-
公开(公告)号：US20230053151A1
公开(公告)日：2023-02-16
申请号：US17496588
申请日：2021-10-07
Inventor： Chan-Kyu PARK , Do-Hyung KIM , Jae-Hong KIM , Jae-Yeon LEE , Min-Su JANG
Abstract: Disclosed herein are an apparatus and method for classifying clothing attributes based on deep learning. The apparatus includes memory for storing at least one program and a processor for executing the program, wherein the program includes a first classification unit for outputting a first classification result for one or more attributes of clothing worn by a person included in an input image, a mask generation unit for outputting a mask tensor in which multiple mask layers respectively corresponding to principal part regions obtained by segmenting a body of the person included in the input image are stacked, a second classification unit for outputting a second classification result for the one or more attributes of the clothing by applying the mask tensor, and a final classification unit for determining and outputting a final classification result for the input image based on the first classification result and the second classification result.
-
公开(公告)号：US20220055221A1
公开(公告)日：2022-02-24
申请号：US17105924
申请日：2020-11-27
Inventor： Woo-Ri KO , Do-Hyung KIM , Jae-Hong KIM , Young-Woo YOON , Jae-Yeon LEE , Min-Su JANG
Abstract: Disclosed herein are an apparatus and method for generating robot interaction behavior. The method for generating robot interaction behavior includes generating co-speech gesture of a robot corresponding to utterance input of a user, generating a nonverbal behavior of the robot, that is a sequence of next joint positions of the robot, which are estimated from joint positions of the user and current joint positions of the robot based on a pre-trained neural network model for robot pose estimation, and generating a final behavior using at least one of the co-speech gesture and the nonverbal behavior.
-
3.发明申请公开(公告)号：US20190164548A1
公开(公告)日：2019-05-30
申请号：US16102398
申请日：2018-08-13
Inventor： Young-Woo YOON , Jae-Hong KIM , Jae-Yeon LEE , Min-Su JANG
Abstract: Disclosed herein are an apparatus and method for determining the speech and motion properties of an interactive robot. The method for determining the speech and motion properties of an interactive robot includes receiving interlocutor conversation information including at least one of voice information and image information about an interlocutor that interacts with an interactive robot, extracting at least one of a verbal property and a nonverbal property of the interlocutor by analyzing the interlocutor conversation information, determining at least one of a speech property and a motion property of the interactive robot based on at least one of the verbal property, the nonverbal property, and context information inferred from a conversation between the interactive robot and the interlocutor, and controlling the operation of the interactive robot based on at least one of the determined speech property and motion property of the interactive robot.
-
4.发明申请APPARATUS FOR PROVIDING VIRTUAL CONTENTS TO AUGMENT USABILITY OF REAL OBJECT AND METHOD USING THE SAME 审中-公开用于提供虚拟内容的装置实现对象的实用性和使用该对象的方法公开(公告)号：US20170053449A1
公开(公告)日：2017-02-23
申请号：US15239037
申请日：2016-08-17
Inventor： Joo-Haeng LEE , Jae-Hong KIM , Woo-Han YUN , A-Hyun LEE , Jae-Yeon LEE
CPC classification number: G06T19/006 , G06F3/011 , G06F2203/011 , G06K9/00671 , G06T2200/04
Abstract: A virtual content provision apparatus and method for augmenting usability of a real object. The virtual content provision apparatus includes a real object information acquisition unit for acquiring real object information corresponding to a real object through an input module, a virtual content search unit for searching for any one piece of virtual content based on the real object information, a virtual interface projection unit for projecting a virtual interface corresponding to the virtual content onto the real object through an output module, a user input detection unit for detecting user input on the virtual interface based on the input module, and a virtual content provision unit for, when the user input is detected, extracting virtual information related to the user input based on the virtual content, and projecting and providing the virtual information to correspond to the real object information through the output module.
Abstract translation: 一种用于增加真实对象的可用性的虚拟内容提供装置和方法。 虚拟内容提供装置包括：真实对象信息获取单元，用于通过输入模块获取与真实对象相对应的实际对象信息;虚拟内容搜索单元，用于基于真实对象信息搜索任何一条虚拟内容;虚拟内容提供装置， 接口投影单元，用于通过输出模块将对应于虚拟内容的虚拟接口投射到实际对象上;用户输入检测单元，用于基于输入模块检测虚拟接口上的用户输入;以及虚拟内容提供单元，用于当 检测用户输入，基于虚拟内容提取与用户输入相关的虚拟信息，并通过输出模块投射并提供虚拟信息以对应于实际对象信息。
-
公开(公告)号：US20160284078A1
公开(公告)日：2016-09-29
申请号：US15079261
申请日：2016-03-24
Inventor： Kye-Kyung KIM , Sang-Seung KANG , Jae-Yeon LEE , Jae-Hong KIM , Joong-Bae KIM , Sung-Woong SHIN
CPC classification number: G06K9/4604 , G06K9/00664 , G06T7/12 , G06T7/73 , G06T2207/30108
Abstract: Disclosed are a bin-picking system and a bin-picking method. A bin-picking system includes a transformable bin-picking box; a supporting unit configured to support the bottom part of the bin-picking box and be movable upward and downward; and a control unit configured to change an alignment of at least one bin-picking candidate object by transforming the bin-picking box by controlling a movement of the supporting unit if no bin-picking target object is detected from the at least one bin-picking candidate object existing inside bin-picking box and placed on the supporting unit to facilitate detection of a bin-picking target object and bin-picking.
