公开(公告)号：KR1020140060081A

公开(公告)日：2014-05-19

申请号：KR1020120126738

申请日：2012-11-09

Applicant: 한국전자통신연구원

Inventor： 이한성 ,  유장희 ,  문대성 ,  최진우

IPC: G06K9/46 ,  G06K9/20 ,  G07C9/00

CPC classification number: G06K9/6202 ,  G06K9/00221 ,  G06T7/246 ,  G06T7/33

Abstract: An apparatus for controlling a speed gate based on remote face recognition is disclosed. An apparatus for controlling a speed gate based on remote face recognition according to the present invention includes: an entrance control part for collecting images, and opening and closing the speed gate; an image part which detects motion by obtaining a difference image from the collected image, and collects a face image of a moving Blob; and a security part for judging whether the face image of the Blob is an authenticated user, by comparing the face image of the Blob with a previously registered face image. The entrance control part supplies the collected image to the image part continuously, and the image part collects a face image continuously, from the image information supplied continuously, and the security part classifies each face image, which is continuously collected, as an authenticated user for a person obtaining the most votes in a candidate group classified as similar users, by comparing each collected face image with the previously registered face image.

Abstract translation: 公开了一种用于基于远程面部识别来控制速度门的装置。 根据本发明的用于控制基于远程面部识别的速度门的装置包括：用于收集图像并打开和关闭速度门的入口控制部分; 图像部分，通过从所收集的图像获得差异图像来检测运动，并且收集移动Blob的面部图像; 以及用于通过将Blob的面部图像与先前登记的面部图像进行比较来判断Blob的脸部图像是否是经认证的用户的安全部件。 入口控制部分将收集的图像连续地提供给图像部分，并且图像部分从连续供应的图像信息中连续地收集面部图像，并且安全部件将连续收集的每个面部图像分类为认证用户， 通过将每个收集的面部图像与先前登记的面部图像进行比较，获得在被分类为类似用户的候选组中的投票最多的人。

公开(公告)号：KR1020130085317A

公开(公告)日：2013-07-29

申请号：KR1020120006393

申请日：2012-01-19

Applicant: 한국전자통신연구원

Inventor： 최진우 ,  박소희 ,  고종국 ,  유장희

IPC: G06T7/20

CPC classification number: G06T7/2033 ,  G06T7/246 ,  G06T7/277 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20076 ,  G06T2207/30196 ,  G06T2207/30232

Abstract: PURPOSE: A human tracing method using a color histogram is provided to adaptively trace a human using the color histogram of different targets according to a pose of the human in case of tracing the human based on a particle filter, thereby stably improving tracing performance despite a change of the pose. CONSTITUTION: A human tracing device performs color space conversion about inputted image data (S20). The human tracing device produces a state equation about a particle based on converted data (S30). The human tracing device calculates an adaptive observation similarity according to a pose of a human (S40). The human tracing device extracts the particle again based on the adaptive observation similarity and calculates a state estimate value of the human (S50,S60). The human tracing device updates a target color histogram (S70). [Reference numerals] (AA) Start; (BB) End; (S10) Input image; (S20) Convert a color space; (S30) Calculate a state equation; (S40) Calculate adaptive observation similarity according to a pose; (S50) Extract particles; (S60) Calculate a state estimate value; (S70) Update a color histogram

Abstract translation: 目的：提供使用颜色直方图的人追踪方法，以使用基于粒子滤波器跟踪人的情况下根据人的姿态使用不同目标的颜色直方图自动跟踪人，从而稳定地提高跟踪性能，尽管 改变姿势。 构成：人物跟踪装置对输入的图像数据执行色彩空间转换（S20）。 人类跟踪装置基于转换的数据产生关于粒子的状态方程（S30）。 人体跟踪装置根据人的姿势计算自适应观察相似度（S40）。 人物跟踪装置基于自适应观察相似度再次提取粒子，并计算人的状态估计值（S50，S60）。 人物追踪装置更新目标颜色直方图（S70）。 （附图标记）（AA）开始; （BB）结束; （S10）输入图像; （S20）转换颜色空间; （S30）计算状态方程; （S40）根据姿势计算自适应观测相似度; （S50）提取颗粒; （S60）计算状态估计值; （S70）更新颜色直方图