-
公开(公告)号：KR101833774B1
公开(公告)日：2018-03-02
申请号：KR1020160107962
申请日：2016-08-24
Applicant: 한국과학기술연구원
CPC classification number: G06T7/0014 , A01G7/00 , A01G22/00 , G06Q50/02 , G06T7/33 , G06T2207/30188
Abstract: 본발명은식물성장모니터링방법에관한것으로, 식물을촬영한식물영상을입력하는식물영상입력단계와, 입력되는상기식물영상에서유사한픽셀특징을갖는인접픽셀들을묶어슈퍼픽셀식물영상을생성하는슈퍼픽셀식물영상생성단계와, 상기슈퍼픽셀식물영상에서각각의슈퍼픽셀에대한슈퍼픽셀특징을추출하고, 기설정된식물영역분류기준을토대로추출된슈퍼픽셀특징을분류하여식물영역영상을생성하는식물영역분할단계와, 상기식물영역영상에서잎영역을추출하고, 추출한잎영역에서개별적인잎을레이블링하는잎영역분류단계및 상기식물영역영상에서상기잎영역을제외한잎자루영역을추출하고, 레이블링한잎영역을토대로추출한잎자루영역에서각각의잎자루를레이블링하는잎자루영역분류단계를포함한다.
-
公开(公告)号：KR1020170128194A
公开(公告)日：2017-11-22
申请号：KR1020170151322
申请日：2017-11-14
Applicant: 한국과학기술연구원
Abstract: 실시예들은발화문장을하나이상의형태소를포함하는형태소패턴들로구분하여하나이상의형태소패턴을생성하는형태소패턴생성부, 지식모델을기초로, 구분된각 형태소패턴에대응하는제스처타입을각 형태소패턴에적용하는제스처타입적용부및 적용된제스처타입에따라로봇을동작시키는동작명령을생성하는동작명령생성부를포함하는지식모델을이용한로봇의동작구현장치및 이를이용한모델링및 동작방법에관련된다.
Abstract translation: 对应于词素图案发生器的基础上各词素图案手势类型的实施例中，知识模型以通过分离发话句子成词素图案包括一个或多个形态产生一个或一个以上形态图案，分隔每个词素图案 姿势的类型的应用程序单元并应用于涉及建模和由该装置中执行的操作的方法，并用包括用于根据适用于手势的类型操作的机器人生成的操作命令生成操作指令的知识模型的机器人的这种操作。
-
公开(公告)号：KR1020170110423A
公开(公告)日：2017-10-11
申请号：KR1020160034789
申请日：2016-03-23
Applicant: 한국과학기술연구원
Abstract: 균형훈련시스템은, 사용자가탑승할수 있는이동보드와, 상기이동보드를지면상에서전방위로이동시키는구동체;를포함하는이동장치를포함하고, 상기이동보드가사용자의체중이동에의해수평상태를벗어나기울어지면상기구동체가굴러이동장치를이동보드의기울어진방향으로이동시키고, 상기이동보드가수평상태를회복하면이동장치의이동이중지되어, 사용자가자신의균형상태를인지하도록한다.
Abstract translation: 该平衡训练系统包括移动装置，该移动装置包括用户可登上的移动板和在地面上的所有方向上移动移动板的驱动主体，并且移动板移出水平状态 当移动板倾斜时，驱动单元沿着移动板的倾斜方向移动滚动装置，并且当移动板返回到水平状态时，移动装置停止移动，由此允许用户识别他或她自己的平衡状态。
-
公开(公告)号：KR1020160056107A
公开(公告)日：2016-05-19
申请号：KR1020140156075
申请日：2014-11-11
Applicant: 한국과학기술연구원
IPC: H04N7/18
CPC classification number: H04N7/18
Abstract: 본발명에따르면, 지정된사물이나영역을대상으로파손, 도난및 방치를감시하기위한감시시스템에있어서, 카메라로부터촬영된영상이미지를획득하는영상획득부(110); 상기영상이미지내에서관심영역을설정하는관심영역설정부(120); 설정된관심영역을윤곽선과질감으로표현하여외형모델을추출하는외형모델추출부(130); 설정된관심영역내에포함된객체의움직임여부를판단하는움직임판단부(140); 상기객체의움직임을시공간적으로분석하는움직임분석부(150); 상기외형모델추출부(130)를통해추출된기준외형모델과움직임이없는현재의외형모델간의유사도를분석하는모델유사도분석부(160); 및객체의움직임분석결과와외형모델유사도분석결과를통합분석하여이상유무를판단하며, 이상판단시알림동작하는이상유무판단부(170);를포함하는감시시스템을개시한다.
