-
1.发明申请APPARATUS AND METHOD FOR INPUTTING AND OUTPUTTING STEREO LIGHT FIELD SUPPORTING GENERATION OF EYE'S MOVED POINT OF SIGHT 审中-公开用于输入和输出立体光场的装置和方法支持眼睛移动点的生成公开(公告)号：US20150208060A1
公开(公告)日：2015-07-23
申请号：US14604120
申请日：2015-01-23
发明人： Do Hyung KIM , Il Kyu PARK , Seong Jin PARK , Bon Ki KOO , Jin Sung CHOI
CPC分类号： H04N13/279 , G06F3/013 , H04N13/243 , H04N13/282 , H04N13/383
摘要： Provided are an apparatus and method for inputting and outputting a stereo light field supporting generation of an eye's moved point of sight. The apparatus includes an image acquisition unit configured to acquire light field data of an object and transmit the acquired light field data, and an image output unit configured to receive the light field data transmitted by the image acquisition unit, generate images according to the points of sight of a viewer's both eyes using the received light field data, and output the generated images.
摘要翻译： 提供一种用于输入和输出支持眼睛移动的视线的产生的立体光场的装置和方法。 该装置包括：图像获取单元，被配置为获取对象的光场数据并发送获取的光场数据;以及图像输出单元，被配置为接收由图像获取单元发送的光场数据，根据 使用接收的光场数据观察观众的双眼，并输出所生成的图像。
-
公开(公告)号：US20230147274A1
公开(公告)日：2023-05-11
申请号：US17903364
申请日：2022-09-06
发明人： Woo Han YUN , Do Hyung KIM , Jae Hong KIM , Tae Woo KIM , Chan Kyu PARK , Ho Sub YOON , Jae Yeon LEE , Min Su JANG
CPC分类号： G06V20/68 , G06V10/25 , G06V10/255 , G06V2201/07 , G06Q50/12
摘要： Disclosed herein a method and apparatus for recommending a table service based on image recognition. According to an embodiment of the present disclosure, there is provided a method for recommending a table service, including: receiving a table image that is captured in real time; acquiring, by using an artificial intelligence of a pre-learned learning model, table information that includes object information and food information of at least one table in the table image; and recommending, based on the table information, a service for each of the at least one table.
-
公开(公告)号：US20150208056A1
公开(公告)日：2015-07-23
申请号：US14309820
申请日：2014-06-19
发明人： Il Kyu PARK , Do Hyung KIM , Seong Jin PARK , Jin Sung CHOI , Bon Ki KOO
CPC分类号： H04N13/139 , H04N13/106
摘要： Provided are three-dimensional (3D) data processing apparatus and method. 3D stereoscopic image common format data preserving common 3D image information is defined by converting 3D stereoscopic image data of each format to apply the same 3D image processing algorithm to 3D data of various formats, and native format data of each format is maintained to maintain merits of each format, and a format-specific algorithm table is maintained with respect to a common 3D image processing function, whereby the same 3D image processing algorithm may be applied to various 3D data and a unique algorithm allowing for maintaining the merits of each 3D data may be applied.
摘要翻译： 提供了三维（3D）数据处理装置和方法。 通过转换每种格式的3D立体图像数据来定义保持公共3D图像信息的3D立体图像通用格式数据，以将相同的3D图像处理算法应用于各种格式的3D数据，并且保持每种格式的本机格式数据以保持优点 相对于共同的3D图像处理功能，维持每个格式和格式特定算法表，由此可以将相同的3D图像处理算法应用于各种3D数据，并且允许维持每个3D数据的优点的唯一算法 应用。
-
4.发明申请公开(公告)号：US20230071310A1
公开(公告)日：2023-03-09
申请号：US17513362
申请日：2021-10-28
发明人： Seongjin PARK , Do Hyung KIM
IPC分类号： H04N13/282 , H04N13/111 , G06N3/08 , H04N13/246
摘要： Disclosed are an electronic device generating a multi-plane image of an arbitrary viewpoint and an operating method thereof. The electronic device includes a memory that stores a plurality of images, and at least one processor that executes a machine learning-based multi-plane image generating module generating an image of an arbitrary viewpoint from the plurality of images stored in the memory. When the multi-plane image generating module is executed, the processor selects at least two images from the plurality of images, by performing geometric calibration on the plurality of images, calculates a plane sweep volume including at least two layer images, performs an operation of a deep neural network to generate a plurality of multi-plane images having probability values, and generates the image of the arbitrary viewpoint by composing the plurality of multi-plane images and stores the image of the arbitrary viewpoint in the memory.
-
5.发明申请公开(公告)号：US20180167599A1
公开(公告)日：2018-06-14
申请号：US15834237
申请日：2017-12-07
发明人： Seong Jun BAE , Ho Wook JANG , Wook Ho SON , Jae Woo KIM , Do Hyung KIM , Seong Jin PARK
CPC分类号： H04N13/111 , G06T7/73 , G06T19/006 , G06T2207/10012 , G06T2207/10148 , H04N5/22541 , H04N5/2258 , H04N13/243 , H04N13/282
摘要： An arbitrary viewpoint image generation method includes obtaining an original image set photographed by a plurality of cameras included in a camera array at each of at least one focal distance at a same time point; obtaining a multi-focus image set by generating a multi-focus image from the original image set for each of the at least one focal distance; and generating an arbitrary viewpoint image at a position where a viewpoint is to be moved from the multi-focus image set.
