date of Patent: February 19, 2013Assignee: Korea Advanced Institute of Science and TechnologyInventors: Seong Dae Kim, Sung Soo Hwang, Su Jung Kim, Hwang Soo Lee, Young Serk Shim, Joon Sik Choi
-
Patent number: 8300051Abstract: Disclosed herein is an apparatus for enhancing images in consideration of region characteristics. An inverse gamma correction unit releases gamma correction and linearizes each of Red (R), Green (G), and Blue (B) colors. A threshold calculation unit calculates m-1 thresholds in order to divide the brightness of pixels into m regions, and labels each of the pixels as one of the m brightness regions. A block segmentation unit divides an input image into M×N blocks. A block statistics calculation unit determines one of the m brightness regions to which each of the blocks pertains, and labels the block as the corresponding brightness region. A block-based Look-Up Table (LUT) generation unit generates enhancement LUTs for the respective blocks. An image enhancement unit corrects the image using the LUTs for the respective blocks. A gamma correction unit performs gamma correction.Type: GrantFiled: November 20, 2008Date of Patent: October 30, 2012Assignee: Korea Advanced Institute of Science and TechnologyInventors: Seong Dae Kim, Keun Dong Lee, Su Jung Kim, Hwang Soo Lee
-
Patent number: 7949185Abstract: Disclosed herein is a method of performing robust white balance. The method includes a first process of dividing an input image into blocks, a second process of selecting blocks having higher color errors, and calculating average RGB values of the selected blocks, a third process of selecting a specific top percentage of bright blocks, and calculating the average RGB values of these selected blocks, a fourth process of calculating average RGB values through color clustering, a fifth process of converting the average RGB values into CIE xyY color space, a sixth process of calculating the Euclidean distances between the x and y values of standard light sources in a color space and the x and y values of the average RGB values in CIE xyY color space, and selecting an average RGB value having the shortest Euclidean distance (Ed), and a seventh process of calculating white balance gain values using the selected average RGB value, and correcting the input image using the balance gain values.Type: GrantFiled: November 7, 2007Date of Patent: May 24, 2011Assignee: Korea Advanced Institute of Science and TechnologyInventors: Seong Dae Kim, Su Jeong Kim, Jeong Woo Hwang
-
Publication number: 20110115941Abstract: Disclosed herein is an apparatus and method for balancing the color of a flashed image using depth estimation. The apparatus includes a depth value measurement unit, a region identification unit, a color impression estimation unit, and a color balancing unit. The depth value measurement unit measures the depth values of the respective regions of an image to be captured using a camera preview image. The region identification unit identifies the regions of the preview image as a region influenced by camera flash or a region not influenced by camera flash using the depth values measured by the depth value measurement unit. The color impression estimation unit estimates the color impression of actual illumination in the region not influenced by camera flash. The color balancing unit corrects the color of the region influenced by camera flash.Type: ApplicationFiled: December 29, 2009Publication date: May 19, 2011Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGYInventors: Seong Dae Kim, Sung Soo Hwang, Su Jung Kim, Hwang Soo Lee, Young Serk Shim, Joon Sik Choi
-
Publication number: 20100085361Abstract: Disclosed herein is an apparatus for enhancing images in consideration of region characteristics. An inverse gamma correction unit releases gamma correction and linearizes each of Red (R), Green (G), and Blue (B) colors. A threshold calculation unit calculates m-1 thresholds in order to divide the brightness of pixels into m regions, and labels each of the pixels as one of the m brightness regions. A block segmentation unit divides an input image into M×N blocks. A block statistics calculation unit determines one of the m brightness regions to which each of the blocks pertains, and labels the block as the corresponding brightness region. A block-based Look-Up Table (LUT) generation unit generates enhancement LUTs for the respective blocks. An image enhancement unit corrects the image using the LUTs for the respective blocks. A gamma correction unit performs gamma correction.Type: ApplicationFiled: November 20, 2008Publication date: April 8, 2010Applicant: Korea Advanced Institute of Science and TechnologyInventors: Seong Dae KIM, Keun Dong LEE, Su Jung KIM, Hwang Soo LEE
-
Publication number: 20090097745Abstract: Disclosed herein is a method of performing robust white balance. The method includes a first process of dividing an input image into blocks, a second process of selecting blocks having higher color errors, and calculating average RGB values of the selected blocks, a third process of selecting a specific top percentage of bright blocks, and calculating the average RGB values of these selected blocks, a fourth process of calculating average RGB values through color clustering, a fifth process of converting the average RGB values into CIE xyY color space, a sixth process of calculating the Euclidean distances between the x and y values of standard light sources in a color space and the x and y values of the average RGB values in CIE xyY color space, and selecting an average RGB value having the shortest Euclidean distance (Ed), and a seventh process of calculating white balance gain values using the selected average RGB value, and correcting the input image using the balance gain values.Type: ApplicationFiled: November 7, 2007Publication date: April 16, 2009Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGYInventors: Seong Dae KIM, Su Jung KIM, Jung Woo HWANG
-
