公开(公告)号：US10685454B2

公开(公告)日：2020-06-16

申请号：US16204414

申请日：2018-11-29

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Young Hee Kim ,  Jin Seo Kim ,  Soon Chan Park ,  Jae Hui Park ,  Ji Young Park ,  Kwang Hyun Shim ,  Moon Wook Ryu ,  Hyuk Jeong

IPC: G06T7/579 ,  G06T11/00 ,  G06T15/50 ,  G06T15/08

Abstract: An apparatus and method for generating synthetic training data for motion recognition. The method includes generating a three-dimensional (3D) human body model in real time according to motion of a human body, converting volume data of the 3D human body model into a 3D linear structure and extracting skeletal joint information, generating a data set of a human body image and skeletal joint information by rendering the 3D human body model and the skeletal joint information, and providing the data set of the image and the skeletal joint information as synthetic training data for motion recognition.

公开(公告)号：US10212412B2

公开(公告)日：2019-02-19

申请号：US15064668

申请日：2016-03-09

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Ju Yong Chang ,  Jin Seo Kim ,  Hee Kwon Kim ,  Soon Chan Park ,  Ji Young Park ,  Kwang Hyun Shim ,  Moon Wook Ryu ,  Ho Wook Jang ,  Hyuk Jeong

IPC: H04N5/14 ,  H04N13/111 ,  H04N13/257 ,  H04N13/271 ,  H04N13/00

Abstract: A method of increasing a photographing speed of a photographing device which capture an image through a combination of two or more photographing devices and generate and provide an image by using the captured image, thereby increasing a photographing speed. An RGB image obtaining device and a depth image obtaining device alternately perform photographing to obtain an image. Also, a second depth image and a second RGB image respectively corresponding to a first RGB image and a first depth image which are alternately obtained by performing alternate photographing are synthesized and output, thereby actually increasing a photographing speed by twice.

公开(公告)号：US10186041B2

公开(公告)日：2019-01-22

申请号：US15078280

申请日：2016-03-23

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Ju-Yong Chang ,  Soon-Chan Park ,  Ji-Young Park ,  Jin-Seo Kim ,  Hee-Kwon Kim ,  Kwang-Hyun Shim ,  Moon-Wook Ryu ,  Ho-Wook Jang ,  Hyuk Jeong

IPC: G06K9/00 ,  G06T7/20 ,  G06T7/246

Abstract: An apparatus and method for analyzing a golf motion. The apparatus includes acquiring, by an image sensor of a camera unit, a 2D image of motion of a user, acquiring, by a depth sensor of the camera unit, a depth image to temporally alternate with acquisition of the 2D image, the depth image including depth values of pixels in the 2D image, increasing an image-capturing speed by generating a corresponding depth image or a corresponding 2D image, which corresponds to a reference 2D image or a reference depth image acquired at a predetermined time, outputting the reference 2D image and the corresponding depth image or the reference depth image and the corresponding 2D image as output data for motion analysis, extracting skeletal information of the user through analysis of output data, and displaying motion of the user on a display unit based on skeletal information.

公开(公告)号：US09412013B2

公开(公告)日：2016-08-09

申请号：US14591307

申请日：2015-01-07

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Moon Wook Ryu ,  Soonchan Park ,  Ju Yong Chang ,  Ji Young Park ,  Kwang Hyun Shim ,  Hee Kwon Kim ,  Hyuk Jeong ,  Seung Woo Nam

IPC: G06K9/00 ,  H04N5/33 ,  G06T7/00 ,  G06T7/20 ,  G06F3/033

CPC classification number: G06K9/00355 ,  G06T7/11 ,  G06T7/207 ,  G06T2207/10028 ,  G06T2207/10048 ,  H04N5/2256 ,  H04N5/23219 ,  H04N5/33 ,  H04N13/106 ,  H04N13/254 ,  H04N13/271

Abstract: A hand motion recognizing apparatus obtains an image with first resolution including a hand and an image with second resolution higher than the first resolution including the hand, maps the image with the first resolution and the image with the second resolution, extracts a hand position from the image with the first resolution, obtains a hand region corresponding to the hand position from the image with the second resolution mapped to the image with the first resolution, and subsequently estimates a hand motion from the hand region.

Abstract translation: 手动识别装置以第一分辨率获得包括手的图像和具有比包括手的第一分辨率高的第二分辨率的图像，将具有第一分辨率的图像和具有第二分辨率的图像映射，从 具有第一分辨率的图像，从具有第二分辨率的图像获得与手位置相对应的手区域，其以第一分辨率映射到图像，并且随后估计来自手区域的手运动。

公开(公告)号：US20130223749A1

公开(公告)日：2013-08-29

申请号：US13781670

申请日：2013-02-28

Applicant: Electronics and Telecommunications Research Institute

Inventor： Sang-Il NA ,  Keun-Dong Lee ,  Weon-Geun OH ,  Hyuk Jeong ,  Sung-Kwan Je ,  Dong-Seok Jeong

IPC: G06K9/46 ,  G06K9/62

CPC classification number: G06K9/46 ,  G06K9/4676 ,  G06K9/6201

Abstract: An image recognition apparatus using a scalable compact local feature descriptor is provided. The image recognition apparatus includes a feature descriptor generator, a database, and a descriptor matcher. The feature descriptor generator extracts scalable compact local feature descriptor information for recognizing an object from input image information. The database includes information on a plurality of feature descriptors. The descriptor matcher compares a feature descriptor output from the feature descriptor generator with a plurality of feature descriptors stored in the database to recognize an object included in an image.

Abstract translation: 提供了一种使用可缩放紧凑局部特征描述符的图像识别装置。 图像识别装置包括特征描述符生成器，​​数据库和描述符匹配器。 特征描述符生成器从输入图像信息中提取用于识别对象的可缩放紧凑局部特征描述符信息。 数据库包括关于多个特征描述符的信息。 描述符匹配器将从特征描述符生成器输出的特征描述符与数据库中存储的多个特征描述符进行比较，以识别图像中包括的对象。