基于加权核密度估计的自适应运动前景检测方法

蒋鹏; 金炜东

doi:10.3969/j.issn.0258-2724.2012.05.007

基于加权核密度估计的自适应运动前景检测方法

doi: 10.3969/j.issn.0258-2724.2012.05.007

蒋鹏,
金炜东

基金项目:

国家自然科学基金资助项目(61134002)

中央高校基本科研业务费专项资金资助项目(SWJTU12CX027)

计量
- 文章访问数: 1136
- HTML全文浏览量: 71
- PDF下载量: 441
- 被引次数: 0
出版历程
- 收稿日期: 2012-03-07
- 刊出日期: 2012-10-25

Adaptive Foreground Detection Based on Weighted Kernel Density Estimation

摘要

摘要: 为解决监控视频背景初始化过程中前景干扰的问题,提出了一种基于加权核密度估计(KDE)的自适应运动前景检测方法.该方法对时间域变化稳定的像素值进行加权,并利用核密度估计构建背景模型,避免了背景初始化过程中前景的干扰.基于该背景模型,提出了一种新的阈值设定策略.该策略根据前景空间分布的连续性自适应获得前景阈值,填充前景中的"孔",并更新阈值.实验结果表明:即使场景中存在运动前景,该方法能够在多种场景下获得90%以上的查准率和查全率,其性能优于传统的背景差法.
- 背景差 /
- 加权核密度估计 /
- 自适应阈值
Abstract: In order to avoid the impacts of moving foreground on background modeling in training stage, an adaptive foreground detection method based on weighted kernel density estimation (KDE) was proposed. In this method, temporal stable pixels are assigned more weights, and a weighted KDE background model is established to reduce the interference of foreground during background model building. Based on this background model, a strategy for dynamic foreground threshold was proposed. With the spatial consistency of foreground, "holes" in foreground are filled and thresholds are updated in the same time. The experimental results show that the proposed foreground detection method is able to achieve over 90% precise and recall rates in various scenes even under the condition that there are moving objects, and it outperforms the conventional background subtraction methods.
- background subtraction /
- weighted kernel density estimation /
- adaptive threshold

HTML全文

参考文献(15)

FRIEDMAN N, RUSSELL S. Image segmentation in video sequences: a probabilistic approach//Proceedings of Thirteenth Conference on Uncertainty in Artificial Intelligence. Providence: Morgan Kaufmann Publishers, 1997: 175-181.

彭强,李华. 基于块直方图分析的视频背景提取方法[J]. 西南交通大学学报,2006,41(1): 48-53. PENG Qiang, LI Hua. Background extraction method based on block histogram analysis for video images[J]. Journal of Southwest Jiaotong University, 2006, 41(1): 48-53.

侯志强,韩崇昭. 基于像素灰度归类的背景重构算法[J]. 软件学报,2005,16(9): 1568-1576. HOU Zhiqiang, HAN Chongzhao. A background reconstruction algorithm based on pixel intensity classification[J]. Journal of Software, 2005, 16(9): 1568-1576.

LEE D S. Effective Gaussian mixture learning for video background subtraction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(5): 827-832.

CHAN A B, MAHADEVAN V. Generalized Stauffer Grimson background subtraction for dynamic scenes[J]. Machine Vision and Applications, 2011, 22(5): 751-766.

ELGAMMAL A, DURAISWAMI R, HARWOOD D, et al. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance[J]. Proceedings of IEEE, 2002, 90(7): 1151-1163.

MITTAL A, PARAGIOS N. Motion-based background subtraction using adaptive kernel density estimation//Proc. Int'l Conf. Computer Vision and Pattern Recognition. Washington: [s.n.], 2004: 302-309.

KIM W, KIM C. Background subtraction for dynamic texture scenes using fuzzy color histograms[J]. IEEE Signal Processing Letters, 2012, 19(3): 127-130.

MANDELLOS N A, KERAMITSOGLOU I. A background subtraction algorithm for detecting and tracking vehicles[J]. Expert Systems with Applications, 2011, 38(3): 1619-1631.

SHEATHER S J, JONES M C. A reliable data-based bandwidth selection method for kernel density estimation[J]. Journal of the Royal Statistical Society Series B, 1991, 53(3): 683-690.

蒋鹏,秦小麟. 复杂背景下的自适应前景分割算法[J]. 中国图象图形学报,2011,16(1): 37-43. JIANG Peng, QIN Xiaolin. Robust foreground detection with adaptive threshold estimation[J]. Journal of Image and Graphics, 2011, 16(1): 37-43.

蒋鹏,秦小麟. 利用背景聚类的快速前景分割算法[J]. 中国图象图形学报,2010,15(12): 1790-1795. JIANG Peng, QIN Xiaolin. Foreground detection based on unsupervised background clustering[J]. Journal of Image and Graphics, 2010, 15(12): 1790-1795.

MARIE R, POTELLE A, MOUADDIB E M. Dynamic background subtraction using moments//2011 18th IEEE International Conference on Image Processing (ICIP). Amiens: [s.n.], 2011: 2369-2372.

WANG S C, SU Tefeng, LAI Shanghong. Detecting moving objects from dynamic background with shadow removal//2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). [s.l.]: IEEE, 2011: 925-928.

MADDALENA L, PETROSINO A. A self-organizing approach to background subtraction for visual surveillance applications[J]. IEEE Tran. Image Processing, 2008, 17(7): 1168-1177.

施引文献

附加材料(0)

访问统计

点击查看大图

计量

文章访问数: 1136
HTML全文浏览量: 71
PDF下载量: 441
被引次数: 0

基于加权核密度估计的自适应运动前景检测方法

doi: 10.3969/j.issn.0258-2724.2012.05.007

计量

出版历程

Adaptive Foreground Detection Based on Weighted Kernel Density Estimation

计量

出版历程

目录