专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

KR100814143B1 데이터 처리 장치 및 데이터 처리 장치 제어 프로그램 有权
标题翻译：数据处理设备和数据处理设备控制程序
公开(公告)号：KR100814143B1
公开(公告)日：2008-03-14
申请号：KR1020067005832
申请日：2004-07-22
申请人： 아사히 가세이 가부시키가이샤
发明人： 쇼자카이마코토 , 나기노고슈
IPC分类号： G10L15/06 , G10L15/14
CPC分类号： G10L21/06 , G06K9/00335 , G06K9/6261 , G10L15/063 , G10L15/07 , G10L15/144
摘要： 화자의 종류, 발화 어휘, 발화 양식, 발화 환경 등의 특정 조건에 의하여 다양화하는 특징 파라미터의 분포를 고려하여 불특정 화자용 음향 모델을 생성하는데 적합하고, 또한 특정 개인의 음성에 가장 적합한 불특정 화자용의 음향 모델을 제공하는데 적합한 데이터 처리장치 및 데이터 처리 장치 제어 프로그램을 제공한다. 데이터 처리장치(1)을 데이터 분류부(1a)와, 데이터 기억부(1b)와, 패턴 모델 생성부(1c)와, 데이터 제어부 (1d)와, 수학적 거리 산출부(1e)와, 패턴 모델 변화부(1f)와, 패턴 모델 표시부(1g)와, 영역 구분부(1h)와, 구분 내용 변경부(1i)와, 영역 선택부(1i)와, 영역 선택부(1j)와, 특정 패턴 모델 생성부(1k)를 포함한 구성으로 하였다.

2. 发明公开

KR1020010091780A 벡터 기술자 표현장치 및 이를 이용한 멀티미디어 데이터 검색장치 失效
标题翻译：用于表示矢量专家的装置和方法和装置以及使用其搜索多媒体数据的方法
公开(公告)号：KR1020010091780A
公开(公告)日：2001-10-23
申请号：KR1020000013816
申请日：2000-03-18
申请人： 주식회사 팬택앤큐리텔 , 한국전자통신연구원
发明人： 심동규 , 김해광 , 김문철 , 김진웅
IPC分类号： H04N19/94
CPC分类号： G06F17/30247 , G06F17/30017 , G06K9/6261
摘要： PURPOSE: An apparatus and a method for expressing a vector expert and an apparatus and a method for searching multimedia data using the same are provided to search multimedia data by expressing and storing vector experts of multimedia data hierarchically. CONSTITUTION: An orthogonal transform portion(100) performs an orthogonal transform process for each feature vector composing vector experts and expresses the feature vectors in an order of a low frequency feature to a high frequency feature. A quantization portion(101) quantizes the feature values of the orthogonal transform portion(100). A variable length coding portion(102) performs a variable length coding process for the quantized feature vector and the number of inputted feature values and stores the coded feature values in a feature value storage portion(103).
摘要翻译：目的：提供一种用于表达向量专家的装置和方法，以及用于搜索使用其的多媒体数据的装置和方法，以通过分级地表达和存储多媒体数据的矢量专家来搜索多媒体数据。构成：正交变换部（100）对各特征向量构成矢量专家进行正交变换处理，并以低频特征的顺序向高频特征表现特征向量。量化部分（101）量化正交变换部分（100）的特征值。可变长度编码部分（102）对量化的特征向量和输入的特征值的数量执行可变长度编码处理，并将编码的特征值存储在特征值存储部分（103）中。

3. 发明授权

KR101883473B1 이동로봇의 지도 작성 장치 및 방법 有权
公开(公告)号：KR101883473B1
公开(公告)日：2018-07-30
申请号：KR1020130051497
申请日：2013-05-07
申请人： 한화지상방산 주식회사
发明人： 김동신
IPC分类号： B25J9/22 , G05B19/42
CPC分类号： G05D1/0246 , G05D1/024 , G05D1/0242 , G05D1/0255 , G05D1/0274 , G05D2201/0207 , G06K9/00664 , G06K9/6261
摘要： 본발명은데이터용량을줄이고접근속도를빠르게할 수있는이동로봇의지도작성장치및 방법에관한것이다. 이동로봇의지도작성방법은이동로봇주변의환경인식을통해임의의공간을점유하는복수의특징데이터들을탐색하는단계, 탐색된제1 특징데이터에대하여쿼드트리분할을수행하고쿼드트리분할결과로써의제1 노드정보들을생성하는단계, 제1 특징데이터를기준으로한 제2 특징데이터의위치를탐색하는단계, 및제1 노드정보들을이용하여탐색된위치별로제2 특징데이터에대한제2 노드정보들을생성하는인접-이동알고리즘을수행하는단계를포함한다.

