운전자의 포인팅 제스처를 이용한 차량 구동 장치 및 그 방법
    11.
    发明公开
    운전자의 포인팅 제스처를 이용한 차량 구동 장치 및 그 방법 无效
    用于驾驶员驾驶的装置及其方法

    公开(公告)号:KR1020130076214A

    公开(公告)日:2013-07-08

    申请号:KR1020110144716

    申请日:2011-12-28

    Abstract: PURPOSE: A vehicle driving device using a pointing gesture of a driver and a method thereof are provided to perform an execution function corresponding to the pointing gesture by obtaining the pointing gesture. CONSTITUTION: A pointing gesture obtaining unit (110) obtains a pointing gesture of a driver and a memory (120) stores an execution function corresponding to the pointing gesture. When the pointing gesture is obtained, a control unit (130) extracts the execution function from the memory to perform the execution function. When the driver points a random direction as a gesture, the control unit detects an obstacle around a vehicle to notify obstacle information to the driver. [Reference numerals] (110) Pointing gesture obtaining unit; (120) Memory; (130) Control unit; (140) Output unit; (150) Key operation unit; (160) Sensor unit; (170) Device operating unit

    Abstract translation: 目的:提供使用驾驶员的指示手势的车辆驾驶装置及其方法,以通过获取指示姿势来执行与指示姿势相对应的执行功能。 构成:指示姿势获取单元(110)获得驾驶员的指示手势,并且存储器(120)存储与指示手势相对应的执行功能。 当获得指示手势时,控制单元(130)从存储器提取执行功能以执行执行功能。 当驾驶员将随机方向指向手势时,控制单元检测车辆周围的障碍物,向驾驶者通知障碍物信息。 (附图标记)(110)指示姿势获取单元; (120)内存; (130)控制单元; (140)输出单元; (150)键操作单元; (160)传感器单元; (170)设备操作单元

    차량 인터랙션 시스템
    12.
    发明授权
    차량 인터랙션 시스템 有权
    车辆相互作用系统

    公开(公告)号:KR101714089B1

    公开(公告)日:2017-03-09

    申请号:KR1020110136419

    申请日:2011-12-16

    Abstract: 탑승자의제스쳐를인지하는인지수단, 탑승자의제스쳐가기설정된소정의패턴과일치하는지판단하는판단수단, 탑승자의제스쳐가소정의패턴과일치하는경우탑승자에게탑승자의제스쳐가올바로인지되었음을알리는피드백수단을포함하고, 피드백수단은탑승자의좌석내에설치된진동모터이며, 복수의진동모터의진동패턴은, 진동시기에시계열적으로차별을두어탑승자가구별할수 있는서로다른피드백신호를발생시키거나, 서로다른복수의위치중 소정위치또는소정위치의조합의진동으로탑승자가구별할수 있는서로다른피드백신호를발생시키거나, 진동의세기에차별을두어탑승자가구별할수 있는서로다른피드백신호를발생시킬수 있는차량인터랙션시스템이다.

    Abstract translation: 目的:提供车辆交互系统,以提供准确的反馈,并使车辆能够安全驾驶,而无需驾驶员的视觉或听觉分散。 构成:车辆交互系统包括识别单元(10),手势识别确定单元(20),存储单元(30)和反馈单元(40)。 识别单元包括触摸显示单元​​(11)和相机(12)。 触摸显示单元​​识别乘客的手势。 相机拍摄乘客的图像并识别乘客的运动。 手势识别确定单元确定由识别单元识别的手势是否与存储在存储单元中的预定手势图案相匹配。 当乘客的手势与预定手势模式相匹配时,反馈单元通知乘客完成手势识别。 (附图标记)(11)触摸显示单元​​; (12)运动识别相机; (20)手势识别和确定单位; (30)存储单元

    스테레오 매칭용 보간 계수 보정 장치
    13.
    发明授权
    스테레오 매칭용 보간 계수 보정 장치 有权
    插值因子校正装置的立体匹配

    公开(公告)号:KR101558805B1

    公开(公告)日:2015-10-07

    申请号:KR1020140117087

    申请日:2014-09-03

    Inventor: 최진하

    Abstract: 본발명은스테레오매칭용보간계수보정장치에관한것으로, 쿼드트리(Quad-tree) 기반스테레오매칭알고리즘에서트리의깊이를결정하는보간계수를영상내 객체의위치에따라적응적으로보정함으로써, 스테레오영상을이용하여객체와의거리산출시정확도를높일수 있는스테레오매칭용보간계수보정장치를제공하고자한다. 이를위하여, 본발명은스테레오매칭용보간계수보정장치에있어서, 보간계수(λ)를생성하는보간계수생성부; 영상내 객체의위치에따라파라미터및 가중치를산출하는보정값산출부; 및상기보정값산출부에의해산출된파라미터및 가중치를상기보간계수생성부에의해생성된보간계수에곱하여상기보간계수를보정하는보간계수보정부를포함한다.

