公开(公告)号：KR1020120003590A

公开(公告)日：2012-01-11

申请号：KR1020100064272

申请日：2010-07-05

Applicant: 성균관대학교산학협력단

Inventor： 전재욱 ,  진승훈 ,  김동균 ,  뉴엔덩투이 ,  정준희 ,  석민식 ,  송지호

IPC: G01P3/00 ,  G08G1/052 ,  G08G1/054

CPC classification number: G01P3/50 ,  G06T15/30 ,  G08G1/0125 ,  G08G1/054

Abstract: PURPOSE: A vehicle velocity measurement apparatus and a method thereof are provided to calculate the moving displacement of a moved vehicle, thereby measuring the velocity displacement of the vehicle while driving. CONSTITUTION: A vehicle velocity measurement apparatus comprises a video camera(100), a image processing part(200), a frame buffer memory part(500), a velocity calculation part(300), and a control part(400). The video camera records a video image with respect to a vehicle while driving. The image processing part creates images for different time slots with respect to the same vehicle using the video image received from the video camera. The frame buffer memory part saves the image processed in the image processing part. The velocity calculation part calculates the velocity of vehicle using two vehicle images created in the image processing part. The control part controls a vehicle velocity calculation process of the velocity calculation part, an image saving process of the frame buffer memory part, and a video image creation process of the image processing part.

Abstract translation: 目的：提供一种车速测量装置及其方法，用于计算移动车辆的移动位移，从而在驾驶时测量车辆的速度位移。 构成：车速测量装置包括摄像机（100），图像处理部分（200），帧缓冲存储器部分（500），速度计算部分（300）和控制部分（400）。 视频摄像机在驾驶时记录关于车辆的视频图像。 图像处理部分使用从摄像机接收的视频图像，针对相同的车辆创建不同时隙的图像。 帧缓冲存储器部分保存在图像处理部分中处理的图像。 速度计算部分使用在图像处理部分中创建的两个车辆图像来计算车辆的速度。 控制部控制速度计算部的车速计算处理，帧缓冲存储部的图像保存处理以及图像处理部的视频图像生成处理。

公开(公告)号：KR101081934B1

公开(公告)日：2011-11-09

申请号：KR1020100017393

申请日：2010-02-25

Applicant: 성균관대학교산학협력단

Inventor： 전재욱 ,  김동균 ,  진승훈 ,  이상준 ,  정준희 ,  석민식 ,  송지호

IPC: H04N5/265 ,  H04N5/262

Abstract: 본발명은영상합성장치및 그파노라마영상생성방법에관한것이다. 복수의카메라로부터수신된영상을이용한파노라마영상생성방법은, 상기복수의카메라로부터화소정보를수신하는단계와; 상기수신된화소정보를가상좌표로변환하는단계와; 상기가상좌표로변환된화소중 유효좌표의화소정보를상기복수의카메라에대응하는복수의제1 메모리에순차적으로저장하는단계와; 상기복수의제1 메모리에저장된화소정보를읽어하나의제2 메모리에순차적으로저장하는단계와; 상기제2 메모리에저장된화소정보를읽어제3 메모리에저장하는단계와; 상기제3 메모리에저장된화소정보에기초하여생성된파노라마영상을출력하는단계를포함한다. 이에의하여, 복수의카메라로부터수신된영상의화소정보만을저장하는적은용량의메모리를계층적으로구성하여, 메모리용량을최소화하고처리속도를향상시킬수 있다.

公开(公告)号：KR1020090104351A

公开(公告)日：2009-10-06

申请号：KR1020080029744

申请日：2008-03-31

Applicant: 성균관대학교산학협력단

Inventor： 전재욱 ,  진승훈 ,  김동균 ,  김기훈 ,  이상준 ,  뉴엔덕융

IPC: G06T7/20

CPC classification number: G06T7/262 ,  G06T2207/10016 ,  G06T2207/30236

Abstract: PURPOSE: An image processing apparatus and method for detecting motion information in real time are provided to be used in an intelligent camera, an industrial field easily by being embedded through simple hardware structure. CONSTITUTION: An image processing apparatus(100) for detecting motion information includes a sub-sampling unit(120), a sensor's conversion unit(140), a correlation calculation unit(150) and a motion detecting unit(160). The sub-sampling unit performs a sub-sampling for each image by receiving plural previous images and current images, and a sensor's conversion unit obtains a sensor's vector by performing conversion for each image sub-sampled. The correlation calculation unit calculates and compares the correlation values between the current and previous images, and detects a region that has high correlation. The motion detection unit detects the motion information within an image by detecting the location of a pixel corresponding to the region that has the high correlation.

