-
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：KR1020140040322A
公开(公告)日：2014-04-03
申请号：KR1020120105926
申请日：2012-09-24
Applicant: 재단법인대구경북과학기술원
IPC: G06T5/00
CPC classification number: G06T5/20 , G06T3/4053
Abstract: Provided is a method for reconstructing a super resolution image. The method of the present invention is a method for reconstructing a super resolution image from a low resolution image using sparse representation and edge reinforcement. Learning-based sparse representation and restoration-based repetitive reverse projection are used for reconstructing a super resolution image in the method. [Reference numerals] (AA) Start; (BB) End; (S10) Input a low resolution image; (S20) Reconstruct the image using a sparse representation; (S30) Preprocess; (S40) Reconstruct the image using repetitive reverse projection; (S50) Output a super resolution image
Abstract translation: 提供了一种用于重建超分辨率图像的方法。 本发明的方法是使用稀疏表示和边缘加强从低分辨率图像重建超分辨率图像的方法。 基于学习的稀疏表示和基于恢复的重复反向投影用于重建该方法中的超分辨率图像。 （附图标记）（AA）开始; （BB）结束; （S10）输入低分辨率图像; （S20）使用稀疏表示重建图像; （S30）预处理; （S40）使用重复反投影重建图像; （S50）输出超分辨率图像
-
公开(公告)号：KR101314293B1
公开(公告)日：2013-10-02
申请号：KR1020120093895
申请日：2012-08-27
Applicant: 재단법인대구경북과학기술원
CPC classification number: G06K9/4661 , G06F17/16 , G06F17/30244 , G06K9/00228
Abstract: PURPOSE: A face recognition system is provided to control misrecognition rates generated in an illumination change environment by applying a characteristic extracting technology based on image covariance. CONSTITUTION: A face database (DB) (150) stores face images and identification information for the face image. A face area detecting unit (110) extracts the face image from the inputted image, and a pre-processing unit (120) changes the pixel values of pixels constructing the face area into a binary pattern. A characteristic extraction unit (130) extracts characteristic information from the face image changed into the binary pattern. A face recognition unit (140) recognizes a face by using the characteristic information for the face images stored in the characteristic information and the face DB. [Reference numerals] (100) Image input unit; (110) Face area detecting unit; (120) Face area pre-processing unit; (130) Characteristic extraction unit; (140) Face recognition unit; (150) Face database
Abstract translation: 目的：提供一种面部识别系统，通过应用基于图像协方差的特征提取技术来控制在照明变化环境中产生的误识别率。 构成：面部数据库（DB）（150）存储面部图像和面部图像的识别信息。 脸部区域检测部（110）从输入图像中提取脸部图像，预处理部（120）将构成脸部区域的像素的像素值变更为二进制图案。 特征提取单元（130）从改变为二进制图案的面部图像提取特征信息。 面部识别单元（140）通过使用存储在特征信息和面部DB中的面部图像的特征信息来识别脸部。 （附图标记）（100）图像输入单元; （110）面部区域检测单元; （120）面部预处理单元; （130）特征提取单元; （140）面部识别单元; （150）脸部数据库
-
Patent Agency Ranking
公开(公告)号：KR1020130050670A
公开(公告)日：2013-05-16
申请号：KR1020110115872
申请日：2011-11-08
Applicant: 재단법인대구경북과학기술원
IPC: G06T7/20
CPC classification number: G06K9/00355 , G06T7/251 , G06T2207/30241 , H04N1/00381
Abstract: PURPOSE: A hand motion recognizing method using a camera and a device thereof are provided to recognize a hand motion by comparing trace information of a hand with a hand motion trace database. CONSTITUTION: A reference point detecting unit(110) detects a reference point of a hand photographed through a camera. A storage unit(120) stores trace information of the hand corresponding to a motion. A position comparing unit(130) calculates a difference value between a current position and the reference point of the hand. A trace comparing unit(140) compares the trace information corresponding to the motion with a hand motion trace database. A motion determining unit determines a hand motion matched with the trace information. [Reference numerals] (110) Reference point detecting unit; (120) Storage unit; (130) Position comparing unit; (140) Trace comparing unit; (150) Trace DB; (160) Motion discriminating unit; (170) Display unit
