-
公开(公告)号：KR101601660B1
公开(公告)日：2016-03-10
申请号：KR1020140154424
申请日：2014-11-07
Applicant: 재단법인대구경북과학기술원
IPC: G06T7/00
Abstract: 본발명은깊이영상을이용한손 영역분류방법및 그장치에관한것이다. 본발명에따르면, 카메라의깊이영상으로부터손 영역을검출하는단계와, 상기손 영역에포함된각 픽셀의특징값을연산하되, 상기깊이영상내에서상기픽셀로부터설정오프셋만큼떨어진두 지점을기준으로임의크기로생성된두 오프셋패치에대한평균깊이값의차이를이용하여상기각 픽셀의특징값을연산하는단계와, 입력되는특징값에대응하는분류라벨을출력하도록미리학습된랜덤결정트리앙상블(Random Decision Forest) 내에상기각 픽셀의특징값을개별입력하여상기손 영역을다수의파트로분류하는단계와, 상기분류된다수의파트별로중심점을설정하는단계, 및상기설정된중심점들을이용하여상기손의스켈레톤(skeleton)을추출하는단계를포함하는깊이영상을이용한손 영역분류방법을제공한다. 상기깊이영상을이용한손 영역분류방법및 그장치에따르면, 손의깊이영상만으로손 영역을다수의파트로효과적으로분류할수 있으며이를통해손의스켈레톤정보를정확하게추출하고손 동작의인식률을향상시킬수 있는이점이있다.
Abstract translation: 本发明涉及使用深度图像的手部分类方法及其装置。 根据本发明，使用深度图像的手部分类方法可以包括：从相机的深度图像检测手部分; 通过使用生成为具有一定尺寸的两个偏移补丁的平均深度值的差异，基于由两个点间隔开的两个点来计算手部分中包括的每个像素的特征值，具体地计算每个像素的特征值 作为参考，与深度图像内的像素的偏移设置; 通过将每个像素的特征值输入随机决策林中，将手部分分为多个部分，其被训练以预先输出与输入的特征值相对应的分类标签; 为多个分类部分设置中心点; 并使用设定的中心点提取手的骨架。 根据使用深度图像的手部分类方法及其装置，通过仅使用深度图像可以有效地将手部分分为多个部分，从而允许精确提取手的骨架信息和提高手部运动的识别率。
-
公开(公告)号：KR1020150042674A
公开(公告)日：2015-04-21
申请号：KR1020130123325
申请日：2013-10-16
Applicant: 재단법인대구경북과학기술원
Abstract: 본발명은외부환경변화에따른모달리티의결합또는선택을통하여사용자인식성능을향상시키기위한방법을제공한다. 본발명은멀티모달사용자인식방법에관한것으로, 얼굴모델템플릿(face model templates)을이용하여입력영상의얼굴특징벡터에대한얼굴유사도를계산하는단계; 음성모델템플릿(speech model templates)을이용하여입력오디오의음성특징벡터에대한음성유사도를계산하는단계; 상기입력영상과연관된조명의크기를이용하여얻어진제1 가중치를상기얼굴유사도에적용하여제1 값을생성하는단계; 상기입력오디오와연관된잡음의크기를이용하여얻어진제2 가중치를상기음성유사도에적용하여제2 값을생성하는단계; 및상기제1 값및 상기제2 값을결합하여얻어진최종스코어를이용하여, 사용자를인식하는단계를포함하는멀티모달사용자인식방법을제공한다.
