[1]张静,陈锦春,黄华灿.概率密度估计和阴影抑制的运动目标检测[J].华侨大学学报(自然科学版),2010,31(1):20-22.[doi:10.11830/ISSN.1000-5013.2010.01.0020]
　ZHANG Jing,CHEN Jin-chun,HUANG Hua-can.Kenel Density Estimation for Motion Detection and Shadow Suppression[J].Journal of Huaqiao University(Natural Science),2010,31(1):20-22.[doi:10.11830/ISSN.1000-5013.2010.01.0020]
点击复制

概率密度估计和阴影抑制的运动目标检测()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第31卷
期数:
2010年第1期
页码:
20-22
栏目:
出版日期:
2010-01-20

文章信息/Info

Title:
Kenel Density Estimation for Motion Detection and Shadow Suppression
文章编号:
1000-5013(2010)01-0020-03
作者:
张静; 陈锦春; 黄华灿
华侨大学信息科学与工程学院
Author(s):
ZHANG Jing;  CHEN Jin-chun;  HUANG Hua-can
College of Information Science and Engineering, Huaqiao University, Quanzhou 362021, China
关键词:
运动检测;  阴影抑制;  核密度估计;  色彩空间;  模式识别
Keywords:
motion detection;  shadow suppression;  kernel density estimation;  color space;  pattern recognition
分类号:
TP391.41
DOI:
10.11830/ISSN.1000-5013.2010.01.0020
文献标志码:
A
摘要:
采用核密度估计算法得到可靠背景,通过试验准确地分割出前景物体.利用最近的历史帧数据估计当前像素的概率密度,以适应不同的复杂背景场景.结合阴影抑制技术,通过HSV色彩的阴影抑制处理降低目标检测的虚警率,不仅减轻污染前景的程度,还能得到更加合理的背景模型和前景目标,提高运动目标检测的准确性和鲁棒性.
Abstract:
This paper proposed a method of kernel density estimation(KDE) to get reliable background,and extract foreground object accurately by the experiment.In order to improve adaptive ability for different backgrounds,historical pixels are used to estimate the probability density of current pixels.Combined with shadow suppression,Hue-Saturation-Value(HSV) color information is used to detect and suppress moving cast shadows.This not only alleviate the pollution of foreground,but also get more reasonable background model and foreground object,and improve the accuracy and robustness of motion detection.

参考文献/References:

[1] PAVLIDIS I, MORELLAS V, TSIAMYRTZIS P. Urban surveillance systems:From the laboratory to the commercialworld [J]. Proceedings of the IEEE, 2001, (10):1478-1497.doi:10.1109/5.959342.
[2] MEYER D, DENZLER J, NIEMANN H. Model based extraction of articulated objects in image sequences for gait analysis [J]. Pro IEEE International Conference on Image Processing, 1997, (26/29):78-81.
[3] TOYAMA K, KRUMM J, BRUMTT B. Wallflower:Principles and practice of background maintenance [A]. 1999.255-261.
[4] STAUFFER C, GRIMSON W E L. Learning patterns of activity using realtime tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000(8):747-757.doi:10.1109/34.868677.
[5] ELGAMMAL A M, HANVOOD D, DAVIS L S. Non-parametric model for background subtraction [M]. London:Springer-Verlag, 2000.751-767.
[6] 毛燕芬, 施鹏飞. 一种核密度估计动态场景建模算法 [J]. 数据采集与处理, 2004(2):391-394.doi:10.3969/j.issn.1004-9037.2004.04.007.
[7] 毛燕芬, 施鹏飞. 高斯核密度估计背景建模及噪声与阴影抑制 [J]. 系统仿真学报, 2005(5):1182-1184.doi:10.3969/j.issn.1004-731X.2005.05.041.

相似文献/References:

[1]陈柏生.HSV彩色空间的室内外运动人检测与阴影消除[J].华侨大学学报(自然科学版),2007,28(1):30.[doi:10.3969/j.issn.1000-5013.2007.01.009]
　CHEN Bai-sheng.Indoor and Outdoor People Detection and Shadow Elimination by Exploiting HSV Color Information[J].Journal of Huaqiao University(Natural Science),2007,28(1):30.[doi:10.3969/j.issn.1000-5013.2007.01.009]

备注/Memo

备注/Memo:
福建省科技计划项目(2006T006); 泉州市科技计划项目(2006G3)
更新日期/Last Update: 2014-03-23