Patents by Inventor Kazuhiko Nishibori
Kazuhiko Nishibori 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).
-
Publication number: 20220375040Abstract: A human region detection unit 32 of a mask generation unit 31 detects a target region from a captured image using a region determination result obtained by semantic segmentation, and a difference region detection result. A mask generation processing unit 33 resets a boundary between a target region and a non-target region on the basis of continuity of a pixel value of a captured image, in a boundary re-search region set to include a target region and a non-target region on the basis of a boundary between the target region and the non-target region, such as a background region, that is indicated by a region determination result, and generates a target region mask using the reset boundary. A filtering unit 35 generates an image in which a background region is blurred, by performing filter processing of a region in a captured image that corresponds to a target region mask, using a target region mask generated by the mask generation unit 31, and a blurring filter coefficient set by a filter setting unit 34.Type: ApplicationFiled: July 17, 2020Publication date: November 24, 2022Inventors: KAZUHIKO NISHIBORI, SHIHHAO WEN, TAKAMITSU GOTO
-
Patent number: 11496661Abstract: The present disclosure relates to an image processing apparatus, an image processing method, and a program that permit acquisition of a more natural-looking synthesized image. A first captured image depicting a first subject is separated into a foreground area and a background area. The first subject appears in the foreground area. The background area is an area other than the area where the first subject appears. Also, a blended image is generated to be displayed on a live view, in which the blended image is obtained by blending the foreground area and the background area of the first captured image with an output image that is output when a second subject is captured. Then, a synthesized image is generated by superimposing the foreground area of the first captured image on the second captured image depicting the second subject with reference to the blended image in such a manner that the backgrounds are substantially identical. The present technology is applicable, for example, to an imaging apparatus.Type: GrantFiled: February 8, 2019Date of Patent: November 8, 2022Assignee: SONY CORPORATIONInventors: Shihhao Wen, Kazuhiko Nishibori
-
Patent number: 11006098Abstract: Provided is a configuration to make a virtual viewpoint image be a more natural stereoscopic image. The virtual viewpoint image is transmitted/received between information processing apparatuses that execute bidirectional communication. A processor calculates a virtual viewpoint position corresponding to a position of a virtual camera that captures a virtual viewpoint image on the basis of viewing position information of a viewing user of the virtual viewpoint image, and generates the virtual viewpoint image corresponding to a captured image from the virtual viewpoint position. The virtual viewpoint image is generated based on the captured image of a real camera that captures an object user, and the virtual viewpoint image is generated by setting a capture direction of a virtual camera to a point C, wherein the point C is in a position different from the object user.Type: GrantFiled: April 7, 2017Date of Patent: May 11, 2021Assignee: SONY CORPORATIONInventors: Masato Akao, Kazuhiko Nishibori
-
Publication number: 20210067676Abstract: The present disclosure relates to an image processing apparatus, an image processing method, and a program that permit acquisition of a more natural-looking synthesized image. A first captured image depicting a first subject is separated into a foreground area and a background area. The first subject appears in the foreground area. The background area is an area other than the area where the first subject appears. Also, a blended image is generated to be displayed on a live view, in which the blended image is obtained by blending the foreground area and the background area of the first captured image with an output image that is output when a second subject is captured. Then, a synthesized image is generated by superimposing the foreground area of the first captured image on the second captured image depicting the second subject with reference to the blended image in such a manner that the backgrounds are substantially identical. The present technology is applicable, for example, to an imaging apparatus.Type: ApplicationFiled: February 8, 2019Publication date: March 4, 2021Inventors: SHIHHAO WEN, KAZUHIKO NISHIBORI
-
Publication number: 20190149807Abstract: A configuration to make a virtual viewpoint image be a more natural stereoscopic image is realized, the virtual viewpoint image being transmitted/received between information processing apparatuses that execute bidirectional communication. A virtual viewpoint position calculation unit configured to calculate a virtual viewpoint position corresponding to a position of a virtual camera that captures a virtual viewpoint image on the basis of viewing position information of a viewing user of the virtual viewpoint image, and a virtual viewpoint image generation unit configured to generate the virtual viewpoint image corresponding to a captured image from the virtual viewpoint position are included.Type: ApplicationFiled: April 7, 2017Publication date: May 16, 2019Inventors: MASATO AKAO, KAZUHIKO NISHIBORI
