-
公开(公告)号：KR1020130068611A
公开(公告)日：2013-06-26
申请号：KR1020110135904
申请日：2011-12-15
Applicant: 한국전자통신연구원
IPC: G06K9/46
CPC classification number: G06K9/4604 , G06F17/30893 , G06K2017/0083
Abstract: PURPOSE: A pattern recognition system and a method thereof are provided to improve the recognition performance of the system by extracting feature information from patterns and sharing the feature information between systems. CONSTITUTION: An LPRS(Local Pattern Recognition System)(100) extracts features about a recognition target in a pattern to grant a label to the recognition target based on the features and to generate an FS including the features and the label. An FSR(Feature Specification Repository)(200) stores the FS received from the LPRS and provides the FS to the LPRS. The LPRS extracts the features from the pattern and calculates similarity between the features and features included in the FS in order to determine the application of the label. [Reference numerals] (AA,BB) Feature specification
Abstract translation: 目的：提供模式识别系统及其方法，通过从模式中提取特征信息并在系统之间共享特征信息来提高系统的识别性能。 构成：LPRS（本地模式识别系统）（100）提取模式中的识别目标的特征，以基于特征向识别目标授予标签，并生成包括特征和标签的FS。 FSR（特征规范库）（200）存储从LPRS接收到的FS，并将FS提供给LPRS。 LPRS从模式中提取特征，并计算FS中包含的特征和特征之间的相似性，以确定标签的应用。 （附图标记）（AA，BB）特征规格
-
公开(公告)号：KR1020130067925A
公开(公告)日：2013-06-25
申请号：KR1020110134975
申请日：2011-12-14
Applicant: 한국전자통신연구원
CPC classification number: B25J9/1664 , B25J9/1674
Abstract: PURPOSE: A method for exploring areas using mobile robots is provided to prevent the exploring area from overlapping using a plurality of mobile robots. CONSTITUTION: A method for exploring areas using mobile robots comprises: a step of setting a temporary destination in the exploring area(220); a step of transferring to the predetermined destination(230); a step of setting a new temporary destination when arriving in the temporary destination; a step of repeating the second setting step and the transferring step; a step of changing the cell value of a cell in which is explored according to the transfer of the mobile robot(240); and a step of setting the new temporary destination considering the cell value by the mobile robot in the second setting step(260). [Reference numerals] (210) Initialize the cell values of a map; (220) Set a temporary destination; (230) Move; (231) Sensing range includes a predetermined range of cells?; (232) Initialize the cell value of a corresponding cell; (233) Transmit cell information; (240) Reduce(or increase) the cell values of the cells; (250) Arrived?; (260) Set a new temporary destination; (270) Search a target/The target is found?; (AA) Start; (BB,DD,FF) No; (CC,EE,GG) Yes; (HH) End
Abstract translation: 目的：提供使用移动机器人探索区域的方法，以防止探索区域与多个移动机器人重叠。 构成：使用移动机器人探索区域的方法包括：在探索区域（220）中设置临时目的地的步骤; 转移到预定目的地（230）的步骤; 到达临时目的地时设置新的临时目的地的步骤; 重复第二设定步骤和转印步骤的步骤; 根据移动机器人（240）的传送来改变其中探索的小区的小区值的步骤; 以及在第二设定步骤（260）中考虑移动机器人的单元值来设置新的临时目的地的步骤。 （附图标记）（210）初始化地图的单元格值; （220）设置临时目的地; （230）移动; （231）感测范围包括预定范围的单元格; （232）初始化相应单元格的单元格值; （233）发送小区信息; （240）减少（或增加）细胞的细胞值; （250）到达？ （260）设置新的临时目的地; （270）搜索目标/找到目标？ （AA）开始; （BB，DD，FF）否; （CC，EE，GG）是; （HH）结束
-
公开(公告)号：KR1020130064270A
公开(公告)日：2013-06-18
申请号：KR1020110130803
申请日：2011-12-08
Applicant: 한국전자통신연구원