Patent number: 5748761Abstract: A method for use in an object-oriented analysis-synthesis coder, for segmenting an image of a current frame into moving objects and describing each motion of the moving objects with a set of motion parameters, which comprises the steps of: (a) comparing the current frame with a preceding frame to detect a motion vector field; (b) sliding window blocks on the motion vector field, and computing the degree of homogeneity for each of the window blocks to produce a seed block; (c) determining a set of initial values for the set of motion parameters based on the seed block; (d) evaluating whether each motion vector contained in and around the seed block is describable with the set of initial values or not, to thereby detect a revised region; (e) determining a set of revised values for the set of motion parameters from the revised region; (f) evaluating whether each motion vector contained in and around the revised region is describable with the set of revised values or not, to thereby detect a newly revised region;Type: GrantFiled: July 13, 1995Date of Patent: May 5, 1998Assignee: Daewoo Electronics Co., Ltd.Inventors: Gyu-Hwan Chang, Hae-Mook Jung, Seong-Dae Kim, Jae-Gark Choi, Si-Woong Lee
-
Patent number: 5734737Abstract: A method, for use in an object-oriented analysis-synthesis coder, for segmenting an image signal into moving objects contained in a current frame and describing each motion of the moving objects with a set of motion parameters using a multi-stage segmentation comprises the steps of: (a) comparing the current frame with its preceding frame to detect a moving area in the current frame; (b) further comparing the current frame with the preceding frame to detect a motion vector for each pixel in the moving area, i.e., a motion vector field; (c) first segmenting the motion vector field by using a two dimensional translational patch model; (d) secondly segmenting the first stage segmenting results by using a planar patch model; and (e) thirdly segmenting the second-stage segmenting results by using a parabolic patch model.Type: GrantFiled: July 13, 1995Date of Patent: March 31, 1998Assignee: Daewoo Electronics Co., Ltd.Inventors: Gyu-Hwan Chang, Hae-Mook Jung, Seong-Dae Kim, Jae-Gark Choi, Si-Woong Lee, Soon-Jae Cho
-
Patent number: 5682341Abstract: An adaptive signal processor using a Newton/least mean square (LMS) algorithm, adapted to remove a signal distortion or noise. The adaptive signal processor is adapted to derive an autocorrelation matrix from an input signal, derive an inverse matrix of the autocorrelation matrix by executing DCT twice or executing DFT and IDFT, and apply the derived inverse matrix to an adaptive signal processing, thereby capable of greatly reducing the total amount of computations to derive the inverse matrix, achieving an easy hardware realization thereof and reducing the manufacture cost thereof.Type: GrantFiled: April 19, 1995Date of Patent: October 28, 1997Assignee: Korea Advanced Institute of Science and TechnologyInventors: Seong-Dae Kim, Tae-Sung Kim
-
Patent number: 5633685Abstract: A processing block is processed by using an extension-interpolation ("E-I") method, wherein the processing block consisting of N.times.Type: GrantFiled: April 8, 1996Date of Patent: May 27, 1997Assignee: Daewoo Electronics Co., Ltd.Inventors: Soon-Jae Cho, Jae-Gark Choi, Si-Woong Lee, Yi-Han Kim, Seong-Dae Kim, Hae-Mook Jung
-
Patent number: 5502489Abstract: The present invention is a motion adaptive spatial filtering(MASF) method for use with a image coding apparatus, which proceeds the temporal band-limitation of the video frame signals on spatial domain along the trajectory of a moving component without temporal aliasing by using a filter having a band-limitation characteristic according to a cutoff frequency. It is well known that video signal may contain a lot of temporal aliasing components because of insufficient frame sampling rate. And it is impossible to design band-limiting temporal filter simply by convolving a sequence of frames along the temporal direction. From a signal processing point of view, the aliasing degrades filter characteristics. This filtering method takes advantage of the fact that, if motion of each pixel is known, the temporal filtering can be performed in the spatial domain filtering along its trajectory. That results in de-aliasing characteristic.Type: GrantFiled: January 3, 1994Date of Patent: March 26, 1996Assignee: Daewoo Electronics Co., Ltd.Inventors: Jong-Hun Kim, Seong-Dae Kim
-
Patent number: 5502510Abstract: A motion adaptive spatial filtering method is employed as a prefilter in an image coding apparatus, which processes the temporal band-limitation of a video signal without temporal aliasing by using a spatial filter having a band-limitation characteristic according to a desired temporal cutoff frequency.Type: GrantFiled: September 19, 1994Date of Patent: March 26, 1996Assignee: Daewoo Electronics Co., Ltd.Inventors: Jong-Hoon Kim, Seong-Dae Kim
-
Patent number: 5404138Abstract: An apparatus for decoding variable length codes utilizing a parallel processing based on a code classification wherein an address determining logic receives output data from a barrel shifter, determines addresses by groups according to the received data, classifies and designates addresses of a decoder look-up table by groups according to the addresses determined by groups. As a result, a high processing speed can be obtained, over the conventional serial processing system. Moreover, no code deformation is required as in Lukacs system. The memory capacity of the decoder look-up table can be reduced, as compared with the conventional parallel processing method. In addition, the present invention can be applied to decoding of all variable length codes having a prefix structure.Type: GrantFiled: October 26, 1993Date of Patent: April 4, 1995Assignee: Agency for Defense DevelopmentInventors: Seong Dae Kim, Yi Han Kim, Sang Zee Lee