QQ客服 官方微博 反馈留言

	基于级联Adaboost的目标检测融合算法
	崔潇潇 ; 姚安邦 ; 王贵锦 ; 林行刚 ; CUI Xiao-Xiao ; YAO An-Bang ; WANG Gui-Jin ; LIN Xing-Gang
	2010-06-09 ; 2010-06-09
关键词	目标检测 融合模型 边界片段特征 Haar特征 级联Adaboost Object detection combined model edge-fragment feature Haar feature cascaded Adaboost TP391.41
其他题名	Object Detection by Combined Model Based on Cascaded Adaboost
中文摘要	单一特征的模型对于颜色纹理变化较大的目标的检测往往存在检测率不高或检测速度慢的缺点.本文提出了一种基于级联Adaboost的"级联-加和"融合算法.融合模型由两个独立训练得到的级联Adaboost分类器组成,分别利用边界片段特征和矩形类Haar小波特征描述整个目标以及目标的一个稳定部件.级联-加和的融合决策以样本在两个分类器中被拒绝或通过的级数信息为依据.在多个数据库上的实验证明这种融合检测算法不仅综合了Haar小波特征检测速度快和边界片段特征鲁棒性好的优点,而且与单一特征的分类器相比,检测性能也有所提高.; Single feature-based model always meets the difficulties of poor detection performance and slow detection speed for object with large variances in color,texture,and shape.A novel cascaded and additive model based on cascaded Adaboost classifier is proposed in this paper.This combined model consists of two cascaded Adaboost classifiers which are independently trained with edge-fragment feature and Haar feature to describe the whole object and one of its stable components,respectively.The final classification decision of the combined model is made according to the stage indexes by which a sample is rejected or accepted in the two cascaded classifiers.Experiments on several test databases show that the combined model can take advantages of the speed merit of Haar feature and the robustness of edge-fragment feature. Compared with single feature-based model,the detection performance of the combined model is greatly improved.; 国家自然科学基金(60472028); 教育部博士点基金(20040003015)资助~~
语种	中文 ; 中文
内容类型	期刊论文
源URL	[http://hdl.handle.net/123456789/54038]
专题	清华大学
推荐引用方式 GB/T 7714	崔潇潇,姚安邦,王贵锦,等. 基于级联Adaboost的目标检测融合算法[J],2010, 2010.
APA	崔潇潇.,姚安邦.,王贵锦.,林行刚.,CUI Xiao-Xiao.,...&LIN Xing-Gang.(2010).基于级联Adaboost的目标检测融合算法..
MLA	崔潇潇,et al."基于级联Adaboost的目标检测融合算法".(2010).

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。