Abstract: PURPOSE: An HRI(Human Robot Interaction)-integrated framework device and an HRI service providing method thereof are provided to supply a satisfied recognition result by continuously and permanently monitoring a volatile recognition result besides integrating individual recognition components. CONSTITUTION: A tracking unit(110) detects user information through sensors and tracks a user state based on the detected information. An ID recognizing unit(120) recognizes a user ID based on the detected information. A behavior recognizing unit(130) recognizes a user gesture based on the information. A multi integrating unit(140) integrates the user state, the user ID, and the user gesture and obtains HRI service information based on the integrated information. An interlinking unit(150) receives an HRI service from a service application and provides the HRI service to the user through the application. [Reference numerals] (110) Tracking unit; (120) ID recognizing unit; (130) Behavior recognizing unit; (140) Multi integrating unit; (145) Database; (150) Interlinking unit; (210) Camera; (220) Microphone
Abstract translation: 目的：提供HRI（人机交互） - 集成框架装置及其HRI服务提供方法，以便通过持续和永久地监视易失性识别结果以提供满意的识别结果，而不仅仅是集成了个体识别组件。 构成：跟踪单元（110）通过传感器检测用户信息，并基于检测到的信息跟踪用户状态。 ID识别单元（120）基于检测到的信息识别用户ID。 行为识别单元（130）基于该信息识别用户手势。 多积分单元（140）集成了用户状态，用户ID和用户手势，并且基于综合信息获得HRI服务信息。 互连单元（150）从服务应用接收HRI服务，并通过应用向用户提供HRI服务。 （附图标记）（110）跟踪单元; （120）识别识别单元; （130）行为识别单元; （140）多重整合单元; （145）数据库; （150）互连单元; （210）相机; （220）麦克风
-
公开(公告)号：KR1020130051680A
公开(公告)日：2013-05-21
申请号：KR1020110116969
申请日：2011-11-10
Applicant: 한국전자통신연구원
IPC: G06K9/46
CPC classification number: G06K9/00664 , G06K9/00248 , G06K9/00288 , G06K9/036
Abstract: PURPOSE: A user face recognition device in a robot and a method thereof are provided to recognize the frequent change of an illumination environment when a robot and a user move at the same time, thereby recognizing the face from a long distance. CONSTITUTION: A face detection unit(130) detects a square area, which a face is located, from an image photographed by a camera. A preprocessing unit(150) performs geometric normalization in a detected face image. The preprocessing unit improves the image quality for removing the interference of the background and illumination. A feature extraction unit(160) extracts a feature vector necessary for face recognition in the face image. A matching and classifying unit(170) assigns ID of the matched face by matching the feature vectors of the face and the extracted feature vectors. [Reference numerals] (110) Camera unit; (120) Image input unit; (130) Face detection unit; (140) Adaboosting database; (150) Preprocessing unit; (160) Feature extraction unit; (170) Matching and classifying unit
Abstract translation: 目的：提供机器人中的用户面部识别装置及其方法，以识别当机器人和用户同时移动时照明环境的频繁变化，从而从长距离识别脸部。 构成：面部检测单元（130）从由照相机拍摄的图像检测脸部所在的正方形区域。 预处理单元（150）在检测到的脸部图像中执行几何归一化。 预处理单元提高了图像质量，以消除背景和照明的干扰。 特征提取单元（160）提取面部图像中的面部识别所需的特征向量。 匹配和分类单元（170）通过匹配面部的特征向量和提取的特征向量来分配匹配面部的ID。 （附图标记）（110）相机单元; （120）图像输入单元; （130）面部检测单元; （140）收购数据库; （150）预处理单元; （160）特征提取单元; （170）匹配和分类单位
-
公开(公告)号：KR1020120075595A
公开(公告)日：2012-07-09
申请号：KR1020100129528
申请日：2010-12-16
Applicant: 한국전자통신연구원
CPC classification number: G06Q50/22 , B25J13/006
Abstract: PURPOSE: A user visiting taking medicine supporting method and robot apparatus thereof are provided to solve inconvenience problems which a user who has a low cognitive ability need to visit a hospital by directly transmitting prescribed medicine to the user. CONSTITUTION: A robot receives medicines according to a prescription(80). The robot moves to a current location of a user(82). After the moved robot confirms the user, the robot measures health states of the user(84,85). The robot transmits the measured health state information to a doctor or a pharmacist. The robot receives the taking medicine state information of the user from the doctor or the pharmacist. When information for a normal state is received, the robot distributes the medicines(88).