Abstract translation: 本发明提供一种根据外部环境的变化通过组合或选择模式来增强用户识别性能的方法。 多模式用户识别方法技术领域本发明涉及一种多模式用户识别方法，其提供多模式用户识别方法，其包括：使用面部模型模板计算输入图像的面部特征向量的面部相似度的步骤; 使用语音模型模板计算输入音频的声乐特征向量的声音相似度的步骤; 通过将与使用与输入图像相关联的照明的大小获得的第一权重应用于面部相似度来创建第一值; 通过将声音相似度应用于使用与输入音频相关联的噪声大小获得的第二权重来产生第二值的步骤; 以及使用从组合第一和第二值获得的最终得分来识别用户的步骤。
-
公开(公告)号：KR101436695B1
公开(公告)日：2014-09-01
申请号：KR1020120128410
申请日：2012-11-13
Applicant: 재단법인대구경북과학기술원
Abstract: 깊이 영상을 이용한 손 검출 장치 및 방법이 개시된다. 깊이 영상을 이용한 손 검출 장치는 카메라에 의해 손을 촬영한 영상을 입력 받고, 상기 카메라와 상기 손 간의 거리에 기초하여, 상기 입력된 영상으로부터 상기 손에 대한 손 영역을 검출하는 검출부와, 상기 손 영역으로부터 2차원의 제1 손 모양 및 3차원의 제2 손 모양을 추정하고, 추정된 상기 제1 손 모양 및 상기 제2 손 모양을 이용하여, 상기 손에 대한 최종 모양을 추정하는 프로세서를 포함한다.
-
公开(公告)号：KR1020140060191A
公开(公告)日：2014-05-19
申请号：KR1020120126989
申请日：2012-11-09
Applicant: 재단법인대구경북과학기술원
CPC classification number: G06F3/017 , G06F3/0304 , G06F3/0346 , G06F3/042 , H05B37/02
Abstract: The present invention relates to a touch-based virtual switch control method and a device for the same. According to the present invention, the touch-based virtual switch control method using a three-dimensional camera which is installed in a target space to acquire the depth data of a subject includes: a step of detecting part of the body of a user from an image taken by the three-dimensional camera; a step of determining if the part of the body touches a virtual switch area predefined in the target space; a step of, if it is determined that the part of the body touches the virtual switch area, recognizing the gesture taken by the part of the body after the touch; a step of extracting a control command corresponding to the recognized gesture from a gesture database in which control commands by gesture are stored; and a step of controlling the operation of at least one electronic device according to the extracted control command. According to the touch-based virtual switch control method and the method thereof, part of the body of a user is traced, and when the part of the body of the user touches the predefined area and takes a certain gesture, a designated operation corresponding to the gesture is applied to an electric switch. By doing so, separate fixed structures such as the existing wires and switches are not necessary. It is also possible to define and use switch actions at a desired position by flexibly changing the virtual switch area.
Abstract translation: 本发明涉及一种基于触摸的虚拟开关控制方法及其装置。 根据本发明，使用安装在目标空间中以获取对象的深度数据的三维相机的基于触摸的虚拟切换控制方法包括：从一个或多个对象的身体检测用户的身体的一部分 由三维摄像机拍摄的图像; 确定身体的一部分是否与目标空间中预定义的虚拟交换区域相接触的步骤; 如果确定身体的一部分接触虚拟开关区域，则识别在触摸之后身体部分拍摄的手势的步骤; 从存储有通过手势的控制命令的手势数据库中提取与所识别的手势相对应的控制命令的步骤; 以及根据所提取的控制命令来控制至少一个电子设备的操作的步骤。 根据基于触摸的虚拟切换控制方法及其方法，跟踪用户身体的一部分，并且当用户的身体的一部分触摸预定区域并采取某种手势时，指定的操作对应于 手势被施加到电开关。 通过这样做，不需要单独的固定结构，例如现有的电线和开关。 还可以通过灵活地改变虚拟交换机区域来在所需位置定义和使用交换机动作。
-
公开(公告)号：KR101382892B1
公开(公告)日：2014-04-08
申请号：KR1020120111255
申请日：2012-10-08
Applicant: 재단법인대구경북과학기술원
IPC: G06T7/00
CPC classification number: G06K9/00228 , G06T3/4053 , G06T5/20 , G06T2207/20028