Abstract translation: 目的：提供一种用于实时检测运动信息的图像处理装置和方法，可以通过简单的硬件结构嵌入智能相机，工业领域中。 构成：用于检测运动信息的图像处理装置（100）包括子采样单元（120），传感器转换单元（140），相关计算单元（150）和运动检测单元（160）。 子采样单元通过接收多个先前图像和当前图像对每个图像执行子采样，并且传感器的转换单元通过对每个次采样的图像执行转换来获得传感器的向量。 相关计算单元计算并比较当前和先前图像之间的相关值，并且检测具有高相关性的区域。 运动检测单元通过检测对应于具有高相关性的区域的像素的位置来检测图像内的运动信息。

公开(公告)号：KR100886323B1

公开(公告)日：2009-03-04

申请号：KR1020070102275

申请日：2007-10-10

Applicant: 성균관대학교산학협력단

Inventor： 전재욱 ,  조정욱 ,  진승훈 ,  김동균 ,  팜다이쑨 ,  이대로 ,  김기훈

IPC: G06T7/20 ,  H04N5/262

CPC classification number: G06T7/74 ,  G06T5/40 ,  G06T7/90 ,  G06T2207/20021

Abstract: A real-time object tracking method and an apparatus thereof using a color histogram capable of continuously tracing the change of an object which is chosen on a track station are provided to modify a reference histogram based on the present histogram of the window which is chosen on the track station. A histogram generator(30) produces a plurality of windows from a successively inputted image. A similarity calculator(40) produces the similarity with the set standards histogram by each present histogram. A tracking target selector(60) extracts a standards histogram and the most high present histogram among the current histograms. The window corresponding to the extracted present histogram is selected as a tracking window. A modifier(70) modifies the standard histogram by reflecting the standard histogram.

Abstract translation: 提供了一种实时对象跟踪方法及其装置，其使用能够连续跟踪在轨道站上选择的对象的变化的颜色直方图，以基于窗口的当前直方图来修改参考直方图， 轨道站。 直方图生成器（30）从连续输入的图像生成多个窗口。 相似度计算器（40）通过每个当前的直方图产生与设置的标准直方图的相似性。 跟踪目标选择器（60）在当前直方图中提取标准直方图和最高当前直方图。 选择对应于提取的当前直方图的窗口作为跟踪窗口。 修改器（70）通过反映标准直方图来修改标准直方图。

公开(公告)号：KR100867163B1

公开(公告)日：2008-11-06

申请号：KR1020070060737

申请日：2007-06-20

Applicant: 성균관대학교산학협력단

Inventor： 전재욱 ,  김기훈 ,  조정욱 ,  진승훈 ,  팜티엔콩 ,  박종현 ,  이대로 ,  김동균

IPC: H04N1/41

Abstract: An image processing device is provided to reduce a thinning process time. Binarization data are divided into predetermined image blocks and stored in an input storing unit(120). A thinning unit(140) parallel thins the divided image blocks. An input switch unit(130) connects the input storing unit and the thinning unit. An output storing unit(160) stored the thinned image blocks. An output switch unit(150) connects the thinning unit and the output storing unit. An image data reconfiguration unit(170) combines the thinned image blocks stored in the output storing unit and reconfigures the blocks as thinned image data.

Abstract translation: 提供一种图像处理装置以减少稀疏处理时间。 二值化数据被划分为预定的图像块并存储在输入存储单元（120）中。 细分单元（140）平行于划分的图像块。 输入开关单元（130）连接输入存储单元和稀疏单元。 输出存储单元（160）存储变薄的图像块。 输出开关单元（150）连接稀疏单元和输出存储单元。 图像数据重新配置单元（170）组合存储在输出存储单元中的稀疏图像块，并将块重新配置为缩小的图像数据。

公开(公告)号：KR100855020B1

公开(公告)日：2008-08-28

申请号：KR1020070059320

申请日：2007-06-18

Applicant: 성균관대학교산학협력단

Inventor： 전재욱 ,  김동균 ,  조정욱 ,  진승훈 ,  이대로 ,  박종현 ,  김기훈 ,  팜티엔콩

IPC: H04N7/24

CPC classification number: G06K9/481 ,  G06T9/20

Abstract: A chain code generating apparatus and method are provided to generate the chain code for an interest decoding target from an input image in real-time only with a small hardware device, thereby reducing the overload of a total image processing system and maximizing the efficiency of the total image processing system. A chain code generating apparatus includes an image input unit(110), an image storage unit(120), a code generation unit(130), a code storage unit(140), and a transmission unit(150). The image input unit receives image signals from a camera(200), converts the received image signals into digital image signals, and divides and outputs sync signals from the image signals. The image storage unit stores image data corresponding to an effective image section by frame out of the digital image signals on the basis of the sync signals. The code generation unit reads the image data stored in the image storage unit to perform the outline searching of an interest decoding area, and generates the chain code in correspondence to location correlation between adjacent pixels forming the outline of the interest decoding area according to a searching result. The image storage unit includes a first buffer memory and a second buffer memory, and stores the image data corresponding to the effective image section alternately in the first buffer memory and the second buffer memory whenever a frame is changed. When the image data is stored in one of the first buffer memory and the second buffer memory, the code generation unit reads image data from the other of the first buffer memory and the second buffer memory to generate the chain code.