    Abstract translation: 本发明涉及一种用于校正立体匹配的内插系数的装置。 更具体地,该装置根据图像中的对象的位置自适应地校正在基于四叉树的立体匹配算法中确定树的深度的内插系数,以便增加通过使用计算出的与对象距离的精度 立体图像。 因此,该装置包括:内插系数生成单元,生成插值系数(λ); 校正值计算单元,其根据所述对象在所述图像中的位置来计算参数和权重值; 以及内插系数校正单元,其将由内插系数生成单元生成的内插系数乘以权重值和由校正值计算单元计算的参数,以校正插值系数。

    스테레오 카메라를 이용한 물체 추적 장치 및 방법
    15.
    发明授权
    스테레오 카메라를 이용한 물체 추적 장치 및 방법 有权
    使用立体摄像机跟踪对象的装置和方法

    公开(公告)号:KR101480626B1

    公开(公告)日:2015-01-08

    申请号:KR1020130077395

    申请日:2013-07-02

    Inventor: 최진하

    CPC classification number: G06T7/285 B60R2300/107 G06T3/4007

    Abstract: 본 발명은 스테레오 카메라를 이용한 물체 추적 장치 및 방법에 관한 것으로, 본 발명에 따른 장치는 차량 전방에 대한 제1 영상을 촬영하는 제1 카메라, 상기 제1 영상의 특정 영역에 대해 줌 인-아웃(zoom in-out)하여 제2 영상을 촬영하는 제2 카메라, 상기 제1 카메라 및 상기 제2 카메라 구동 시 상기 제2 카메라에 대한 설정 계수에 따라 상기 제2 카메라의 줌 인-아웃을 제어하는 구동 제어부, 및 상기 구동 제어부의 제어에 따라 상기 제1 카메라 및 상기 제2 카메라에 의해 획득된 상기 제1 영상 및 상기 제2 영상으로부터 상기 차량 주변의 물체를 추적하는 트래킹부를 포함한다.

    Abstract translation: 本发明涉及一种使用立体相机跟踪物体的装置和方法。 根据本发明的装置包括:第一相机,拍摄车辆前部的第一图像; 第二相机,其放大或缩小第一图像的特定区域以拍摄第二图像; 驱动控制单元,当驱动第一和第二相机时,根据第二相机的设定系数控制第二相机的变焦; 以及跟踪单元,其分别根据驱动控制单元的控制从第一图像和第一相机和第二相机拍摄的第二图像跟踪车辆周围的物体。

    양안 시차 영상의 보정 장치 및 그 방법
    16.
    发明公开
    양안 시차 영상의 보정 장치 및 그 방법 审中-实审
    用于补偿差异图像的装置及其方法

    公开(公告)号:KR1020140076430A

    公开(公告)日:2014-06-20

    申请号:KR1020120144917

    申请日:2012-12-12

    CPC classification number: H04N13/128 H04N2013/0096

    Abstract: The present invention relates to a correction apparatus for a binocular disparity image and a method thereof and, more specifically, to a correction apparatus for a binocular disparity image and a method thereof capable of correcting the binocular disparity image by converting an invalid pixel which is generated in the binocular disparity image which is generated through a stereo matching of a local mode into a valid pixel. The correction apparatus for a binocular disparity image, which is provided by the present invention for the forementioned, includes: an input unit which receives a binocular disparity image; a validity judging unit which detects a pixel (invalid pixel) which has an invalid binocular disparity value by judging the invalidity of the binocular disparity value of each pixel in the binocular disparity image which is received by the input unit; a brightness difference calculating unit which calculates a brightness difference between a surrounding pixel and the invalid pixel detected by the validity judging unit; a distance calculating unit which calculates a distance between the surrounding pixel and the invalid pixel detected by the validity judging unit; a depth similarity calculating unit which calculates a binocular disparity value difference between the surrounding pixel and the invalid pixel detected by the validity judging unit; a weighed value calculating unit which calculates a weighed value by multiplying the brightness difference calculated by the brightness difference calculating unit, the inter-pixel distance calculated by the distance calculating unit, the binocular disparity value difference calculated by the depth similarity calculating unit; and a correction unit which corrects a binocular disparity value of a pixel which has the greatest weighed value among weighed values which are calculated by the weighed value calculating unit with a binocular disparity value of a central pixel.