Abstract: The present invention relates to a face recognition method in a low resolution image and a face recognition device in a low resolution image in which an internal image patch is replaced with a high resolution image patch, which is retained through learning in advance, for a low resolution face image detected from a surveillance camera. As an embodiment, the face recognition method in a low resolution image includes the steps of maintaining a database in which a first image patch is recorded in correspondence to a second image patch having higher resolution than the first image patch; identifying a recognition target region from image information input from the camera; among image patches of the recognition target region, defining an image patch not satisfying a reference resolution as the first image patch; in the database, searching the database for the second image patch recorded in correspondence to the defined first image patch; and recovering the recognition target region by replacing found second image patch with the defined first image patch. [Reference numerals] (110) Database control unit; (115) Database; (120) Region identification unit; (130) Image processing unit; (140) Image recovery unit; (150) Compensation unit; (160) Face recognition unit
Abstract translation: 本发明涉及一种低分辨率图像中的人脸识别方法和低分辨率图像中的面部识别装置，其中内部图像贴片被高分辨率图像贴片替代，该高分辨率图像贴片通过预先学习而保持低电平 从监控摄像机检测到的分辨率脸部图像。 作为实施例，低分辨率图像中的面部识别方法包括以下步骤：对应于具有比第一图像补丁更高分辨率的第二图像补片，维持其中记录第一图像补片的数据库; 从从相机输入的图像信息中识别识别对象区域; 在所述识别目标区域的图像块中，将不满足参考分辨率的图像块定义为所述第一图像块; 在所述数据库中，搜索所述数据库中对应于所述定义的第一图像补丁记录的所述第二图像补丁; 以及通过用所定义的第一图像补片替换所发现的第二图像补片来恢复识别目标区域。 （附图标记）（110）数据库控制单元; （115）数据库; （120）区域识别单位; （130）图像处理单元; （140）图像恢复单元; （150）赔偿单位; （160）脸部识别单元
-
Patent Agency Ranking
公开(公告)号：KR101296365B1
公开(公告)日：2013-08-14
申请号：KR1020110120263
申请日：2011-11-17
Applicant: 재단법인대구경북과학기술원
IPC: G06F3/03
Abstract: 본 발명은 카메라를 이용한 홀로그램 터치 인식방법에 관한 것으로, (a) 복수의 스테레오 카메라 및 적어도 하나의 깊이 카메라로 촬영된 뷰(view) 영상을 일치시키기 위해 영상 보정하는 단계; (b) 상기 복수의 스테레오 카메라 및 적어도 하나의 깊이 카메라로 홀로그램 발생부에서 생성한 홀로그램 영상을 포함하는 3D 영상을 실시간으로 촬영하는 단계; (c) 터치 인식부에서 상기 스테레오 카메라에서 촬영된 3D 영상과 상기 깊이 카메라에서 촬영된 3D 영상을 비교하여 상기 홀로그램 영상을 인식하고, 상기 홀로그램 영상의 공간상 위치정보를 획득하는 단계; 및 (d) 터치 인식부에서 사용자가 상기 홀로그램의 영상에서의 공간상에 터치하는 터치 위치정보를 획득하는 단계를 포함한다.
이와 같은 본 발명은 이와 같은 본 발명은 여러 가지 카메라를 이용하여 공간상의 홀로그램을 직접 터치하고 이를 인식할 수 있는 간단하고 용이한 방법을 제공하게 되고, 카메라 외에는 다른 센서를 사용하지 않고 또한 사람에 몸에 부착하지 않아도 될 뿐만 아니라, 아무런 부가적인 장치 없이 공간상의 홀로그램과 서로 자연스럽게 인터페이스 할 수 있는 방법을 제공하게 된다.-
公开(公告)号：KR1020130054711A
公开(公告)日：2013-05-27
申请号：KR1020110120263
申请日：2011-11-17
Applicant: 재단법인대구경북과학기술원
IPC: G06F3/03
CPC classification number: G06F3/0425 , G02B27/2292
Abstract: PURPOSE: A hologram touch recognition method using cameras is provided to be naturally interfaced with a hologram with only cameras. CONSTITUTION: Image correction is performed for agreeing with view images which are photographed by stereo cameras and a depth camera(S100). The stereo cameras and the depth camera photograph 3D images, which include a hologram image generated in a hologram generation unit, in real time(S200). The hologram image is recognized by comparing a 3D image photographed by a stereo camera with a 3D image photographed by the depth camera, and position information of the hologram image is obtained(S330). A touch recognition unit obtains touch position information of the hologram image(S430). [Reference