Abstract translation: 公开了一种拣选系统和拣选方法。 垃圾拣选系统包括可变形垃圾箱拾取箱; 支撑单元，其构造成支撑所述料仓拾取箱的底部并可上下移动; 以及控制单元，其被配置为通过如下方式来改变所述至少一个拣选候选对象的对齐：通过控制所述支持单元的移动，如果从所述至少一个拣选中检测到拣选目标对象， 存在于采摘箱内的候选物体，并放置在支撑单元上，以便于检测拣选目标物体和拣选。
-
Patent Agency Ranking
公开(公告)号：US20250069432A1
公开(公告)日：2025-02-27
申请号：US18434093
申请日：2024-02-06
Inventor： Ho-Sub YOON , Jae-Hong KIM , Jae-Yoon JANG
IPC: G06V40/16
Abstract: Disclosed herein are a facial recognition method and apparatus based on masking. The facial recognition method based on masking includes performing detection and normalization of a face area including five landmarks in an input image, separating a face portion other than a portion covered by an obstacle in the detected face area, generating a mask corresponding to the separated face portion when there is a portion covered by an obstacle in the separated face portion, applying the mask to an image in a face image registration database and extracting a feature of a masking region, and determining whether it is an identical person based on the extracted feature value.
-
公开(公告)号：US20200074158A1
公开(公告)日：2020-03-05
申请号：US16213833
申请日：2018-12-07
Inventor： Do-Hyung KIM , Jin-Hyeok JANG , Jae-Hong KIM , Sung-Woong SHIN , Jae-Yeon LEE , Min-Su JANG
Abstract: Disclosed herein are a human behavior recognition apparatus and method. The human behavior recognition apparatus includes a multimodal sensor unit for generating at least one of image information, sound information, location information, and Internet-of-Things (IoT) information of a person using a multimodal sensor, a contextual information extraction unit for extracting contextual information for recognizing actions of the person from the at least one piece of generated information, a human behavior recognition unit for generating behavior recognition information by recognizing the actions of the person using the contextual information and recognizing a final action of the person using the behavior recognition information and behavior intention information, and a behavior intention inference unit for generating the behavior intention information based on context of action occurrence related to each of the actions of the person included in the behavior recognition information.
-
公开(公告)号：US20240127587A1
公开(公告)日：2024-04-18
申请号：US18479499
申请日：2023-10-02
Inventor： Do-Hyung KIM , Ho-Beom JEON , Hyung-Min KIM , Jae-Hong KIM , Jeong-Dan CHOI
Abstract: Disclosed herein is a method for integrated anomaly detection. The method includes detecting a thing object and a human object in input video using a first neural network, and tracking the human object, and detecting an anomalous situation based on an object detection result and a human object tracking result.
-
公开(公告)号：US20220024046A1
公开(公告)日：2022-01-27
申请号：US17082843
申请日：2020-10-28
Inventor： Min-Su JANG , Do-Hyung KIM , Jae-Hong KIM , Jae-Yeon LEE
Abstract: Disclosed herein are an apparatus and method for determining a modality of interaction between a user and a robot. The apparatus includes memory in which at least one program is recorded and a processor for executing the program. The program may perform recognizing a user state and an environment state by sensing circumstances around a robot, determining an interaction capability state associated with interaction with a user based on the recognized user state and environment state, and determining the interaction behavior of the robot for the interaction with the user based on the user state, the environment state, and the interaction capability state.
-
公开(公告)号：US20200167583A1
公开(公告)日：2020-05-28
申请号：US16227327
申请日：2018-12-20
Inventor： Ho-Sub YOON , Jae-Yoon JANG , Jae-Hong KIM
Abstract: Disclosed herein are an apparatus and method for registering face poses for face recognition. The apparatus includes a face detection unit for detecting the face of a user from an image including the face of the user; a pose recognition unit for recognizing the face pose of the face of the user based on the degree of rotation of the face of the user; a registration interface unit for providing an interface for showing information about whether the face poses of the face of the user are registered; and a face registration unit for registering the face pose of the face of the user when the face pose of the face of the user is recognized as an unregistered face pose based on the interface.
-
-
-
-
-
-
-
-
-
Search Results
23
records
(took 0.019 seconds)