-
Patent number: 10136101Abstract: An information processing apparatus according to the present disclosure includes: a receiver unit that acquires information relevant to a sight line of a user of a communication partner from a communication partner terminal that performs remote communication; a face detection unit that detects information relevant to a position and a size of a face of the user of the communication partner, on the basis of a video signal that includes the face of the user of the communication partner; and a superimposition unit that displays and superimposes a sight line position of the user of the communication partner on the video signal including the face of the user of the communication partner, based on the information relevant to the sight line of the user of the communication partner and the information relevant to the position and the size of the face of the user of the communication partner.Type: GrantFiled: February 8, 2016Date of Patent: November 20, 2018Assignee: SONY CORPORATIONInventors: Masato Akao, Ryohei Okada, Junichi Tanaka, Kazuhiko Nishibori
-
Publication number: 20180077383Abstract: An information processing apparatus according to the present disclosure includes: a receiver unit that acquires information relevant to a sight line of a user of a communication partner from a communication partner terminal that performs remote communication; a face detection unit that detects information relevant to a position and a size of a face of the user of the communication partner, on the basis of a video signal that includes the face of the user of the communication partner and is received from the communication partner terminal; and a superimposition unit that displays and superimposes a sight line position of the user of the communication partner on the video signal that includes the face of the user of the communication partner, on the basis of the information relevant to the sight line of the user of the communication partner and the information relevant to the position and the size of the face of the user of the communication partner.Type: ApplicationFiled: February 8, 2016Publication date: March 15, 2018Inventors: MASATO AKAO, RYOHEI OKADA, JUNICHI TANAKA, KAZUHIKO NISHIBORI
-
Patent number: 9071832Abstract: Provided is an image processing device including a congruence degree detecting unit which detects a degree of congruence of each of multiple scenes with respect to an input image made of a two-dimensional image, a depth image generating unit which generates, with respect to the input image, depth images each obtained by a technique corresponding to each of the scenes, a blending unit which blends the depth images, which are generated by the depth image generating unit and each generated by a technique corresponding to each of the scenes, at a blending ratio based on the degree of congruence of each of the scenes, to generate a blended depth image, and a three-dimensional image generating unit which generates a three-dimensional image, which can be viewed three-dimensionally, made of a left-eye image and a right-eye image generated by shifting each pixel of the input image using the blended depth image.Type: GrantFiled: July 5, 2012Date of Patent: June 30, 2015Assignee: Sony CorporationInventors: Nobuo Ueki, Hironori Mori, Takashi Kojima, Yuki Tokizaki, Kazuhiko Nishibori, Seiji Kimura
-
Publication number: 20140071237Abstract: An apparatus may include a hardware processor and a storage medium. The storage medium may be coupled to the processor, and may store instructions. When executed by the processor, the instructions may cause the apparatus to determine a number of viewers. The instructions may also cause the apparatus to calculate a number of viewpoints based on the number of viewers. Additionally, the instructions may cause the apparatus to generate a plurality of images corresponding to the viewpoints.Type: ApplicationFiled: June 8, 2012Publication date: March 13, 2014Applicant: Sony CorporationInventors: Nobuo Ueki, Kazuhiko Nishibori
-
Patent number: 8503531Abstract: With regard to a subject block including a subject pixel and four adjacent blocks vertically and horizontally adjacent to the subject block, respective motion vectors of these blocks are considered as candidates of a pixel motion vector of the subject pixel. The block motion vectors are actually applied to the subject pixel, and one of the motion vectors that minimizes difference between pixel values of pixels used for inter-field interpolation is selected as the pixel motion vector of the subject pixel.Type: GrantFiled: March 28, 2005Date of Patent: August 6, 2013Assignee: Sony CorporationInventors: Koji Aoyama, Kazuhiko Nishibori, Xavier Michel, Masuyoshi Kurokawa
-
