Electronics and Telecommunications Research Institute

Samsung Electronics Co., Ltd.

Jae-Yeon Lee

Do-Hyung Kim

Jae-Hong Kim

Min-Su Jang

Young-Jo Cho

Young-Woo Yoon

Kye-Kyung Kim

Hye-Jin Kim

Sung-Woong Shin

Ho-Sub Yoon

Su-Young Chi

Soo-Hyun Cho

Hyun-Soo Kim

Seung-Yong Lee

Dong-Uk Choi

Young-Chul Park

Yong-suk Choi

Jeong-Dan Choi

Je-Han Yoon

Joon-Woo Lee

Joong-Bae Kim

Yu-Cheol Lee

Hong-Je Cho

Myung-Chan Roh

Kyu-sang Kim

Kwan-Tack Lim

Seo-Hyun Jeon

Ji-Hyo Lee

Sang-Seung Kang

Woo-Han Yun

Cheon-Shu Park

Jin-Su Kim

Seung-Hwan Park

Jin-Hyeok Jang

Seung-Hwan Chon

Woo-Ri Ko

Chan-Kyu Park

Soo-Young Chi

Disclosed herein are an apparatus and method for evaluating a human motion using a mobile robot. The method may include identifying the exercise motion of a user by analyzing an image of the entire body of the user captured using a camera installed in the mobile robot, evaluating the pose of the user by comparing the standard pose of the identified exercise motion with images of the entire body of the user captured by the camera of the mobile robot from two or more target locations, and comprehensively evaluating the exercise motion of the user based on the pose evaluation information of the user from each of the two or more target locations.

Apparatus and method for evaluating human motion using mobile robot

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.

Apparatus and method for classifying clothing attributes based on deep learning

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.

Apparatus and method for generating robot interaction behavior

Disclosed herein are an autonomous driving robot apparatus and an autonomous driving method. The autonomous driving method of the autonomous driving robot apparatus includes receiving task information for autonomous driving from a server device for supporting autonomous driving; creating a route for autonomous driving based on the task information and performing autonomous driving; and selecting an autonomous driving operation corresponding to any one of moving, waiting, and wandering when arriving at a preset destination by performing autonomous driving along the route.

Autonomous driving robot apparatus and method for autonomously driving the robot apparatus

Disclosed herein are an interaction apparatus and method. The interaction apparatus includes an input unit for receiving multimodal information including an image and a voice of a target to allow the interaction apparatus to interact with the target, a recognition unit for recognizing turn-taking behavior of the target using the multimodal information, and an execution unit for taking an activity for interacting with the target based on results of recognition of the turn-taking behavior.

Interaction apparatus and method for determining a turn-taking behavior using multimodel information

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.

Human behavior recognition apparatus and method

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.

Apparatus for determining speech properties and motion properties of interactive robot and method thereof

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.

Bin-picking system and method for bin-picking

A system and method for verifying the face of a user using a light mask are provided. The system includes a facial feature extraction unit for extracting a facial feature vector from a facial image received from a camera. A non-user Gaussian Mixture Model (GMM) configuration unit generates a non-user GMM from a facial image stored in a non-user database (DB). A user GMM configuration unit generates a user GMM by applying light masks to a facial image stored in a user DB. A log-likelihood value calculation unit inputs the facial feature vector both to the non-user GMM and to the user GMM, thus calculating log-likelihood values. A user verification unit compares the calculated log-likelihood values with a predetermined threshold, thus verifying whether the received facial image is a facial image of the user.

System and method for verifying face of user using light mask

In realizing a user recognition system and a method thereof, a user feature vector is extracted from an input facial image, and at least one cluster is generated and a user feature template is enrolled. The cluster includes the feature vector as a member of it. When a user facial image is inputted, a user feature vector is extracted from the image, and a similarity between the feature vector and the user feature template is calculated. When the similarity is greater than a predetermined threshold value, a user of the user feature template is recognized as the user of the input image.

User recognition system and method thereof

A target detecting system and method for detecting a target from an input image is provided. According to the target detecting system and method, when a target is detected from an input image and there are moving areas in the input image, camera movement parameters are obtained, image frames are transformed, and movement candidate areas are extracted from the image frame and the previous input image frame. In addition, image feature information is extracted from the input image, and based on the movement candidate areas and the image feature information a shape of the target is extracted. Therefore, the target can be exactly and rapidly extracted and tracked.

Target detecting system and method

A user recognizing system and method is provided. According to the user recognizing system and method, user ID and predetermined user feature information are stored, first and second user feature information are extracted from the user image data transmitted from the image input unit, and first and second probabilities that the extracted first and second user feature information determine the predetermined user are respectively generated based on the information stored at the user information database, the first user feature information being absolutely unique biometric information and the second user feature information being unique semibiometric information under a predetermined condition, and ID of the input image is finally determined by combining the first probability and the second probability. According to the user recognizing system and method, a user identity can be authenticated even when the user freely moves.

User authentication system and method thereof

An etchant for removing an indium oxide layer includes sulfuric acid as a main oxidizer, an auxiliary oxidizer such as HPO, HNO, CHCOOH, HClO, HO, and a Compound A that is obtained by mixing potassium peroxymonosulfate (2KHSO), potassium bisulfate (KHSO), and potassium sulfate (KSO) together in the ratio of 5:3:2, an etching inhibitor comprising an ammonium-based material, and water. The etchant may remove desired portions of the indium oxide layer without damage to a photoresist pattern or layers underlying the indium oxide layer.

Etchant composition for indium oxide layer and etching method using the same

Growing community of inventors

Daejeon, South Korea

Jae-Yeon Lee