4. 发明公开

KR1020140132228A 이동로봇의 지도 작성 장치 및 방법 审中-实审
标题翻译：用于构造移动机器人地图的装置和方法
公开(公告)号：KR1020140132228A
公开(公告)日：2014-11-17
申请号：KR1020130051497
申请日：2013-05-07
申请人： 한화지상방산 주식회사
发明人： 김동신
IPC分类号： B25J9/22 , G05B19/42
CPC分类号： G05D1/0246 , G05D1/024 , G05D1/0242 , G05D1/0255 , G05D1/0274 , G05D2201/0207 , G06K9/00664 , G06K9/6261
摘要： The present invention relates to an apparatus and a method for constructing a map of a mobile robot, which can reduce the amount of data and can increase the speed of access. The method for constructing a map of a mobile robot comprises: a step of searching for multiple characteristic data which occupies a fixed space through surrounding environment recognition of a mobile robot; a step of performing quad tree on the searched first characteristic data and generating first node information as the qua tree division result; a step of searching for the positions of second characteristic data based on the first characteristic data; and a step of performing an adjacency-movement algorithm which generates second node information on the second specific data by the searched positions.
摘要翻译：本发明涉及一种用于构建移动机器人的地图的装置和方法，其可以减少数据量并且可以提高访问速度。用于构建移动机器人的地图的方法包括：通过周边的移动机器人的环境识别来搜索占用固定空间的多个特征数据的步骤; 对所搜索到的第一特征数据执行四叉树并产生第一节点信息作为树分割结果的步骤; 基于第一特征数据搜索第二特征数据的位置的步骤; 以及执行邻接移动算法的步骤，其通过搜索位置生成关于第二特定数据的第二节点信息。

5. 发明公开

KR1020140096910A 객체 계수 장치 및 방법 有权
标题翻译：用于计算对象数量的装置和方法
公开(公告)号：KR1020140096910A
公开(公告)日：2014-08-06
申请号：KR1020130010090
申请日：2013-01-29
申请人： 한화테크윈 주식회사
发明人： 김혁래
IPC分类号： G06T7/40 , G06T7/00
CPC分类号： G06T7/254 , G06K9/6261
摘要： The present invention relates to a device and a method for counting objects which can accurately count objects of each subspace by dividing the entire space into a plurality of subspaces and applying different counting algorithms to the divided subspaces. The method for counting objects comprises: a space division step of dividing any entire space into one or more indoor spaces and one or more outdoor spaces; an entire space counting step of generating object counting information by counting entering/leaving objects using a camera or a sensor arranged around an entrance of the entire space; an indoor space counting step of generating object counting information by counting entering/leaving objects using a camera or a sensor arranged around an entrance of the indoor space; and an outdoor space counting step of generating object counting information by counting objects of the outdoor space using a sensor or a camera arranged in the outdoor space.
摘要翻译：本发明涉及一种用于计数物体的装置和方法，其可以通过将整个空间划分成多个子空间并将不同的计数算法应用于分割的子空间来精确地计数每个子空间的对象。用于计数物体的方法包括：空间分割步骤，将任何整个空间分成一个或多个室内空间和一个或多个室外空间; 整个空间计数步骤，通过使用布置在整个空间的入口周围的照相机或传感器对进入/离开对象进行计数来生成对象计数信息; 室内空间计数步骤，通过使用布置在室内空间的入口周围的照相机或传感器对进入/离开物体进行计数来生成物体计数信息; 以及室外空间计数步骤，通过使用布置在室外空间中的传感器或照相机对室外空间进行计数来生成物体计数信息。