numerals] (AA) Start; (BB) End; (S100) Correct an image for matching view images of a stereo camera and a depth camera; (S200) Photograph 3D images including a hologram image with the stereo camera and the depth camera in real time; (S310) Existence of the hologram image by deducting the images of the stereo camera and the depth camera?; (S330) Obtain spatial position information of the hologram image; (S410) Recognize a touch pointer of a spatial user of the hologram image; (S430) Obtain touch position information of the touch pointer through the image of the stereo camera; (S500) Transmit touch position information to an external hologram generation unit
Abstract translation: 目的：提供使用相机的全息图触摸识别方法，仅使用相机自然地与全息图进行接口。 构成：执行图像校正以与由立体相机和深度相机拍摄的观看图像一致（S100）。 立体相机和深度相机实时拍摄包括在全息图生成单元中生成的全息图的3D图像（S200）。 通过将由立体摄像机拍摄的3D图像与由深度摄像机拍摄的3D图像进行比较来识别全息图像，并获得全息图像的位置信息（S330）。 触摸识别单元获得全息图像的触摸位置信息（S430）。 （附图标记）（AA）开始; （BB）结束; （S100）校正用于匹配立体相机和深度相机的观看图像的图像; （S200）实时拍摄包含立体相机和深度相机的全息图像的3D图像; （S310）通过扣除立体相机和深度相机的图像来存在全息图像; （S330）获取全息图像的空间位置信息; （S410）识别全息图像的空间用户的触摸指示器; （S430）通过立体摄像机的图像获取触摸指针的触摸位置信息; （S500）将触摸位置信息发送到外部全息图生成单元
-
公开(公告)号：KR101260053B1
公开(公告)日：2013-05-06
申请号：KR1020110120027
申请日：2011-11-17
Applicant: 재단법인대구경북과학기술원
CPC classification number: B60K28/02 , B60K28/00 , G06F3/011 , G06F3/017 , G06F3/0304 , G06F3/0346 , G06F3/16
Abstract: PURPOSE: An intelligent vehicle control device using motion and voice and a method thereof are provided to control the operation of the desired equipment in a range of not interfering in driving by determining a vehicle control command by combining a voice recognition technique and a motion recognition unit. CONSTITUTION: An intelligent vehicle control device(100) using motion and voice comprises a storage unit(110), an interface unit(120), a 3D filming unit(130), a motion recognition module(140), a microphone, a voice recognition module(160), and a control unit(170). The storage unit stores a vehicle control command corresponding to the hand motion and voice of a driver. The interface unit connects the device and a vehicle control module(200) to communicate with each other. The 3D filming unit films the hand motion of the driver with a 3D image. The motion recognition module recognizes the filmed hand motion, and the microphone receives the voice of the driver. The voice recognition module recognizes the voice inputted through the microphone based on a hand motion recognized by the motion recognition module. The control unit confirms the vehicle control command corresponding to the filmed hand motion and the recognized voice. [Reference numerals] (100) Intelligent vehicle control device; (110) Storage unit; (120) Interface unit; (130) 3D filming unit; (140) Motion recognition module; (142) Image registration unit; (144) Depth calculating unit; (146) Hand motion detecting unit; (150) Microphone; (160) Voice recognition module; (170) Control unit; (200) Vehicle control module; (300) Vehicle device; (310) Radio; (320) Airconditioner; (330) Navigation
