-
公开(公告)号：US09449392B2
公开(公告)日：2016-09-20
申请号：US14280990
申请日：2014-05-19
Applicant: SAMSUNG ELECTRONICS CO., LTD. , IMPERIAL INNOVATIONS LTD.
Inventor： Jae Joon Han , Danhang Tang , Tae Kyun Kim , Seung Ju Han , Byung In Yoo , Chang Kyu Choi , Alykhan Tejani , Hyung Jin Chang
CPC classification number: G06T7/0046 , G06K9/00382 , G06K9/00389 , G06K9/6219 , G06K9/6256 , G06K9/6259 , G06K9/627 , G06K9/6282 , G06K2209/05 , G06T7/75 , G06T2207/10028 , G06T2207/20081 , G06T2207/30196
Abstract: An estimator training method and a pose estimating method using a depth image are disclosed, in which the estimator training method may train an estimator configured to estimate a pose of an object, based on an association between synthetic data and real data, and the pose estimating method may estimate the pose of the object using the trained estimator.
-
2.发明授权公开(公告)号：US09311713B2
公开(公告)日：2016-04-12
申请号：US14283646
申请日：2014-05-21
Applicant: SAMSUNG ELECTRONICS CO., LTD. , IMPERIAL INNOVATIONS LTD.
Inventor： Jae Joon Han , Danhang Tang , Tae Kyun Kim , Seung Ju Han , Byung In Yoo , Chang Kyu Choi , Alykhan Tejani , Hyung Jin Chang
CPC classification number: G06T7/0046 , G06K9/00382 , G06K9/00389 , G06K9/6219 , G06K9/6256 , G06K9/6259 , G06K9/627 , G06K9/6282 , G06K2209/05 , G06T7/75 , G06T2207/10028 , G06T2207/20081 , G06T2207/30196
Abstract: An estimator training method and a pose estimating method using a depth image are disclosed, in which the estimator training method may train an estimator configured to estimate a pose of an object, based on an association between synthetic data and real data, and the pose estimating method may estimate the pose of the object using the trained estimator.
Abstract translation: 公开了一种使用深度图像的估计器训练方法和姿态估计方法，其中估计器训练方法可以基于合成数据和实际数据之间的关联来训练被配置为估计对象的姿态的估计器，以及姿态估计 方法可以使用经过训练的估计器估计对象的姿态。
-
公开(公告)号：US09721151B2
公开(公告)日：2017-08-01
申请号：US14302908
申请日：2014-06-12
Applicant: Samsung Electronics Co., Ltd.
Inventor： Seung Ju Han , Jae Joon Han , Chang Kyu Choi
CPC classification number: G06K9/00335 , G06K9/00201 , G06K9/00362 , G06K9/342 , G06T7/254 , G06T2207/10028 , G06T2207/20072 , G06T2207/30196
Abstract: An apparatus for detecting an interfacing region in a depth image detects the interfacing region based on a depth of a first region and a depth of a second region which is an external region of the first region in a depth image.
-
公开(公告)号：US09690985B2
公开(公告)日：2017-06-27
申请号：US14074247
申请日：2013-11-07
Applicant: Samsung Electronics Co., Ltd.
Inventor： Jae Joon Han , Chang Kyu Choi , Chang Kyo Lee
CPC classification number: G06K9/00375 , G06K9/00201 , G06K9/4652 , G06K9/6282 , G06K9/6298
Abstract: An apparatus recognizes an object using a hole in a depth image. An apparatus may include a foreground extractor to extract a foreground from the depth image, a hole determiner to determine whether a hole is present in the depth image, based on the foreground and a color image, a feature vector generator to generate a feature vector, by generating a plurality of features corresponding to the object based on the foreground and the hole, and an object recognizer to recognize the object, based on the generated feature vector and at least one reference feature vector.
-
公开(公告)号：US09588658B2
公开(公告)日：2017-03-07
申请号：US14448045
申请日：2014-07-31
Applicant: Samsung Electronics Co., Ltd.
Inventor： Jae Joon Han , Chang Kyu Choi
IPC: G06F17/30 , G06F3/0484 , G06F3/0481 , G06F3/0488
CPC classification number: G06F3/0484 , G06F3/04812 , G06F3/04817 , G06F3/0488 , G06F17/30595
Abstract: A display information controlling apparatus and method are provided. The display information controlling apparatus may select at least one object from one or more objects based on a location of each of the one or more objects on a display and a location on the display corresponding to a user input signal. The display information controlling apparatus may perform a predetermined operation corresponding to the selected at least one object.