6. 发明公开

KR1020130138457A 증강현실의 호모그래피 정확도 향상을 위한 ＣＳＰ 기반의 ＲＡＮＳＡＣ 샘플링 방법 有权
标题翻译：基于约束现实中约束满足问题的随机抽样方法的采样方法
公开(公告)号：KR1020130138457A
公开(公告)日：2013-12-19
申请号：KR1020120062051
申请日：2012-06-11
申请人： 인하대학교 산학협력단
发明人： 조근식 , 장철희
IPC分类号： G06T7/00 , G06T3/00
CPC分类号： G06K9/00416 , G06K9/46 , G06K9/6261 , G06T19/006 , G06T2207/20021
摘要： Disclosed is a CSP based random sample consensus (RANSAC) sampling method for improving homography accuracy in an augmented reality. A sampling method for estimating homography displaying a conversion relationship between a plurality of images using an RANSAC algorithm comprises the preprocessing step in which an object image of the images is divided into a plurality of lattice regions, and a characteristic point extracted from the object image is classified into the lattice regions; and the selecting step in which all of the disclosed constraints for the classified characteristic point are applied to select the characteristic point for estimating the homography. [Reference numerals] (AA) (a):Initially selected characteristic point , (b): Violation of distance limitation, (c): Violation of linear limitation, (d)(e)(f)(g): Selected characteristic point
摘要翻译：公开了一种用于提高增强现实中的单倍性准确性的基于CSP的随机样本共有（RANSAC）抽样方法。用于估计使用RANSAC算法显示多个图像之间的转换关系的单倍性的采样方法包括：预处理步骤，其中图像的对象图像被划分为多个格子区域，并且从对象图像提取的特征点是分为晶格区域; 以及选择步骤，其中应用所分配的特征点的所有公开的约束以选择用于估计单应性的特征点。（AA）（a）：初始选择的特征点，（b）：违反距离限制，（c）：违反线性限制，（d）（e）（f）（g）

7. 发明授权

KR101581112B1 계층적 패턴 구조에 기반한 기술자 생성 방법 및 이를 이용한 객체 인식 방법과 장치 有权
标题翻译：用于生成基于分层结构的基于图案的描述符的方法和使用描述符及其设备识别对象的方法
公开(公告)号：KR101581112B1
公开(公告)日：2015-12-30
申请号：KR1020140035235
申请日：2014-03-26
申请人： 포항공과대학교 산학협력단
发明人： 김인수 , 김대진
IPC分类号： G06T7/00
CPC分类号： G06K9/6261 , G06K9/469 , G06K9/6282
摘要： 계층적패턴구조기반의기술자서술방법및 이를이용한이미지내 객체의포즈추정방법과객체인식장치가개시된다. 계층적패턴구조기반의기술자서술방법은, 입력된분석대상이미지의특징점에대한패치영역에기반하여부모노드를정의하고, 부모노드를소정의깊이까지분할한자식노드를정의하여계층적패턴구조를생성하는단계와, 부모노드와자식노드의위치좌표및 픽셀대표값에기반하여패치영역의주방향벡터를산출하는단계와, 주방향벡터에기반하여패치영역의회전각을산출하고계층적패턴구조를회전각만큼회전하는단계를포함하여구성될수 있다.

8. 发明授权

KR101453713B1 객체 인식 방법 및 그 장치 有权
标题翻译：对象识别方法和装置
公开(公告)号：KR101453713B1
公开(公告)日：2014-10-22
申请号：KR1020140012145
申请日：2014-02-03
申请人： 연세대학교 산학협력단
发明人： 김신덕 , 정현섭
IPC分类号： G06T7/00 , G06K9/46
CPC分类号： G06K9/4609 , G06K9/6261 , G06T7/246
摘要： Disclosed are an object recognition method and an apparatus thereof. An object recognition method includes a step of detecting corner points in an input image; a step of calculating a corner point weighted value with regard to the detected corner point based on the edge distance of the input image; a step of calculating corner point rotation sensitivity by using a difference between the input image and a rotation image of rotating the input image; a step of extracting a feature point from at least one among the detected corner points by using the corner point weighted value and the corner rotation sensitivity; and a step of recognizing an object by using the extracted feature point.
摘要翻译：公开了一种物体识别方法及其装置。对象识别方法包括检测输入图像中的角点的步骤; 基于输入图像的边缘距离计算关于检测到的角点的角点加权值的步骤; 通过使用输入图像与旋转输入图像的旋转图像之间的差来计算角点旋转灵敏度的步骤; 通过使用角点加权值和拐角旋转灵敏度从检测到的角点中的至少一个提取特征点的步骤; 以及通过使用所提取的特征点来识别对象的步骤。

