南京大学学报(自然科学版) ›› 2015, Vol. 51 ›› Issue (2): 219226.
廖 娟 1* , 王 江 1 , 徐 亮 2 , 李 勃 1 , 陈启美 1
Liao Juan,Wang Jiang, Li Bo, Chen Qimei
摘要: 前景检测是视频监控中信息提取的关键,而相机抖动造成背景边缘的像素极易误检为前景像素,降低前景检测的精确度.为此,文中提出相机抖动场景下一种基于运动信息的前景检测算法:分析二值图像中候选前景点的运动信息,构建非参数的背景运动信息分布模型;计算候选前景的运动信息与背景模型的概率似然性,由自适应的阈值控制来确定真实前景,该自适应阈值由Mean-shift及信息熵算法共同确定,可以克服单个的全局阈值对场景变化适应能力差问题;针对检测到的前景点和背景点的运动信息,采用首进首出的策略更新背景运动信息分布模型,提高模型对场景实时变化的适应性.实验结果表明,该算法具有良好的鲁棒性,能有效地检测相机抖动场景下的运动前景.
[1] Brahme Y B,Kulkarni P S. An implementation of moving object detection, tracking and counting objects for traffic surveillance system.International Conference on Computational Intelligence and Communication Systems, 2011: 143-148. [2] 高凯亮,覃团发,陈跃波等. 一种混合高斯背景模型下的像素分类运动目标检测方法.南京大学学报(自然科学),2011,47(2) : 195-200. [3] 徐东彬,黄 磊,刘昌平.自适应核密度估计运动检测方法.自动化学报, 2009,35(4):379-385. [4] Goyette N, Jodoin P M, Porikli F, et al. Changedetection.net: a new change detection benchmark dataset.IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2012: 1-8. [5] Stauffer C, Grimson W E L. Learning patterns of activity using real-time tracking. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000, 22(8): 747-757. [6] Zivkovic Z, van der Heijden F. Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recognition Letters, 2006: 773-780. [7] Elgammal A, Harwood D, Davis L. Non-parametric model for background subtraction. IEEE European Conference on Computer Vision, 2000:751-767 [8] Maddalena L, Petrosino A. A self-organizing approach to background subtraction for visual surveillance applications. IEEE Trans on Image Processing, 2008, 17(7): 1168-1177. [9] Barnich O, Droogenbroeck M V. ViBe: A universal background subtraction algorithm for video sequences. IEEE Trans on Image Processing, 2011, 20(6): 1709-1724. [10] Jodoin P M, Konrad J, Saligrama V, et al. Motion detection with an unstable camera. IEEE International Conference Image Process, 2008: 229-232. [11] Liao Juan, Dong Rong, Li Bo, et al. A non-parametric motion model for foreground detection in camera jitter scenes. IEEE Signal Processing Letters, 2014, 21(6): 677-681. [12] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis. IEEE Trans on Pattern Recognition and Machine Learning, 2002, 24(5): 603-619. [13] 1st IEEE Change Detection Workshop. Change Detection.net Video Database[OL].2012-10. |
No related articles found! |
|