Patent number: 8411974Abstract: An image processing apparatus detecting, from an input image, a still-zone area disposed at an edge of the input image and displaying a same image continuously, the apparatus including: a difference calculation mechanism calculating a difference between pixel values of pixels located at a same position of the input image in different frames with each other for each pixel of the input image; a pixel-motion-information generation mechanism generating pixel-motion information indicating whether there is a change in the pixel values of the pixels of the input image on the basis of the difference; and a first detection mechanism comparing the pixel-motion information of a plurality of the pixels arranged in a first direction in the input image, and detecting a boundary position in the first direction between the still-zone area and an effective area excluding the still-zone area in the input image.Type: GrantFiled: December 10, 2009Date of Patent: April 2, 2013Assignee: Sony CorporationInventors: Shintaro Okada, Kazuhiko Nishibori
-
Publication number: 20130063424Abstract: Provided is an image processing device including a congruence degree detecting unit which detects a degree of congruence of each of multiple scenes with respect to an input image made of a two-dimensional image, a depth image generating unit which generates, with respect to the input image, depth images each obtained by a technique corresponding to each of the scenes, a blending unit which blends the depth images, which are generated by the depth image generating unit and each generated by a technique corresponding to each of the scenes, at a blending ratio based on the degree of congruence of each of the scenes, to generate a blended depth image, and a three-dimensional image generating unit which generates a three-dimensional image, which can be viewed three-dimensionally, made of a left-eye image and a right-eye image generated by shifting each pixel of the input image using the blended depth image.Type: ApplicationFiled: July 5, 2012Publication date: March 14, 2013Inventors: Nobuo UEKI, Hironori MORI, Takashi KOJIMA, Yuki TOKIZAKI, Kazuhiko NISHIBORI, Seiji KIMURA
-
Patent number: 8391623Abstract: An image processing apparatus includes a motion vector detection unit configured to detect a motion vector at a predetermined space position of a frame at a predetermined time from an input image of a plurality of temporally different frames and obtain a reliability of the motion vector; a motion vector evaluation unit configured to obtain, at each space position, an evaluation value of the motion vector at the space position that is within a predetermined range including a subject space position that is a space position of interest, on the basis of the reliability at the space position and a distance from the subject space position; and a motion vector correction unit configured to correct the motion vector at the subject space position on the basis of the evaluation value and the motion vector at the space position of the predetermined range.Type: GrantFiled: June 17, 2009Date of Patent: March 5, 2013Assignee: Sony CorporationInventors: Tomohiro Nishi, Kazuhiko Nishibori, Shintaro Okada, Toshinori Ihara
-
Patent number: 8244055Abstract: An image processing apparatus includes: a difference-value calculation mechanism calculating a difference value between the first accumulated value produced by accumulating luminance values of a plurality of pixels in a first image and the second accumulated value produced by accumulating luminance values of a plurality of pixels in a second image having a difference in time with the first image; a threshold-value creation mechanism for creating a plurality of threshold values on the difference value in accordance with the first accumulated value, corresponding to the luminance change levels in order to grade a luminance change between the first image and the second image by a luminance change level indicating a degree of the luminance change; and a luminance-change-level determination mechanism for determining the luminance change level corresponding to the difference value on the basis of the plurality of threshold values.Type: GrantFiled: June 23, 2009Date of Patent: August 14, 2012Assignee: Sony CorporationInventors: Shintaro Okada, Kazuhiko Nishibori, Tomohiro Nishi, Toshinori Ihara
-
Patent number: 8204124Abstract: An image processing apparatus includes a unit configured to calculate a sum of absolute differences between pixel values of pixels in a block of interest and pixel values of pixels in a reference block, a unit configured to compare sums of absolute differences calculated and to determine a minimum sum of absolute differences thereamong, a unit configured to estimate a motion vector for the pixel of interest using the reference pixel having the minimum sum of absolute differences and the pixel of interest, a unit configured to generate a motion-compensated image by using pixel values of the pixels as pixel values of corresponding pixels in the motion-compensated image, a unit configured to cumulatively add sums of absolute differences, and a unit configured to generate an interpolation image by mixing the pixels and corresponding pixels in the motion-compensated image according to an obtained cumulative-sum result.Type: GrantFiled: August 26, 2008Date of Patent: June 19, 2012Assignee: Sony CorporationInventors: Shintaro Okada, Kazuhiko Nishibori, Tomohiro Nishi, Toshinori Ihara, Masuyoshi Kurokawa
-