-
公开(公告)号：US20170266656A1
公开(公告)日：2017-09-21
申请号：US15432671
申请日：2017-02-14
发明人： Dae-Sik LEE , Jeong Won PARK , Moon Youn JUNG , Do Hyung KIM , Jae Ku LEE , Hun Seok LEE
IPC分类号： B01L3/00
CPC分类号： B01L3/508 , B01L3/502753 , B01L2200/0652 , B01L2200/0668 , B01L2300/0809 , B01L2300/0816 , B01L2300/0848 , B01L2400/086
摘要： Provided is a cell capturing cartridge. According to an embodiment of the inventive concept, the cell capturing cartridge may include a substrate and structures provided on an upper surface of the substrate and constituting a plurality of rows that are parallel to a row direction. The structures in one row may be offset from the structures in the neighboring rows in the row direction. Each of the substrates may have a first side surface facing one side of the substrate and a second side surface disposed opposite to the first side surface and having a width greater than that of the first side surface.
-
公开(公告)号：US20170255877A1
公开(公告)日：2017-09-07
申请号：US15167861
申请日：2016-05-27
发明人： Hyunwoo CHO , Do Hyung KIM , Cheol RYU , Seok Jin YOON , Jae Ho LEE , Hyung-Seok LEE , Kyung Hee LEE
IPC分类号： G06N99/00
CPC分类号： G06N20/00 , G06F9/5083
摘要： There is provided a heterogeneous computing method. A heterogeneous computing method includes performing offline learning on an algorithm using compilations and runtimes of application programs, executing a first application program in a mobile device, distributing a workload to a central processing unit (CPU) and a graphic processing unit (GPU) in the first application program, using the algorithm, performing online learning to reset the workload distributed to the CPU and GPU in the first application program, and resetting the workload distributed to the CPU and GPU in the first application program, corresponding to a result of the online learning.
-
公开(公告)号：US20160216770A1
公开(公告)日：2016-07-28
申请号：US14663188
申请日：2015-03-19
发明人： Min Su JANG , Do Hyung KIM , Jae Hong KIM , Nam Shik PARK , Mun Sung HAN , Cheon Shu PARK , Sung Woong SHIN
CPC分类号： G06F3/017 , G06F3/0304 , G06F19/3481 , G06K9/00342
摘要： The present invention relates to a motion based interactive service method and system which provide various motion based interactive services such as repeated training of a motion, progressive difficulty adjustment, evaluation for every body part, and feedback based on the analysis result of the user's motion so that a user of a dance game or a dance lesson can efficiently perform a motion based performance or take a lesson by easy and various methods.
摘要翻译： 本发明涉及基于运动的交互式服务方法和系统，其提供各种基于运动的交互服务，例如运动的重复训练，逐步难度调整，每个身体部位的评估以及基于用户运动的分析结果的反馈 舞蹈游戏或舞蹈课程的用户可以通过简单和多种方法有效地执行基于运动的表演或进行教训。
-
公开(公告)号：US20240271916A1
公开(公告)日：2024-08-15
申请号：US18435861
申请日：2024-02-07
发明人： Do Hyung KIM
IPC分类号： F41J5/02 , F41J3/00 , G06T7/70 , H04N23/957
CPC分类号： F41J5/02 , F41J3/0009 , G06T7/70 , H04N23/957 , G06T2207/10016 , G06T2207/10052 , G06T2207/20221
摘要： A method of detecting the location of a dart pin is disclosed by the present disclosure, of which at least one embodiment provides a method of detecting a location of a dart pin attached to a dart target plate, including generating refocused images for multiple preset focal planes based on plenoptic videos of the dart target plate, which are obtained by using one or more cameras disposed around the dart target plate, generating, based on the refocused images, an extracted image for an object dart pin located in one focal plane of the multiple preset focal planes, and determining an attachment location of the object dart pin based on the extracted image.
-
10.发明申请公开(公告)号：US20190139228A1
公开(公告)日：2019-05-09
申请号：US16181144
申请日：2018-11-05
发明人： Seong Jin PARK , Do Hyung KIM , Jae Woo KIM , Seong Jun BAE , Ho Wook JANG
摘要： Disclosed is an apparatus and method of segmenting an object. An object segmentation method according to the present disclosure includes: receiving an input image; receiving an user input indicating at least one piece of information on a foreground region and a background region included in the input image; generating at least one among a foreground pixel list and a background pixel list using the received user input; calculating Gaussian distribution of at least one pixel that makes up the input image using at least one among the generated foreground pixel list and background pixel list; and determining whether the at least one pixel is a foreground pixel or a background pixel using the calculated Gaussian distribution.
-
-
-
-
-
-
-
-
-
搜索结果
20 条记录 (耗时 0.02 秒)
