-
公开(公告)号：KR101428401B1
公开(公告)日：2014-08-14
申请号：KR1020130082120
申请日：2013-07-12
Applicant: 한양대학교 산학협력단
IPC: G06F3/01
Abstract: Disclose are an apparatus and a method to convert image information into tactile signals and provide the tactile signals. The apparatus includes: an image acquisition unit which acquires image information for objects around a user using at least one sensor; an image processing unit which generates tactile sensation generation information by processing the image information for the objects; and a tactile sensation providing unit which generates tactile signals based on the tactile sensation generation information, and provides a user with the tactile signals. Therefore, the apparatus and the method can identify information on the existence of a neighboring obstacle as well as the information on the location, curvature, and shape of an object in advance, thereby effectively providing a user with moving information, and being applicable to a virtual technology such as an interactive simulator.
Abstract translation: Disclose是将图像信息转换为触觉信号并提供触觉信号的装置和方法。 该装置包括：图像获取单元，其使用至少一个传感器获取用户周围的对象的图像信息; 图像处理单元，其通过处理对象的图像信息来生成触感发生信息; 以及触觉感觉提供单元，其基于触觉感觉产生信息产生触觉信号，并向用户提供触觉信号。 因此，装置和方法可以预先识别关于邻近障碍物的存在的信息以及关于对象的位置，曲率和形状的信息，从而有效地向用户提供移动信息，并且适用于 虚拟技术如交互式模拟器。
-
公开(公告)号：KR1020140094761A
公开(公告)日：2014-07-31
申请号：KR1020130007102
申请日：2013-01-22
Applicant: 한양대학교 산학협력단
Abstract: The objective of the present invention is to make users properly select food depending on the own amount of the food and to set a reasonable price according to the amount of the food. Thus, the present invention can protect domestic natural environment and can save resources by effectively reducing the amount of food wastes approaching 8,000 billion won per year. A restaurant needs fast and accurate calculation due to the constraints of time and space since there are a lot of people coming in all at the same time. To solve the problem, adopting a method using a computer vision is essential. The system divides the image of a food tray obtained by a distance camera for providing distance information and a color camera into each food section by analyzing the image of the food tray, and determines the kinds of the food in each divided section by matching the food with a today′s set menu. Then, the system measures the volume of the food tray using the distance camera to calculate the volume of the food. Accordingly, the system obtains weight information from the volume information on the food and calculates and displays the calorie and price of the food.
Abstract translation: 本发明的目的是使用户根据食物的数量适当地选择食物，并根据食物量设定合理的价格。 因此，本发明可以保护国内自然环境，节约资源，有效减少每年接近8000亿韩元的食品废物。 由于时间和空间的限制，餐厅需要快速准确的计算，因为有很多人同时进入。 为了解决这个问题，采用计算机视觉的方法至关重要。 该系统通过分析食物托盘的图像将通过距离摄像机获得的食物托盘的图像分配给每个食物部分，并通过匹配食物来确定每个分割部分中的食物的种类 用今天的菜单。 然后，系统使用距离摄像机测量食物托盘的体积以计算食物的体积。 因此，系统从食物的体积信息中获取体重信息，并计算并显示食物的卡路里和价格。
-
公开(公告)号：KR1020140093189A
公开(公告)日：2014-07-25
申请号：KR1020140005198
申请日：2014-01-15
Applicant: 한국전자통신연구원 , 한양대학교 산학협력단
CPC classification number: G06K9/00275 , G06K9/6215 , G06K2009/485
Abstract: The present specification provides a method and an apparatus for face tracking robust to face rotation. The face tracking method of the present specification comprises the steps of: receiving an image including a user′s face; predicting an area having the high possibility for the face and the degree of rotation of the face within the image; detecting a facial area where the face exists from the image based on the predicted value; calculating the similarity of the facial area in a horizontal direction to obtain the degree of rotation of the face; and compensating the predicted value, based on the position of the face and the degree of rotation thereof, to extract the compensated facial area.