    Abstract translation: 本发明涉及一种用于双目视差图像的校正装置及其方法,更具体地,涉及一种用于双目视差图像的校正装置及其方法,其能够通过转换生成的无效像素来校正双目视差图像 在通过局部模式的立体匹配生成到有效像素中的双目视差图像中。 用于前述的本发明提供的用于双目视差图像的校正装置包括:输入单元,其接收双目视差图像; 有效性判断单元,其通过判断由所述输入单元接收的所述双目视差图像中的每个像素的双目视差值的无效性来检测具有无效双眼视差值的像素(无效像素); 亮度差计算单元,计算由所述有效性判定单元检测出的周围像素与所述无效像素之间的亮度差; 距离计算单元,其计算由所述有效性判定单元检测的所述周围像素与所述无效像素之间的距离; 深度相似度计算单元,其计算周围像素与由有效性判定单元检测到的无效像素之间的双目视差值差; 权重值计算单元,通过将由亮度差计算单元计算出的亮度差乘以由距离计算单元计算的像素间距离,由深度相似度计算单元计算的双眼视差值进行乘积来计算加权值; 以及校正单元,其校正由称重值计算单元用中心像素的双目视差值计算的称重值中具有最大称重值的像素的双目视差值。

    카메라 영상의 반사광 제거 장치 및 방법
    17.
    发明授权
    카메라 영상의 반사광 제거 장치 및 방법 有权
    用于去除摄像机反射光的装置和方法

    公开(公告)号:KR101327032B1

    公开(公告)日:2013-11-20

    申请号:KR1020120062806

    申请日:2012-06-12

    Inventor: 최진하

    Abstract: The present invention relates to an apparatus and a method for controlling reflected light of an camera image. The method for controlling reflected light of a camera image comprises: a filter control unit for outputting a control signal which directs a connected filter to be turned on or off at given intervals by being connected to either of filters through which reflected light passes and which are positioned on the windshield of a car and a camera lens respectively; an image obtaining unit for obtaining an image which is photographed by a camera installed in the windshield direction while the filter connected to the filter control unit is on or off according to control signals from the filter control unit; a vehicle image generating unit for generating a vehicle image by removing a reflected image, which is photographed while the filter connected to the filter control unit is on, from an general image, which is photographed while the filter connected to the filter control unit is off, among images photographed by the camera; and a vehicle image correction unit for obtaining a final image by correcting the brightness level of an area, which is part of the vehicle image and corresponds to the reflected image, based on a blurred image. [Reference numerals] (100) Apparatus for removing reflected light

    Abstract translation: 本发明涉及一种用于控制照相机图像的反射光的装置和方法。 用于控制相机图像的反射光的方法包括:滤波器控制单元,用于输出控制信号,该控制信号通过连接到反射光通过的滤波器中的任何一个,以指定的间隔引导连接的滤波器被接通或断开, 分别位于汽车挡风玻璃和相机镜头上; 图像获取单元,用于根据来自滤波器控制单元的控制信号来获取在安装在挡风玻璃方向上的相机拍摄的图像,同时连接到滤波器控制单元的滤波器接通或断开; 车辆图像生成单元,用于通过去除在与滤波器控制单元连接的滤波器处于打开状态的同时拍摄的反射图像,通过在连接到滤波器控制单元的滤波器关闭时拍摄的一般图像来生成车辆图像 在相机拍摄的图像中; 以及车辆图像校正单元,用于基于模糊图像来校正作为车辆图像的一部分并对应于反射图像的区域的亮度水平来获得最终图像。 (附图标记)(100)用于去除反射光的装置

    제스쳐 인식 기반 서비스 제공 시스템
    18.
    发明公开
    제스쳐 인식 기반 서비스 제공 시스템 无效
    基于姿态识别提供服务的系统

    公开(公告)号:KR1020130071241A

    公开(公告)日:2013-06-28

    申请号:KR1020110138638

    申请日:2011-12-20

    CPC classification number: G06F3/017 B60W50/08 G06F3/0304 G06F3/0346

    Abstract: PURPOSE: A gesture recognition based service providing system is provided to display necessary information on an HUD(Head-Up Display) screen of a navigation terminal by recognizing gesture suitable for each input. CONSTITUTION: A storage module(51) stores stored gesture based on change of a position. A skeleton recognition module(53) extracts a skeleton of a driver which is photographed by a vision camera corresponding to a skeleton and a joint point of a database. A gesture recognition module(54) traces gesture of the driver based on movement of the skeleton and the joint point. A control module(56) compares the extracted gesture with the stored gesture. When the extracted gesture corresponds to the stored gesture, the control module performs a function corresponding to the gesture. [Reference numerals] (51) Storage module; (52) Image processing module; (53) Skeleton recognition module; (54) Gesture recognition module; (55) Communication module; (56) Control module