Abstract translation: 目的：提供访问药物支持方法的用户和机器人装置，以解决低认知能力的用户通过直接向用户发送处方药而访问医院的不便问题。 规定：机器人按照处方方式接收药品（80）。 机器人移动到用户的当前位置（82）。 移动的机器人确认用户后，机器人会测量用户的健康状况（84,85）。 机器人将测量的健康状态信息传送给医生或药剂师。 机器人从医生或药剂师接收用户的服药状态信息。 当接收到用于正常状态的信息时，机器人分发药品（88）。
-
Patent Agency Ranking
公开(公告)号：KR1020120072253A
公开(公告)日：2012-07-03
申请号：KR1020100134091
申请日：2010-12-23
Applicant: 한국전자통신연구원
IPC: G01S1/68
CPC classification number: H04W64/00 , G01S1/68 , G01S5/0252 , G01S5/0263
Abstract: PURPOSE: A locating device and method are provided to improve the accuracy of positioning by combining various context information when locating a user-carrying/wearing device associated with an RF based radio network. CONSTITUTION: A locating unit(107) calculates the location of a mobile RF node based on the location information of a fixed RF node and a message inputted from the mobile RF node and outputs the location information of the mobile RF node. A context storage unit(109b) stores a recognition result inputted from a recognition device as context information on user's location. An inferring unit(108) corrects the distortion of the location information of the mobile RF node inputted from the locating unit by referring to the context information stored in the context storage unit.
Abstract translation: 目的：提供一种定位装置和方法，用于在定位与基于RF的无线电网络相关联的用户携带/佩戴装置时，通过组合各种上下文信息来提高定位精度。 构成：定位单元（107）基于固定RF节点的位置信息和从移动RF节点输入的消息来计算移动RF节点的位置，并输出移动RF节点的位置信息。 上下文存储单元（109b）将从识别装置输入的识别结果存储为用户位置的上下文信息。 推测单元（108）通过参照上下文存储单元中存储的上下文信息来校正从定位单元输入的移动RF节点的位置信息的失真。
-
公开(公告)号：KR1020120071738A
公开(公告)日：2012-07-03
申请号：KR1020100133404
申请日：2010-12-23
Applicant: 한국전자통신연구원
CPC classification number: H04N7/188
Abstract: PURPOSE: An environment sensor stabilizing system and a method for operating a moving object corresponding to asymmetric environments are provided to recognize an environment by using a robot and to establish a map when shaking by compensating a sensor output value. CONSTITUTION: An environment sensor stabilizing system for operating a moving object corresponding to asymmetric environments comprises a sensor unit(104), a signal synchronization unit(112), an amplitude extraction unit(114), and an image correction unit(116). The sensor unit detects vibration of a moving object, thereby outputting sensing signals. The signal synchronization part synchronizes signals by mapping captured images of an image photographing module(102) and sensing signals of the sensor unit. The amplitude extraction unit extracts inclination information of the moving object based on the sensing signals of the sensor unit and calculates a visual field and movement distance of the moving object based on the inclination information. The image correction unit generates corrected images by performing a coordination conversion of the captured images by using the visual field and movement distance.