Abstract translation: 提供了显示信息控制装置和方法。 显示信息控制装置可以基于显示器上的一个或多个对象中的每一个的位置以及对应于用户输入信号的显示器上的位置，从一个或多个对象中选择至少一个对象。 显示信息控制装置可以执行与所选择的至少一个对象相对应的预定操作。
-
Patent Agency Ranking
公开(公告)号：US20130278633A1
公开(公告)日：2013-10-24
申请号：US13866218
申请日：2013-04-19
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Min Su Ahn , Seung Ju Han , Jae Joon Han , Do Kyoon Kim , Yong Beom Lee
IPC: G06T19/00
CPC classification number: G06T19/006
Abstract: A method and system for generating an augmented reality (AR) scene may include obtaining real world information including multimedia information and sensor information associated with a real world, loading an AR locator representing a scheme for mixing the real world information and at least one virtual object content and the real world information onto an AR container, obtaining the at least one virtual object content corresponding to the real world information using the AR locator from a local storage or an AR contents server, and visualizing AR information by mixing the real world information and the at least one virtual object content based on the AR locator.
Abstract translation: 用于生成增强现实（AR）场景的方法和系统可以包括获得包括与真实世界相关联的多媒体信息和传感器信息的真实世界信息，加载表示用于混合真实世界信息的方案的AR定位器和至少一个虚拟对象 内容和真实世界信息存储到AR容器上，使用来自本地存储器或AR内容服务器的AR定位器获得与真实世界信息相对应的至少一个虚拟对象内容，并通过混合现实世界信息和 所述至少一个虚拟对象内容基于所述AR定位器。
-
公开(公告)号：US20130271449A1
公开(公告)日：2013-10-17
申请号：US13858336
申请日：2013-04-08
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Chang Kyo LEE , Byung In Yoo , Chang Kyu Choi , Jae Joon Han
IPC: G06T15/08
Abstract: A method of generating three-dimensional (3D) volumetric data may be performed by generating a multilayer image, generating volume information and a type of a visible part of an object, based on the generated multilayer image, and generating volume information and a type of an invisible part of the object, based on the generated multilayer image. The volume information and the type of each of the visible part and invisible part may be generated based on the generated multilayered image which may be include at least one of a ray-casting-based multilayer image, a chroma key screen-based multilayer image, and a primitive template-based multilayer image.
Abstract translation: 可以通过生成多层图像，基于生成的多层图像生成体信息和对象的可见部分的类型，并且生成体积信息和类型的多个图像，来生成三维（3D）体积数据的方法 基于生成的多层图像，对象的不可见部分。 可以基于所生成的多层图像来生成可见部分和不可见部分中的每一个的体积信息和类型，所述多层图像可以包括基于射线铸造的多层图像，基于色度键屏幕的多层图像， 和基于模板的原始多层图像。
-
公开(公告)号：US12014571B2
公开(公告)日：2024-06-18
申请号：US17333915
申请日：2021-05-28
Applicant: Samsung Electronics Co., Ltd.
Inventor： SungUn Park , Hyeongwook Yang , Tushar Balasaheb Sandhan , Jiaqian Yu , Jingtao Xu , Youngjun Kwak , Juwoan Yoo , Jae Joon Han
CPC classification number: G06V40/168 , G06F18/211 , G06F18/251 , G06F18/253 , G06V10/803 , G06V40/193 , G06V40/45 , G06V40/161
Abstract: Provided is a liveness verification method and device. A liveness verification device acquires a first image and a second image, and select one or more liveness models based on respective analyses of the first image and the second image, including analyses based on an object part being detected in the first image and/or the second image, and to verify, using the selected one or more liveness models, a liveness of the object based on the first image and/or the second image. The first image may be a color image and the second image may be an Infrared image.
-
公开(公告)号：US10755162B2
公开(公告)日：2020-08-25
申请号：US15584611
申请日：2017-05-02
Applicant: Samsung Electronics Co., Ltd.
Inventor： Seung Ju Han , Jung Bae Kim , Jae Joon Han , Chang Kyu Choi
Abstract: A method to reduce a neural network includes: adding a reduced layer, which is reduced from a layer in the neural network, to the neural network; computing a layer loss and a result loss with respect to the reduced layer based on the layer and the reduced layer; and determining a parameter of the reduced layer based on the layer loss and the result loss.
-
公开(公告)号：US10163215B2
公开(公告)日：2018-12-25
申请号：US15296624
申请日：2016-10-18
Applicant: Samsung Electronics Co., Ltd.
Inventor： Byung In Yoo , Chang Kyu Choi , Chang Kyo Lee , Jae Joon Han
IPC: G06T15/20 , G06T15/40 , G06T7/00 , G06K9/00 , G06K9/46 , G06K9/62 , G06T7/73 , G06T15/06 , G06T15/08 , G06T17/00
Abstract: An object recognition system is provided. The object recognition system for recognizing an object may include an input unit to receive, as an input, a depth image representing an object to be analyzed, and a processing unit to recognize a visible object part and a hidden object part of the object, from the depth image, by using a classification tree. The object recognition system may include a classification tree learning apparatus to generate the classification tree.
-
-
-
-
-
-
-
-
-
Search Results
31
records
(took 0.023 seconds)