Abstract translation: 目的：提供一种使用运动和语音的智能车辆控制装置及其方法，用于通过组合语音识别技术和运动识别单元来确定车辆控制命令，在不干扰驾驶的范围内控制所需设备的操作 。 构成：使用运动和声音的智能车辆控制装置（100）包括存储单元（110），接口单元（120），3D成像单元（130），运动识别模块（140），麦克风，语音 识别模块（160）和控制单元（170）。 存储单元存储与驾驶员的手动和声音相对应的车辆控制命令。 接口单元连接设备和车辆控制模块（200）以彼此通信。 3D拍摄单元用3D图像拍摄驾驶员的手动。 运动识别模块识别拍摄的手的运动，并且麦克风接收驾驶员的声音。 语音识别模块基于由运动识别模块识别的手动识别通过麦克风输入的声音。 控制单元确认对应于被拍摄的手动和识别的声音的车辆控制命令。 （附图标记）（100）智能车辆控制装置; （110）存储单元; （120）接口单元; （130）3D拍摄单元; （140）运动识别模块; （142）图像配准单元; （144）深度计算单元; （146）手动检测单元; （150）麦克风; （160）语音识别模块; （170）控制单元; （200）车辆控制模块; （300）车辆装置; （310）电台; （320）空调; （330）导航
-
公开(公告)号：KR101175611B1
公开(公告)日：2012-08-21
申请号：KR1020110023164
申请日：2011-03-16
Applicant: 재단법인대구경북과학기술원
CPC classification number: G06T7/246 , G06T7/13 , G06T7/514 , G06T7/73 , G06T2207/10048 , G06T2207/30204
Abstract: PURPOSE: A system and method for tracking object locations using a marker is provided to recognize marker locations by analyzing an infrared image acquired by an infrared camera. CONSTITUTION: An infrared projector(110) projects an infrared ray to an object(10). An infrared camera(120) captures the infrared ray reflected by a market(11) attached on the object. An image processing unit(130) analyzes an infrared image acquired by the infrared camera. The image processing unit recognizes a marker location and a marker shape. An object location tracker(140) tracks object locations according to maker recognition results of the image processing unit.
Abstract translation: 目的：提供使用标记跟踪对象位置的系统和方法，通过分析由红外摄像机获取的红外图像来识别标记位置。 构成：红外投影仪（110）将红外线投射到物体（10）。 红外摄像机（120）捕获由附着在物体上的市场（11）反射的红外线。 图像处理单元（130）分析由红外线摄像机获取的红外图像。 图像处理单元识别标记位置和标记形状。 物体位置跟踪器（140）根据图像处理单元的制造商识别结果跟踪对象位置。
-
公开(公告)号：KR1020110060697A
公开(公告)日：2011-06-08
申请号：KR1020090117365
申请日：2009-11-30
Applicant: 재단법인대구경북과학기술원
Abstract: PURPOSE: A black box for vehicle function and operator monitoring function are offered selectively and the safety of operator can be improved. CONSTITUTION: A camera system of processing picture data for vehicle for the vehicles comprises a photographing device(102), a photographing device photographing angle variable device(104), a vehicle control device interface device(110), and a control device(100). It locates in the front side of the driver's seat of the vehicles and it fulfills imaging and the photographing apparatus outputs the camera information. As to the photographing apparatus recording angle, the adjusting device interlinks the photographing apparatus and vehicles. And the camera angle of the photographing apparatus is varied. The vehicle control system interface equipment fulfills interface with the vehicle control system included in the vehicles. The control device extracts the face characteristic information after the adjustment of the camera angle from the camera information from the photographing apparatus. It encodes the camera information from the photographing apparatus after the adjustment of the camera angle and the control device stores.
Abstract translation: 目的：选择性地提供车辆功能和操作员监控功能的黑盒，可以提高操作员的安全性。 构成：车辆处理图像数据的相机系统包括拍摄装置（102），拍摄装置拍摄角度可变装置（104），车辆控制装置接口装置（110）和控制装置（100） 。 它位于车辆驾驶员座椅的前侧，并且其完成成像，并且拍摄设备输出摄像机信息。 关于拍摄装置记录角度，调节装置将拍摄装置和车辆相互连接。 并且拍摄装置的摄像机角度是变化的。 车辆控制系统接口设备与包括在车辆中的车辆控制系统进行接口。 控制装置从摄像装置的相机信息调整摄像机角度后提取脸部特征信息。 在调整摄像机角度并且控制装置存储之后，它对来自拍摄装置的照相机信息进行编码。
-
-
-
-
-
-
-
-
-
Search Results
79
records
(took 0.026 seconds)