9. 发明授权

KR101384627B1 영상 내 객체 영역 자동분할 방법 有权
标题翻译：在视频中自动分割对象区域的方法
公开(公告)号：KR101384627B1
公开(公告)日：2014-04-11
申请号：KR1020120119574
申请日：2012-10-26
申请人： 전남대학교산학협력단
发明人： 나인섭 , 김수형 , 오강한
IPC分类号： G06T7/00
CPC分类号： G06K9/6261 , G06K9/40 , G06K9/4676 , G06K9/6223 , G06K9/6247
摘要： The present invention relates to an automatic segmentation method of an object area in an image and, more specifically, to an automatic segmentation method of an object area in an image which quickly segments an object containing a flower from an image by a probability distribution estimation algorithm. According to an embodiment of the present invention, a time required for segmentation can be minimized as a mobile terminal automatically segments a target object and a background from an input image when the input image of flower or plant is obtained. [Reference numerals] (S1000) Step of converting an image format of input images; (S2000) Step of estimating a predetermined area estimated in which the candidate object is located in the input images as a candidate area; (S3000) Step of extracting each feature information to the candidate object and a background in the candidate area; (S4000) Step of dividing the images in the input image by using the feature information; (S5000) Step of removing the noise of the divided object n the input images
摘要翻译：本发明涉及图像中的对象区域的自动分割方法，更具体地，涉及图像中的对象区域的自动分割方法，其通过概率分布估计算法从图像中快速地分割包含花朵的对象。根据本发明的实施例，当获取花或植物的输入图像时，移动终端可以最小化分割所需的时间，因为移动终端自动地从输入图像中分割目标对象和背景。（参考数字）（S1000）转换输入图像的图像格式的步骤; （S2000）将所述候选对象所位于的预定区域估计为所述输入图像作为候选区域的步骤; （S3000）向所述候选对象提取每个特征信息和所述候选区域中的背景的步骤; （S4000）使用所述特征信息来分割输入图像中的图像的步骤; （S5000）去除分割对象在输入图像上的噪声的步骤

10. 发明授权

KR100767489B1 벡터 기술자 표현장치 및 이를 이용한 멀티미디어 데이터 검색장치 失效
标题翻译：用于表示向量描述符的装置，以及用于使用其来检索多媒体数据的装置
公开(公告)号：KR100767489B1
公开(公告)日：2007-10-16
申请号：KR1020000013816
申请日：2000-03-18
申请人： 주식회사 팬택앤큐리텔 , 한국전자통신연구원
发明人： 심동규 , 김해광 , 김문철 , 김진웅
IPC分类号： H04N19/94
CPC分类号： G06F17/30247 , G06F17/30017 , G06K9/6261
摘要： The present invention relates to an apparatus and a method for vector descriptor representation and multimedia data retrieval, which can quantize a plurality of feature values described by a vector descriptor respectively, represent the quantized feature values in the form of bit or orthogonally transform the quantized bector feature values, and rearrange the feature values represented in the form of bit from the highest bit to the lowest bit or rearrange the transformed coefficient from low frequency to high frequency to represent the vector descriptor hierarchically. Moreover, when retrieving multimedia data, the present invention can code in variable length and store the rearranged feature values and the number of feature values which are input, inversely code only the feature values corresponding to the number of the feature values of the stored feature values, inversely arrange the inversely coded feature values to be restored to original feature values, inversely quantize the restored feature values, and compare the feature values restored by the inverse quantization with the feature values stored in a multimedia database to retrieve multimedia data.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式