公开(公告)号：KR1020130058286A

公开(公告)日：2013-06-04

申请号：KR1020110124209

申请日：2011-11-25

Applicant: 한국전자통신연구원 ,  고려대학교 산학협력단

Inventor： 여준기 ,  천익재 ,  석정희 ,  윤상훈 ,  노태문 ,  김대환 ,  박원재 ,  고성제

IPC: G06T7/00

CPC classification number: G06K9/00369 ,  G06K9/6269

Abstract: PURPOSE: A pedestrian detection method of a pedestrian detection device is provided to perform pedestrian detection on a search window using a second classifier with high accuracy after reducing the number of search windows, thereby performing highly accurate detection of an object while reducing the complexity of detection procedure and power consumption. CONSTITUTION: A pedestrian detection device obtains an image from a digital image device and performs blocking of search windows(210,220). The pedestrian detection device selects a specific block from blocks determined by a pre-learned classifier(230) and produces a specific vector of HOG features from the selected block(240,250). The pedestrian detection device calculates a SVM(Support Vector Machine) response value using the produced feature vector, and performs a first object detection by applying the response value to an AdaBoost Classifier(260,270). If a pedestrian is detected at the first object detection, the pedestrian detection device performs a second object detection to the search window(280). [Reference numerals] (210) Obtain an image; (220) Performs blocking of search windows; (230) Pre-learned classifier; (240) Select a specific block; (250) Produce a specific vector; (260) Calculates a SVM response value; (270) Perform a first object detection; (280) Perform a second object detection; (290) Output decision; (AA) No; (BB) Yes

Abstract translation: 目的：提供一种行人检测装置的行人检测方法，在减少搜索窗口数量之后，使用第二分类器在搜索窗口上进行行人检测，从而对目标进行高精度的检测，同时降低检测的复杂度 程序和功耗。 规定：行人检测装置从数字图像装置获取图像并执行搜索窗口的封锁（210,220）。 行人检测装置从预先学习的分类器（230）确定的块中选择特定的块，并从所选择的块（240,250）生成特定的HOG特征向量。 行人检测装置使用所产生的特征向量来计算SVM（Support Vector Machine）响应值，并通过将响应值应用于AdaBoost分类器（260,270）来执行第一对象检测。 如果在第一物体检测中检测到行人，则行人检测装置对搜索窗口进行第二物体检测（280）。 （附图标记）（210）获取图像; （220）执行搜索窗口的阻止; （230）预先学习分类器; （240）选择一个特定块; （250）生成特定载体; （260）计算SVM响应值; （270）执行第一个对象检测; （280）执行第二对象检测; （290）产出决定; （AA）否 （BB）是的