Abstract translation: 本说明书提供了一种用于面部跟踪的方法和装置，其适用于面向旋转。 本说明书的面部追踪方法包括以下步骤：接收包括用户脸部的图像; 预测图像中的面部的脸部和脸部旋转的可能性高的区域; 基于所述预测值从所述图像检测所述面部存在的面部区域; 计算面部区域在水平方向上的相似度以获得脸部的旋转度; 并且基于面部的位置和其旋转程度来补偿预测值，以提取补偿面部区域。
-
公开(公告)号：KR101283262B1
公开(公告)日：2013-07-11
申请号：KR1020110108378
申请日：2011-10-21
Applicant: 엘지이노텍 주식회사 , 한양대학교 산학협력단
CPC classification number: G06T7/0079 , G06T7/10 , G06T7/70 , G06T2207/10028
Abstract: 본 발명은 영상 처리 장치 및 방법에 관한 것으로서, 영상의 깊이 정보를 획득하고, 영상에서 목표물이 존재하는 영역에 대한 제1 관심 영역을 분리하고, 상기 제1 관심 영역으로부터 목표물에 대한 후보 영역을 검출하고, 상기 검출된 후보 영역이 목표물에 대응되는 지를 판단하고, 상기 후보 영역이 목표물에 대응되는 경우 상기 후보 영역을 이용하여 목표 영역을 검출하고, 상기 목표 영역을 이용하여 목표물의 자세를 추정하며, 상기 목표물을 모델링함으로써 깊이 정보만을 이용하여 목표물을 간단하고 정확하게 모델링할 수 있다.
Abstract translation: 公开了一种图像处理方法和图像处理装置。 图像处理方法包括：将图像划分为多个区域; 将所述分割区域的一部分设置为第一感兴趣区域; 从所述第一感兴趣区域检测目标的候选区域; 确定检测到的候选区域是否对应于目标; 如果所述候选区域对应于所述目标，则通过使用所述候选区域来检测目标区域; 通过使用检测到的目标区域估计目标的姿势; 并对目标进行建模。
-
公开(公告)号：KR101040904B1
公开(公告)日：2011-06-16
申请号：KR1020090088184
申请日：2009-09-17
Applicant: 한양대학교 산학협력단
Abstract: 레이저를 이용한 통행량 추정 시스템 및 방법을 개시한다. 통행량 추정 시스템은 통행량을 측정하고자 하는 감시영역에 조사된 레이저 빛을 검출하는 카메라 장치로부터 입력받은 영상을 이용하여 거리 영상을 생성하는 거리 영상 생성부, 거리 영상에 기초하여 이동체 각각의 최상단 영역을 추적하는 최상단 영역 추적부 및 추적된 최상단 영역에 기초하여 감시영역의 통행량을 추정하는 통행량 추정부를 포함한다.
레이저, 통행량, 이동량, 평균 이동(mean shift)-
Patent Agency Ranking
公开(公告)号：KR1020110021132A
公开(公告)日：2011-03-04
申请号：KR1020090078752
申请日：2009-08-25
Applicant: 한양대학교 산학협력단
Inventor： 김회율
Abstract: PURPOSE: An ultrasonic cleaner is provided, which can effectively eliminate waste product, contaminant, cosmetic, and the like piled on the skin. CONSTITUTION: An ultrasonic cleaner comprises: a cleaning bath(110) formed into a shape that cleaning water can be put; an injector(120) which sprays cleaning water in continuous water stream to an object located in the upper part of the cleaning bath; and an ultrasonic instrument(130) transferring ultrasonic wave to the cleaning water. The injector is equipped with: a first injector spraying fixed amount of cleaning water; and a second injector which horizontally sprays cleaning water to the center of the cleaning bath.
Abstract translation: 目的：提供超声波清洗机，可以有效消除堆放在皮肤上的废物，污染物，化妆品等。 构成：超声波清洗器包括：形成为可以放置清洁水的形状的清洗槽（110） 喷射器（120），其将连续水流中的清洁水喷射到位于所述清洗槽上部的物体; 以及将超声波传送到清洗水的超声波仪器（130）。 注射器配备有：第一喷射器喷洒固定量的清洁水; 以及第二喷射器，其将清洁水水平地喷射到清洁浴的中心。
-
公开(公告)号：KR1020100119420A
公开(公告)日：2010-11-09
申请号：KR1020090038526
申请日：2009-04-30
Applicant: 한국전자통신연구원 , 한양대학교 산학협력단
IPC: G06T7/00
CPC classification number: G06K9/00604 , G06K9/00234 , G06T7/11 , G06T7/60 , G06T7/70
Abstract: PURPOSE: An apparatus and a method for detecting eye location using an eye descriptor are provided to accurately detect eye location by detecting the geometric eye location through the similarity of an eye. CONSTITUTION: A face image detector(110) detects a face image from an input image, and a similarity calculation unit(120) compares the detected face image with a studied pupil descriptor to calculate pupil similarity. The similarity calculation unit calculates the eye position in the detected face image through the calculated pupil similarity, and an eye position calculator(130) calculates the pupil location of a user based on the calculated face image.