    Abstract translation: 目的:提供基于手势识别的服务提供系统,通过识别适合于每个输入的手势来显示导航终端的HUD(平视显示)屏幕上的必要信息。 构成:存储模块(51)基于位置的改变存储存储的手势。 骨架识别模块(53)提取由对应于数据库的骨架和联合点的视觉摄像机拍摄的驾驶员的骨架。 手势识别模块(54)基于骨架和关节点的移动跟踪驾驶员的姿态。 控制模块(56)将所提取的手势与存储的手势进行比较。 当提取的手势对应于存储的手势时,控制模块执行与该手势相对应的功能。 (附图标记)(51)存储模块; (52)图像处理模块; (53)骨骼识别模块; (54)手势识别模块; (55)通讯模块; (56)控制模块

    동작 인식을 이용한 차량주변 촬영시스템
    19.
    发明公开
    동작 인식을 이용한 차량주변 촬영시스템 有权
    使用运动识别的图像车辆的成像系统

    公开(公告)号:KR1020130068943A

    公开(公告)日:2013-06-26

    申请号:KR1020110136417

    申请日:2011-12-16

    Abstract: PURPOSE: A shooting system for vehicle surrounding using movement recognition is provided to conveniently shoot vehicle surrounding without the driver separately taking out a camera by controlling the shooting movement of a shooting module which installed on a vehicle according to the promised movement with a user. CONSTITUTION: A shooting system(100) using movement recognition comprises a shooting module(10) installed on the vehicle to shoot surrounding the vehicle; a sensing module(20) installed on the vehicle to sense the promised movement of the user; and a control module(50) which shoots the surrounding of the vehicle and stores the shot image by controlling the shooting movement of the shooting movement according to the promised movement. The shooting method for vehicle surrounding using movement recognition comprises the following steps. (a) Promised movement of a user is sensed. (b) The surrounding of a vehicle is shot and the shot image is stored to a database(60) by controlling the shooting movement of the shooting module which is installed on a vehicle and shoots the surrounding of a vehicle according to the promised movement. [Reference numerals] (10) Shooting module; (20) Sensing module; (30) Setting storing module; (40) Display module; (50) Control module; (60) Data base

    Abstract translation: 目的:提供一种使用移动识别的车辆周边拍摄系统,方便拍摄车辆周边,而无需驾驶员分别取出相机,通过用户根据承诺的动作控制安装在车辆上的拍摄模块的拍摄动作。 构成:使用移动识别的拍摄系统(100)包括安装在车辆上以拍摄围绕车辆的拍摄模块(10) 安装在所述车辆上的感测模块(20),以感测所述使用者所许诺的运动; 以及控制模块(50),其通过根据承诺的运动控制拍摄动作的拍摄动作来拍摄车辆的周围并存储拍摄图像。 使用运动识别的车辆周边拍摄方法包括以下步骤。 (a)感测到用户的承诺的移动。 (b)通过控制安装在车辆上的拍摄模块的拍摄动作并根据承诺的动作拍摄车辆的周围,拍摄车辆的周围并将拍摄图像存储到数据库(60)。 (附图标记)(10)拍摄模块; (20)感应模块; (30)设定存储模块; (40)显示模块; (50)控制模块; (60)数据库

    개선된 차선 인식 방법
    20.
    发明授权

    公开(公告)号:KR101738034B1

    公开(公告)日:2017-05-22

    申请号:KR1020150097576

    申请日:2015-07-09

    Inventor: 황진규 최진하

    Abstract: 본발명은차선을인식하는방법에관한것으로서, 보다상세하게는스테레오카메라로부터취득한칼라영상과깊이영상을이용하여중복된차선에서실제차선을검출하는개선된차선인식방법에관한것이다. 보다구체적으로본 발명에대하여설명하면, 본발명은스테레오카메라로부터칼라영상과깊이영상을획득하는단계, 상기깊이영상을이용해수평위치과수직위치를인식하여소실점을도출하는단계, 상기소실점을이용해차선후보군을생성·투영하는단계, 상기칼라영상을이용해차선을인식하는단계, 칼라영상을이용해인식된차선과깊이영상을이용해생성·투영된차선후보군의유사도를측정하는단계및 실제차선을확정하는단계를포함하는개선된차선인식방법을제공한다.

Patent Agency Ranking