Abstract translation: 公开了一种用于监测指定对象或区域的损坏，被盗和疏忽的监视系统。 监视系统包括：用于获取由相机拍摄的视频图像的视频获取单元（110）; 兴趣区域设定单元，用于设置视频图像中的感兴趣区域; 外部模型提取单元，用于通过在轮廓和纹理中表达感兴趣的设定区域来提取外部模型; 运动确定单元，用于确定包括在所设置的感兴趣区域中的对象的运动; 运动分析单元，用于分析物体在时空上的运动; 模型相似度分析单元，用于分析由外部模型提取单元（130）提取的参考外部模型与当前静止外部模型之间的相似度; 以及用于通过对象的运动分析结果的综合分析和外部模型的相似度分析结果来确定异常的异常确定单元（170），并且当确定异常时执行通知操作。
-
公开(公告)号：KR1020140061823A
公开(公告)日：2014-05-22
申请号：KR1020120128921
申请日：2012-11-14
Applicant: 한국과학기술연구원
IPC: G06T7/20
Abstract: The present invention relates to an apparatus and a method for tracking an atypical object based on selected feature points and selectively-expected course estimation based on image, which comprises (a) a step of detecting an object; (b) a step of setting up an object area and a peripheral area by dividing an area based on the detected object into the object area and the peripheral area; (c) a step of extracting feature points from the object and a peripheral area, respectively; (d) a step of judging discernment of object feature points based on the feature points extracted from the object and the peripheral area; (e) a step of generating and updating a change map of the peripheral area based on the extracted and updated feature points of the object and the feature area; (f) a step of limiting and extracting a transferable area of the object based on the degrees of the changing feature points in the peripheral area; and (g) a step of tracking the object inside the limited and extracted transferable area of the object by adaptively selecting the feature points of the object which is determined to have discernment.
Abstract translation: 本发明涉及一种基于所选择的特征点和基于图像的有选择地预期的路线估计来跟踪非典型物体的装置和方法，其包括：（a）检测对象的步骤; （b）通过将基于检测对象的区域划分为对象区域和周边区域来建立对象区域和周边区域的步骤; （c）分别从对象和外围区域提取特征点的步骤; （d）基于从对象和周边区域提取的特征点来判断对象特征点的识别的步骤; （e）基于对象和特征区域的提取和更新的特征点来生成和更新外围区域的改变图的步骤; （f）基于周边区域中的改变特征点的程度来限制和提取对象的可转移区域的步骤; 以及（g）通过自适应地选择被确定为具有辨别力的对象的特征点来跟踪对象的受限和提取的可转移区域内的对象的步骤。
-
Patent Agency Ranking
公开(公告)号：KR101394270B1
公开(公告)日：2014-05-13
申请号：KR1020120128922
申请日：2012-11-14
Applicant: 한국과학기술연구원
IPC: G06T7/20 , G06T7/40 , G08B13/196
CPC classification number: G06T7/246 , G06K9/00771 , G08B13/196 , H04N7/18
Abstract: The present invention relates to an image detection method for behavior recognition and abnormal situation automatic detection based on an event comprises the following steps of: (a) detecting an object; (b) tracking the detected object; (c) analyzing the behavior of the tracked object; (d) recognizing whether the object behaves typically or atypically based on the behavior analysis; (e) extracting the order of situation/activity priorities from the typical and atypical behavior recognition result according to a predetermined rule, and setting countermeasures according to the order of priorities; and (f) activating an alarm for each countermeasure based on the set countermeasures according to the order of priorities, wherein the atypical behavior recognition is determined based on a relationship between consecutive behaviors.