Publication number: 20100150462Abstract: An image processing apparatus detecting, from an input image, a still-zone area disposed at an edge of the input image and displaying a same image continuously, the apparatus including: a difference calculation mechanism calculating a difference between pixel values of pixels located at a same position of the input image in different frames with each other for each pixel of the input image; a pixel-motion-information generation mechanism generating pixel-motion information indicating whether there is a change in the pixel values of the pixels of the input image on the basis of the difference; and a first detection mechanism comparing the pixel-motion information of a plurality of the pixels arranged in a first direction in the input image, and detecting a boundary position in the first direction between the still-zone area and an effective area excluding the still-zone area in the input image.Type: ApplicationFiled: December 10, 2009Publication date: June 17, 2010Inventors: Shintaro OKADA, Kazuhiko Nishibori
-
Publication number: 20090324125Abstract: An image processing apparatus includes: a difference-value calculation mechanism calculating a difference value between the first accumulated value produced by accumulating luminance values of a plurality of pixels in a first image and the second accumulated value produced by accumulating luminance values of a plurality of pixels in a second image having a difference in time with the first image; a threshold-value creation mechanism for creating a plurality of threshold values on the difference value in accordance with the first accumulated value, corresponding to the luminance change levels in order to grade a luminance change between the first image and the second image by a luminance change level indicating a degree of the luminance change; and a luminance-change-level determination mechanism for determining the luminance change level corresponding to the difference value on the basis of the plurality of threshold values.Type: ApplicationFiled: June 23, 2009Publication date: December 31, 2009Inventors: Shintaro OKADA, Kazuhiko Nishibori, Tomohiro Nishi, Toshinori Ihara
-
Publication number: 20090324102Abstract: An image processing apparatus includes a difference calculation unit that obtains a luminance difference between images of two successive frames; an average calculation unit that calculates the average of luminance differences obtained for a predetermined number of successive frames; a change determination unit that determines, for each frame of the predetermined number of the successive frames, whether images of two successive frames including the frame are the same by comparing the luminance difference obtained for the frame with the average; and a display pattern determination unit that determines a temporal display pattern of images of the predetermined number of the successive frames from among a plurality of display patterns including a display pattern in which groups each having a certain number of successive frames in which the same image is displayed are regularly repeated, using a determination result obtained by the change determination unit.Type: ApplicationFiled: June 26, 2009Publication date: December 31, 2009Inventors: Shintaro OKADA, Kazuhiko NISHIBORI, Tomohiro NISHI, Toshinori IHARA
-
Publication number: 20090310876Abstract: An image processing apparatus includes a motion vector detection unit configured to detect a motion vector at a predetermined space position of a frame at a predetermined time from an input image of a plurality of temporally different frames and obtain a reliability of the motion vector; a motion vector evaluation unit configured to obtain, at each space position, an evaluation value of the motion vector at the space position that is within a predetermined range including a subject space position that is a space position of interest, on the basis of the reliability at the space position and a distance from the subject space position; and a motion vector correction unit configured to correct the motion vector at the subject space position on the basis of the evaluation value and the motion vector at the space position of the predetermined range.Type: ApplicationFiled: June 17, 2009Publication date: December 17, 2009Inventors: Tomohiro NISHI, Kazuhiko Nishibori, Shintaro Okada, Toshinori Ihara
-
Patent number: 7626601Abstract: A video signal processing apparatus for outputting an output video signal to a display unit and displaying an image based on an input video signal on the display unit includes a signal processor for dividing the input video signal into a predetermined number of signals and outputting the signals as the output video signal. The signals as the output video signal drive associated areas obtained by dividing a display-capable area of the display unit. In accordance with the display unit, the predetermined number of signals is set so that the clock frequency of each of the signals output as the output video signal is less than or equal to a clock frequency that can be processed by the display unit.Type: GrantFiled: July 6, 2006Date of Patent: December 1, 2009Assignee: Sony CorporationInventors: Toru Nishi, Mitsuyasu Asano, Kazuhiko Ueda, Masuyoshi Kurokawa, Kazuhiko Nishibori