ISCAS OpenIR  > 天基综合信息系统全国重点实验室
基于稳定区域梯度方向直方图的行人检测方法
Alternative Titlepedestrian detection based on hog of stable area
陈锐; 彭启民
2012
Source计算机辅助设计与图形学学报
ISSN10039775
Volume24Issue:3Pages:372-377
English Abstract针对HOG算法采用简单均匀分布的块提取行人特征,导致过多冗余特征和检测效率较低问题,提出一种启发式的块生成算法.首先将待检测窗口划分成多个大小不一且交叉重叠的块,然后根据各个块的梯度方向直方图特征的稳定性对各个块进行排序,最后选取稳定性最高的多个块作为最终HOG算法的特征提取块.实验结果表明,该算法可取得较好的检测效果,并且检测速度得到了进一步的提高.
AbstractIn this paper we propose a novel heuristic block-generating algorithm for reducing redundant features and increasing detection efficiency in pedestrian detection. Firstly, the detection window is divided into overlapped blocks with variant sizes. Then these blocks are sorted according to the stability of the histogram of oriented gradient for each block. Finally, HOG features from the most stable blocks can be extracted. Experimental results show that the proposed algorithm is faster and more accurate than the existing ones.
KeywordAlgorithms
Department中国科学院软件研究所天基综合信息系统重点实验室;中国科学院研究生院;
SubjectComputer Science
Language中文
Content Type期刊论文
URIhttp://ir.iscas.ac.cn/handle/311060/14660
Collection天基综合信息系统全国重点实验室
Recommended Citation
GB/T 7714
陈锐,彭启民. 基于稳定区域梯度方向直方图的行人检测方法[J]. 计算机辅助设计与图形学学报,2012,24(3):372-377.
APA 陈锐,&彭启民.(2012).基于稳定区域梯度方向直方图的行人检测方法.计算机辅助设计与图形学学报,24(3),372-377.
MLA 陈锐,et al."基于稳定区域梯度方向直方图的行人检测方法".计算机辅助设计与图形学学报 24.3(2012):372-377.
Files in This Item:
File Name/Size DocType Version Access License
基于稳定区域梯度方向直方图的行人检测方法(869KB) 开放获取LicenseApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[陈锐]'s Articles
[彭启民]'s Articles
Baidu academic
Similar articles in Baidu academic
[陈锐]'s Articles
[彭启民]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[陈锐]'s Articles
[彭启民]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.