Abstract translation: 本发明涉及一种基于事件的行为识别和异常情况自动检测的图像检测方法，包括以下步骤：（a）检测对象; （b）跟踪检测到的物体; （c）分析跟踪对象的行为; （d）基于行为分析来识别对象是否典型地或不典型地行为; （e）根据预定规则从典型和非典型行为识别结果中提取情况/活动优先顺序，并根据优先顺序设置对策; 和（f）基于根据优先级顺序的所设置的对策来激活每个对策的警报，其中基于连续行为之间的关系来确定非典型行为识别。
-
公开(公告)号：KR1020130136827A
公开(公告)日：2013-12-13
申请号：KR1020120060529
申请日：2012-06-05
Applicant: 한국과학기술연구원
IPC: A61B5/0476 , A61B5/11
Abstract: The present invention relates to an apparatus and a method for storing brain activity data using image and distance information, which are capable of automatically correct noises that are generated when a subject moves in a bio-signal detection system. To this end, the apparatus for storing brain activity data using image and distance information is configured to comprise: a brain activity measuring sensor for measuring brain activity; an image measuring unit for measuring image and distance information; a movement detecting unit for detecting movement of the subject using the image and distance information measured by the image measuring unit; and a brain activity data storing unit for storing brain activity data measured by the brain activity measuring sensor, wherein the brain activity data storing unit stores the brain activity data excluding a part of the brain activity data in a range where the movement of the subject is detected by the movement detecting unit. [Reference numerals] (AA) Subject;(BB) Measure image and distance information;(CC) Measure brain waves;(DD) sense a movement;(EE) Trigger generated;(FF) Store the trigger;(GG) Store the brain waves;(HH) Eliminate noises
Abstract translation: 本发明涉及一种使用图像和距离信息存储脑活动数据的装置和方法，其能够自动校正当对象在生物信号检测系统中移动时产生的噪声。 为此，用于使用图像和距离信息存储脑活动数据的装置被配置为包括：用于测量脑活动的脑活动测量传感器; 用于测量图像和距离信息的图像测量单元; 移动检测单元，用于使用图像检测被摄体的移动和由图像测量单元测量的距离信息; 以及脑活动数据存储单元，用于存储由脑活动测量传感器测量的脑活动数据，其中脑活动数据存储单元将除了一部分脑活动数据之外的大脑活动数据存储在受试者的运动范围内 由运动检测单元检测。 （AA）主题;（BB）测量图像和距离信息;（CC）测量脑波;（DD）感测运动;（EE）触发生成;（FF）存储触发;（GG） 脑波;（HH）消除噪音
-
公开(公告)号：KR1020130136826A
公开(公告)日：2013-12-13
申请号：KR1020120060528
申请日：2012-06-05
Applicant: 한국과학기술연구원
Abstract: The present invention relates to an apparatus and a method for correcting the position of an MEG sensor and the position of the head of a person under test by using image and distance information and, more in detail, to an apparatus for enhancing the accuracy of measured MEG data by correcting automatically the position of the sensor and the head of the person under test in the case that the MEG sensor attached to the head of the person under test moves because the person moves. For this, the apparatus for correcting the position of an MEG sensor and the position of the head of a person under test by using image and distance information comprises: the MEG sensor for measuring activities of the brain; an initial position storing part for prestoring the position of the head of the person under test relative the position of the MEG sensor at an initial stage of sensing in the MEG sensor; an image measuring part for measuring the image and distance information; a position correcting part for detecting a movement of the person under test by using the image and the distance information measured from the image measuring part and correcting the position of the MEG sensor based on the position of the head relative to the position of the MEG sensor; and an MEG data storing part for storing MEG data measured from the MEG sensor. [Reference numerals] (10) MEG sensor;(20) Image measuring part;(30) Initial position storing part;(40) Trigger generating part;(50) Position correcting part;(60) MEG data storing part;(70) Display part