Abstract translation: 提供了一种链码生成装置和方法，用于仅通过小的硬件设备实时地从输入图像生成兴趣解码目标的链码，从而减少了整个图像处理系统的过载并且最大限度地提高了效率 总图像处理系统。 一种链码生成装置，包括图像输入单元（110），图像存储单元（120），代码生成单元（130），代码存储单元（140）和传输单元（150）。 图像输入单元从摄像机（200）接收图像信号，将接收到的图像信号转换成数字图像信号，并从图像信号中分离并输出同步信号。 图像存储单元基于同步信号，从数字图像信号中逐个存储对应于有效图像的图像数据。 代码生成单元读取存储在图像存储单元中的图像数据以执行兴趣解码区域的轮廓搜索，并且根据搜索结果生成与形成感兴趣解码区域的轮廓的相邻像素之间的位置相关性的链码 结果。 图像存储单元包括第一缓冲存储器和第二缓冲存储器，并且每当帧被改变时，将与有效图像部分相对应的图像数据交替地存储在第一缓冲存储器和第二缓冲存储器中。 当图像数据存储在第一缓冲存储器和第二缓冲存储器之一中时，代码生成单元从第一缓冲存储器和第二缓冲存储器中的另一个读取图像数据，以生成链码。

公开(公告)号：KR1020140040527A

公开(公告)日：2014-04-03

申请号：KR1020120107347

申请日：2012-09-26

Applicant: 삼성전자주식회사 ,  성균관대학교산학협력단

Inventor： 한정호 ,  김정섭 ,  김동균 ,  뉴엔덕융 ,  이상준 ,  전병무 ,  전재욱 ,  박상배 ,  최진욱

IPC: G06T7/00

CPC classification number: G06T7/0012 ,  G06T5/20 ,  G06T2207/30008 ,  G06T2219/2016

Abstract: According to the present invention, an apparatus for detecting body skeleton and body parts information from an image comprises: an Euclidean distance transform image input unit for receiving an Euclidean distance transformed image by applying the Euclidean distance transformation to a body image inputted from a user image input device; a body detection unit for detecting the body skeleton and body parts information by applying a local maxima calculation to the Euclidean distance transformed image; and a body parts information output unit for outputting the detected body skeleton and body parts information. [Reference numerals] (200) Euclidean distance transform image input imot; (231) Skeleton detection uni; (232) Head detection unit; (234) Body detection unit; (236) Shoulder/hip detection unit; (238) Arms/legs detection unit; (260) Body parts information output unit; (290) Euclidean distance transformation image output unit

Abstract translation: 根据本发明，一种用于从图像检测身体骨骼和身体部位信息的装置包括：欧几里得距离变换图像输入单元，用于通过将欧几里得距离变换应用于从用户图像输入的身体图像来接收欧几里德距离变换图像 输入设备; 身体检测单元，用于通过对欧几里德距离变换图像应用局部最大值计算来检测身体骨骼和身体部位信息; 以及身体部位信息输出单元，用于输出检测到的身体骨骼和身体部位信息。 （附图标记）（200）欧氏距离变换图像输入图像; （231）骨骼检测单位 （232）头检测单元; （234）身体检测单元; （236）肩臀检测单位; （238）臂/腿检测单元; （260）身体部位信息输出单元; （290）欧氏距离变换图像输出单元

公开(公告)号：KR1020130084437A

公开(公告)日：2013-07-25

申请号：KR1020120005223

申请日：2012-01-17

Applicant: 성균관대학교산학협력단

Inventor： 전재욱 ,  송지호 ,  정준희 ,  김동균 ,  이상준 ,  김대진 ,  김문상

IPC: G06T7/00

CPC classification number: G06K9/00268

Abstract: PURPOSE: A real time face recognition apparatus is provided to automatically obtain an image coordinate of a face for an image inputted to a camera and to output a recognition result of a face in real time. CONSTITUTION: A face detector (110) obtains an image coordinate of a face from an inputted image and detects a face image. An eye detector (120) obtains a binocular image coordinate from the detected face image. A face feature extractor (130) generates feature histogram data through the parallel processing of the detected face image. A histogram matching unit (150) compares the generated feature histogram data with a comparison feature histogram in a database unit (140) and outputs the similarity of the face image. [Reference numerals] (100) Real-time face recognition device; (110) Face detector; (120) Eye detector; (130) Face feature extractor; (131) Face normalizing unit; (132) Convolution filtering operation unit; (133) MLBP operation unit; (134) Histogram generating unit; (140) Database unit; (150) Histogram matching unit; (160) Recognition result output unit