Abstract translation: 目的：提供一种环境传感器稳定系统和用于操作对应于不对称环境的移动物体的方法，以通过使用机器人来识别环境，并通过补偿传感器输出值来振动时建立地图。 构成：用于操作对应不对称环境的运动物体的环境传感器稳定系统包括传感器单元（104），信号同步单元（112），振幅提取单元（114）和图像校正单元（116）。 传感器单元检测移动物体的振动，从而输出感测信号。 信号同步部分通过映射图像拍摄模块（102）的拍摄图像和传感器单元的感测信号来同步信号。 幅度提取单元基于传感器单元的感测信号提取移动物体的倾斜信息，并且基于倾斜信息计算移动物体的视野和移动距离。 图像校正单元通过使用视场和移动距离进行拍摄图像的协调转换来生成校正图像。
-
公开(公告)号：KR1020120070340A
公开(公告)日：2012-06-29
申请号：KR1020100131859
申请日：2010-12-21
Applicant: 한국전자통신연구원
IPC: G06K9/46
CPC classification number: G06T7/254 , G06T7/194 , G06T2207/20224
Abstract: PURPOSE: An object tracking apparatus and method thereof are provided to reduce object tracking failure rates in the change of a background area by accurately confirming the boundary of an object. CONSTITUTION: An object analysis unit(301) analyzes the inputted image of an object area as object feature information. A background analysis unit(302) analyzes a back ground area for the object area background feature information. The object analysis unit tracks the object area by using the analyzed background feature information and the analyzed object feature information. The background analysis unit includes a background modeling unit. The background modeling unit models the background area as the background feature information.
Abstract translation: 目的：提供一种物体跟踪装置及其方法，通过准确地确认对象的边界来减少背景区域的改变中的物体跟踪失败率。 构成：对象分析单元（301）将对象区域的输入图像分析为对象特征信息。 背景分析单元（302）分析对象区背景特征信息的背景区域。 对象分析单元通过使用分析的背景特征信息和分析对象特征信息来跟踪对象区域。 背景分析单元包括背景建模单元。 背景建模单元将背景区域作为背景特征信息进行建模。
-
公开(公告)号：KR1020120064571A
公开(公告)日：2012-06-19
申请号：KR1020100125854
申请日：2010-12-09
Applicant: 한국전자통신연구원
Abstract: PURPOSE: Apparatus and method for controlling waking assist robot is provided to assist the walk of a user by recognizing the walking intention of a user by using electromyography signals. CONSTITUTION: Apparatus for controlling waking assist robot comprises a sensor unit(110), a generating unit(120), and a control unit(130). The sensor unit comprises an electromyography sensor, and an analysis part(112). The electromyography sensor is attached to a human body for obtain signals. The analysis section analyzes signals generated from the sensor unit. The signal generating unit generates a walk intention signal by sensing the contraction change of muscle over specific value through electromyography signal. The control unit set and controls the walking mode of the waking assist robot through the generated signal.
Abstract translation: 目的：提供用于控制唤醒辅助机器人的装置和方法，以通过使用肌电图信号识别用户的行走意图来帮助用户行走。 构成：用于控制唤醒辅助机器人的装置包括传感器单元（110），生成单元（120）和控制单元（130）。 传感器单元包括肌电图传感器和分析部件（112）。 肌电图传感器连接到人体以获得信号。 分析部分分析从传感器单元产生的信号。 信号发生单元通过肌电信号感测特定值的肌肉的收缩变化来生成行走意图信号。 控制单元通过产生的信号设定并控制醒来辅助机器人的行走模式。
-
公开(公告)号：KR1020120054804A
公开(公告)日：2012-05-31
申请号：KR1020100116115
申请日：2010-11-22
Applicant: 한국전자통신연구원
CPC classification number: G06F17/30029
Abstract: PURPOSE: A data processing system for recalling memory and a method thereof are provided to collect data using a robot and supply data collected at timing that a user wants for recalling memory of the user. CONSTITUTION: A query information input unit(110) receives at least one query information. A data detecting unit(120) detects data related to a person who inputs the query information. A data display unit(130) displays data which are detected for recalling memory of the person. A data collecting unit(150) collects data related to the user whenever there is a request of a user. A data classifying unit(160) classifies the collected data in connection with at least one query information.
Abstract translation: 目的：提供一种用于调用存储器的数据处理系统及其方法，用于使用机器人收集数据，并提供在用户想要调用用户的存储器的定时收集的数据。 构成：查询信息输入单元（110）接收至少一个查询信息。 数据检测单元（120）检测与输入查询信息的人有关的数据。 数据显示单元（130）显示被检测用于召回人的存储器的数据。 数据收集单元（150）每当存在用户的请求时收集与用户相关的数据。 数据分类单元（160）将所收集的数据与至少一个查询信息相结合进行分类。
-
-
-
-
-
-
-
-
-
Search Results
191
records
(took 0.03 seconds)
