检索结果-南通市图书馆

Boosted cascade of scattered rectangle features for object detection

Science in China(Series F) 2009年第2期52卷 236-243页

作者： ZHANG WeiZe TONG RuoFeng DONG JinXiang Institute of Artificial Intelligence Zhejiang University Hangzhou 310027 China

This paper presents a variant of haar-Iike feature used in Viola and Jones detection framework, called scattered rectangle feature, based on the common-component analysis of local region feature. Three common components, feature filter, feature structure and feature form, are extracted without concerning the details of the studied region features, which cast a new light on region feature design for specific applications and requirements： modifying some component（s） of a feature for an improved one or combining different components of existing features for a new favorable one. Scattered rectangle feature follows the former way, extending the feature structure component of haar-like feature out of the restriction of the geometry adjacency rule, which results in a richer representation that explores much more orientations other than horizontal, vertical and diagonal, as well as misaligned, detached and non-rectangle shape information that is unreachable to haar-Iike feature. The training result of the two face detectors in the experiments illustrates the benefits of scattered rectangle feature empirically; the comparison of the ROC curves under a rigid and objective detection criterion on MIT＋CMU upright face test set shows that the cascade based on scattered rectangle features outperforms that based on haar-Iike features.

关键词： haar-like feature feature filter feature structure feature form cascade

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

An Improved Detection Algorithm of Face with Combining AdaBoost and SVM 25th

An Improved Detection Algorithm of Face with Combining AdaBo...

引用

第25届中国控制与决策会议

作者： Jia Mingxing Du Junqiang Cheng Tao Yang Ning Jiang Yi Zhang Zhen Academy of Information Science and Engineer Northeastern University

ISBN: (纸本)9781467355339

This paper proposes a face detection method by combining SVM into the traditional face detection algorithm named AdaBoost. This method adopts SVM classifier instead of traditional AdaBoost classifier based on AdaBoost cascade framework. To get SVM classifier, extract several haar-like features with the strongest classification ability in the process of training SVM classifier. To ensure the generalization capability of classifier classify validation set, and using the penalty factor setting with focus makes SVM classifier pay more attention to the face samples, while the training samples reached a high goodness of fit. At the same time, this thesis improves the extraction method of haar-like feature. Finally, using matlab simulation test the effectiveness of the algorithm. The experiments show that the improved detection algorithm of face with combining AdaBoost and SVM reduces the amount of computation and improve the detection rate.

关键词： AdsBoost algorithm face detection haar-like feature SVM

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Real-time Rear of Vehicle Detection from a Moving Camera

Real-time Rear of Vehicle Detection from a Moving Camera

引用

第26届中国控制与决策会议

作者： Qing Xu Feng Gao Ke Shi Guoyan Xu School of Transportation Science and Engineering Beihang University

ISBN: (纸本)9781479937097

Based on the requirement of real-time on road vehicle detection from a moving camera, a feature based rear of vehicle detection algorithm is developed. A haar-like feature classifier is trained to capture the rear of vehicles from the video stream in real-time and a premier test is performed. Aiming at some issues found in the test, which include duplicated detection, false alarms, undetected objects and the failure of detecting distant object due to limited resolution,a revised algorithm is given. Some further tests and analyses indicate that the revised algorithm can effectively detect the rear of vehicles in real-time with complex background from a moving camera.

关键词： Vision sensing Vehicle detection haar-like feature

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：