Abstract translation: 目的：提供一种使用眼睛描述符检测眼睛位置的装置和方法，以通过眼睛的相似度检测几何眼睛位置来准确地检测眼睛位置。 构成：面部图像检测器（110）从输入图像检测面部图像，并且相似度计算单元（120）将检测到的面部图像与研究的瞳孔描述符进行比较，以计算瞳孔相似度。 相似度计算单元通过计算的瞳孔相似度计算检测到的人脸图像中的眼睛位置，并且眼睛位置计算器（130）基于所计算的面部图像来计算用户的瞳孔位置。
-
公开(公告)号：KR1020090131995A
公开(公告)日：2009-12-30
申请号：KR1020080058033
申请日：2008-06-19
Applicant: 한양대학교 산학협력단
CPC classification number: G08B13/19606 , G01J1/4257 , G08B13/1963 , H04N7/188
Abstract: PURPOSE: A traffic estimating system using laser and a method thereof are provided to obtain an image signal only, which corresponds to a specific wavelength of a laser beam, thereby easily obtaining an interested image. CONSTITUTION: A laser device(10) irradiates a laser beam on a monitoring area. The monitoring area is an area for traffic measurement. A camera device(20) detects the irradiated laser beam. A traffic estimating unit(30) receives an image from the camera device. The traffic estimating unit generates accumulated images. Based on location change of the laser beam within the accumulated images, the traffic estimating unit estimates traffic of a mobile body.
Abstract translation: 目的：提供使用激光的交通量估计系统及其方法，以获得仅对应于激光束的特定波长的图像信号，从而容易地获得感兴趣的图像。 构成：激光装置（10）将激光束照射在监视区域上。 监控区域是交通量测量的区域。 相机装置（20）检测照射的激光束。 交通量估计单元（30）从相机装置接收图像。 流量估计单元生成累积图像。 基于累积图像内的激光束的位置变化，流量估计单元估计移动体的流量。
-
公开(公告)号：KR100907096B1
公开(公告)日：2009-07-09
申请号：KR1020070115555
申请日：2007-11-13
Applicant: 한양대학교 산학협력단
Abstract: 통행량 추정 방법 및 장치가 개시된다. 통행량 추정 방법은 하나 이상의 가상 문(virtual gate)에 대한 설정 정보를 저장하는 단계; 비디오 센서로부터 입력되는 비디오 데이터의 각 프레임을 이용하여 이동체에 대한 전경 영역(foreground region)을 분리하는 단계; 및 상기 가상 문에 겹쳐지는 전경 영역의 픽셀 수를 카운트하여 상응하는 통행량 값을 산출하는 단계를 포함한다. 본 발명에 의해, 이미 설치된 영상 생성 장치를 범용적으로 이용할 수 있고, 관찰 시점 및/또는 사람간의 겹쳐짐에 의해 측정 결과가 왜곡되지 않는 장점이 있다.
통행량, 영상 해석, 비디오 데이터, 영상 감시-
公开(公告)号：KR1020080099671A
公开(公告)日：2008-11-13
申请号：KR1020070045524
申请日：2007-05-10
Applicant: 한양대학교 산학협력단
Abstract: A method of extracting epiphysis region using pattern recognition is provided to reduce error by referring only three largest points to be measured in the entire finger with a mean filter. A method of extracting epiphysis region using pattern recognition is composed of steps: extracting the finger image from the input image(101); generating a candidate area of the epiphysis plate by using the vertical projection differential value of the extracted finger image(102); comparing the average of the differential value of the certain region in the candidate area and extracting the location of the epiphysis plate(103); calculating the average of the differential value of the certain region within the candidate area; extracting the location of the epiphysis plate having the highest mean value.
Abstract translation: 提供使用模式识别提取骨ysis区域的方法，通过使用平均滤波器仅在整个手指中仅引用要测量的三个最大点来减少误差。 使用模式识别提取骨ysis区域的方法由步骤：从输入图像（101）提取手指图像; 通过使用所提取的手指图像（102）的垂直投影差分值来产生ysis板的候选区域; 比较候选区域中特定区域的差分值的平均值，并提取骨盆板（103）的位置; 计算候选区域内特定区域的差分值的平均值; 提取具有最高平均值的骨盆板的位置。
-
-
-
-
-
-
-
-
-
Search Results
100
records
(took 0.031 seconds)