Abstract translation: 目的：提供使用相机及其装置的手动识别方法，通过将手的迹线信息与手运动跟踪数据库进行比较来识别手动。 构成：参考点检测单元（110）检测通过照相机拍摄的手的参考点。 存储单元（120）存储与运动对应的手的轨迹信息。 位置比较单元（130）计算当前位置和手的参考点之间的差值。 跟踪比较单元（140）将对应于运动的跟踪信息与手运动跟踪数据库进行比较。 运动确定单元确定与跟踪信息匹配的手动。 （附图标记）（110）参考点检测单元; （120）存储单元; （130）位置比较单元; （140）跟踪比较单位; （150）追踪DB; （160）运动识别单元; （170）显示单元
-
公开(公告)号：KR1020120111514A
公开(公告)日：2012-10-10
申请号：KR1020110030027
申请日：2011-04-01
Applicant: 재단법인대구경북과학기술원
Abstract: PURPOSE: An apparatus and method for extracting vehicle acceleration and deceleration information are provided to offer accurate information to a driver by extracting acceleration and deceleration information by considering of traffic conditions. CONSTITUTION: A raw data acquisition unit acquires raw data related to the driving of a vehicle(S510). A driving information creation unit converts the raw data into driving information which a driver is easy to understand(S520). A feature extraction unit extracts feature information related to acceleration and deceleration from current driving information(S530). A pattern recognition unit extracts the acceleration and deceleration information by receiving the information of current traffic conditions from a pattern recognition model(S540). [Reference numerals] (AA) Start; (BB) End; (S510) Low data acquisition; (S520) Driving information is created by processing low data; (S530) Features are extracted from driving information; (S540) Deceleration information is extracted by considering road state through a pattern recognition model
Abstract translation: 目的：提供车辆加速和减速信息提取装置和方法，通过考虑交通状况提取加速和减速信息，为司机提供准确的信息。 规定：原始数据采集单元获取与车辆的驾驶有关的原始数据（S510）。 驾驶信息创建单元将原始数据转换为驾驶员易于理解的驾驶信息（S520）。 特征提取单元从当前驾驶信息提取与加速和减速有关的特征信息（S530）。 模式识别单元通过从模式识别模型接收当前交通条件的信息来提取加速和减速信息（S540）。 （附图标记）（AA）开始; （BB）结束; （S510）低数据采集; （S520）通过处理低数据创建驾驶信息; （S530）从驾驶信息中提取功能; （S540）通过模式识别模型考虑道路状态来提取减速信息
-
公开(公告)号：KR101427854B1
公开(公告)日：2014-08-07
申请号：KR1020120105926
申请日：2012-09-24
Applicant: 재단법인대구경북과학기술원
IPC: G06T5/00
Abstract: 본 발명은 희소 표현법 및 에지 강화를 이용한 저해상도 영상을 고해상도 영상으로 복원하는 방법으로 학습 기반의 희소 표현법을 사용하고 복원 기반의 반복적 역투영을 사용하여 초고해상도로 영상을 복원할 수 있는 초고해상도 영상 복원 방법을 제공한다.
-
公开(公告)号：KR101422549B1
公开(公告)日：2014-07-24
申请号：KR1020120128451
申请日：2012-11-13
Applicant: 재단법인대구경북과학기술원
Abstract: 얼굴 인식 방법 및 그 시스템이 개시된다. 여기서, 얼굴 인식 방법은 얼굴 영상을 처리하는 장치의 얼굴 인식 방법으로서, 인식 대상인 얼굴 영상의 순차적인 데이터를 입력받는 단계, 2DDW(2-dimensional dynamic warping)을 알고리즘을 사용하여 상기 순차적인 데이터와 기 등록된 얼굴 영상의 순차적인 데이터 간에 픽셀 단위 최적 매칭을 수행하는 단계, 그리고 최적 매칭을 통해 도출된 픽셀들간의 유사도를 측정하여 얼굴 인식을 수행하는 단계를 포함한다.
-
公开(公告)号：KR1020140061189A
公开(公告)日：2014-05-21
申请号：KR1020120128451
申请日：2012-11-13
Applicant: 재단법인대구경북과학기술원
CPC classification number: G06K9/00261 , G06K9/6201 , G06T3/0093
Abstract: Disclosed are a face recognition method and a system thereof. The face recognition method of the present invention is a method for recognizing a face of a device which processes facial images. The face recognition method includes a step of receiving consecutive data of a facial image to be recognized; a step of performing pixel-level optimum matching between the received consecutive data and consecutive data of a pre-registered facial image using two-dimensional dynamic warping (2DDW) algorithm; and a step of recognizing a face by measuring similarity among pixels acquired through the optimum matching.
Abstract translation: 公开了面部识别方法及其系统。 本发明的脸部识别方法是用于识别处理面部图像的装置的面部的方法。 面部识别方法包括：接收要识别的面部图像的连续数据的步骤; 使用二维动态翘曲（2DDW）算法对所接收的连续数据和预先登记的面部图像的连续数据进行像素级最佳匹配的步骤; 以及通过测量通过最佳匹配获得的像素之间的相似度来识别面部的步骤。
-
-
-
-
-
-
-
-
-
Search Results
33
records
(took 0.019 seconds)