Abstract translation: 目的：提供实时脸部识别装置，以自动获得输入到照相机的图像的脸部的图像坐标，并实时输出脸部的识别结果。 构成：面部检测器（110）从输入图像获得脸部的图像坐标，并检测脸部图像。 眼睛检测器（120）从检测到的脸部图像获得双目图像坐标。 面部特征提取器（130）通过所检测的脸部图像的并行处理产生特征直方图数据。 直方图匹配单元（150）将生成的特征直方图数据与数据库单元（140）中的比较特征直方图进行比较，并输出面部图像的相似度。 （附图标记）（100）实时面部识别装置; （110）面部检测器; （120）眼科检测仪; （130）面部特征提取器; （131）脸部归一化单元; （132）卷积滤波运算单元; （133）MLBP操作单元; （134）直方图生成单元; （140）数据库单元; （150）直方图匹配单位; （160）识别结果输出单元

公开(公告)号：KR1020120018946A

公开(公告)日：2012-03-06

申请号：KR1020100081964

申请日：2010-08-24

Applicant: 성균관대학교산학협력단

Inventor： 전재욱 ,  석민식 ,  진승훈 ,  김동균 ,  정준희 ,  송지호 ,  이상준

IPC: G06F3/03

CPC classification number: G06F3/0317 ,  G06F3/005 ,  G06F3/0386 ,  H04N5/23216 ,  H04N5/74

Abstract: PURPOSE: A laser pointer interface apparatus and an interface supplying method using the same are provided to set up a pointer coordinate value of a laser pointer in a dynamic environment by performing calibration. CONSTITUTION: A projector(10) projects a basis image. A camera unit(100) photogrpahs a first pointer image which displays a point of a laser pointer. A focus control part(200) controls the focus of a second pointer image in which the first pointer image is magnified or reduced. An image data processor(300) processes data of the first and second pointer image. A calibrator(400) matches the basic image with first pointer image. A point detector(500) detects the location of the point from the first or the second pointer image.

Abstract translation: 目的：提供激光指针接口装置和使用该激光指针接口装置的接口提供方法，以通过执行校准在动态环境中建立激光指示器的指针坐标值。 规定：投影机（10）投影基础图像。 相机单元（100）照射显示激光指示器的点的第一指针图像。 聚焦控制部分（200）控制放大或缩小第一指针图像的第二指针图像的焦点。 图像数据处理器（300）处理第一和第二指针图像的数据。 校准器（400）将基本图像与第一指针图像匹配。 点检测器（500）从第一或第二指针图像检测点的位置。

公开(公告)号：KR101000036B1

公开(公告)日：2010-12-09

申请号：KR1020080047681

申请日：2008-05-22

Applicant: 성균관대학교산학협력단

Inventor： 전재욱 ,  진승훈 ,  김동균 ,  김기훈 ,  이상준

IPC: H04N7/01

Abstract: 본 발명은 실시간 영상 처리를 위한 시스템 및 방법에 관한 것으로, 보다 구체적으로는 실시간 영상 처리를 위한 서브 샘플링 시스템 및 방법에 관한 것이다.
본 발명은, 원본 이미지에 대하여 다수의 서브 샘플링 레이트(rate)에 따라 서브 샘플링을 수행하는 시스템에 있어서, 상기 다수의 서브 샘플링 레이트에 상응하는 저장 공간을 갖는 레지스터를 할당하고, 상기 원본 이미지 및 다수의 서브 샘플링 레이트에 상응하는 내부 메모리를 할당하는 윈도우 생성부; 상기 원본 이미지의 어느 일부를 상기 내부 메모리에 픽셀 단위로 순차적으로 저장시키고, 상기 내부 메모리에 저장된 픽셀 데이터 중 서브 샘플링이 수행되는 영역에 상응하는 무빙 윈도우에 속하는 픽셀 데이터를 상기 레지스터에 순차적으로 저장시키고, 상기 무빙 윈도우를 순차적으로 이동시키는 윈도우 연산부; 상기 레지스터에 저장된 픽셀 데이터를 이용하여 상기 다수의 서브 샘플링 레이트 각각에 상응하는 다수의 보간 픽셀을 산출하는 픽셀 보간부; 및 상기 보간 픽셀을 출력하는 서브 샘플링 영상 출력부를 포함한다.
실시간 영상 처리, 서브 샘플링, 보간, 병렬 처리