Abstract translation: 本发明涉及一种用于通过使用图像和距离信息来校正MEG传感器的位置和被测试者的头部的位置的装置和方法，并且更详细地涉及一种用于增强测量的准确度的装置 MEG数据通过自动校正传感器的位置和被测试人员的头部，因为附着在被测试人员的头部的MEG传感器因人的移动而移动。 为此，用于通过使用图像和距离信息来校正MEG传感器的位置和被测试者的头部的位置的装置包括：用于测量脑的活动的MEG传感器; 初始位置存储部分，用于在MEG传感器的感测的初始阶段相对于MEG传感器的位置预先测试被测试者的头部的位置; 用于测量图像和距离信息的图像测量部分; 位置校正部分，用于通过使用图像和从图像测量部分测量的距离信息来检测被测试者的移动，并且基于头部相对于MEG传感器的位置的位置来校正MEG传感器的位置; ; 以及用于存储从MEG传感器测量的MEG数据的MEG数据存储部分。 （10）MEG传感器;（20）图像测量部;（30）初始位置存储部;（40）触发生成部;（50）位置校正部;（60）MEG数据存储部;（70） 显示部分
-
公开(公告)号：KR101260367B1
公开(公告)日：2013-05-07
申请号：KR1020110096764
申请日：2011-09-26
Applicant: 한국과학기술연구원
IPC: G06T7/00
Abstract: 본발명은 (1) 대상물체의영상데이터수신및 3D 윤곽을획득하는단계와 (2) 상기영상데이터및 상기 3D 윤곽을이용하여상기대상물체의기본파지타입및 기능파지타입을탐색하는단계와 (3) 상기설정된각각의파지타입에대하여파지큐(Grasping Cue)를추출하고, 이를통해 1 이상의후보파지영역(Grasping Region)을생성하는단계와 (4) 상기각각의후보파지영역별로파지점후보쌍들을추출하는단계및 (5) 상기각각의파지타입별로상기후보파지영역중에서하나의파지영역을선택하고, 상기선택된파지영역내의후보쌍들중에서하나의파지점쌍을선택하는단계를포함하는범주인식에의한파지점생성방법및 그방법에대한프로그램을기록한컴퓨터로읽을수 있는기록매체에관한것으로서본 발명에따르면로봇스스로동일한범주에속하나형상이다른다양한물체를인식하여파지할수 있게되는효과가있다.
-
公开(公告)号：KR1020130032990A
公开(公告)日：2013-04-03
申请号：KR1020110096764
申请日：2011-09-26
Applicant: 한국과학기술연구원
IPC: G06T7/00
CPC classification number: G06T1/0014 , B25J19/023 , G06T7/13
Abstract: PURPOSE: A method for generating a nip point by range recognition and a computer-readable recording medium including a program for the method are provided to recognize and grip objects in various shapes in the same range by generating a nip point by recognizing the objects in the same range. CONSTITUTION: A CPU(Central Processing Unit) explores an object gripping direction after obtaining a 3D outline from image data(S10,S20). The CPU extracts a gripping cue for each set gripping cue and generates a candidate gripping area for each gripping cue(S30). The CPU selects one of candidate pairs in an optimal gripping area after the points of nip point candidate pairs are extracted(S40,S50). The CPU generates a nip point manifold(S60). [Reference numerals] (AA) Start; (BB) End; (S10) Step of obtaining a 3D outline from image data; (S20) Step of searching a basic or function grasping type; (S30) Step of generating a candidate grasping area; (S40) Step of extracting grasping point candidate pairs; (S50) Step of selecting a grasping point pair; (S60) Step of generating a grasping point manifold;
Abstract translation: 目的：提供一种用于通过范围识别产生夹点的方法和包括用于该方法的程序的计算机可读记录介质，以通过生成夹点来识别和夹持在相同范围内的各种形状的对象， 相同范围 构成：CPU（中央处理单元）从图像数据中获取3D轮廓后，探索对象夹持方向（S10，S20）。 CPU为每个夹持提示提取夹持线索，并为每个夹持线索产生候选夹持区域（S30）。 在提取夹点候选对的点之后，CPU在最佳夹持区域中选择候选对中的一个（S40，S50）。 CPU产生压点歧管（S60）。 （附图标记）（AA）开始; （BB）结束; （S10）从图像数据获取3D轮廓的步骤; （S20）搜索基本或功能抓取类型的步骤; （S30）生成候选抓取区域的步骤; （S40）提取抓取候选对的步骤; （S50）选择对位点对的步骤; （S60）产生把持歧管的步骤;
-
-
-
-
-
-
-
-
-
Search Results
116
records
(took 0.03 seconds)
