Abstract In the algorithm of self-organizing background subtraction, the real-time performance is poor and the background model is easy to offset under complicated environment due to non-periodic changes. Aiming at these problems, a hierarchical algorithm of self-organizing background subtraction with memory storage is proposed. Firstly, a border-shared background model is established to reduce the time and space complexity. And a cache strategy is introduced on the basis of the original matrix model to store the past and the current background data, respectively. Then, during the object detection, a decision mechanism for different granularity levels is designed to determine whether a pixel is an object or not. Experimental results show that the proposed algorithm can overcome the shortcomings of the original one and achieve higher detection accuracy and better real-time performance.
Fund:Supported by National Natural Science Foundation of China (No.61502105,61473089)
About author:: (LIN Dewei, born in 1990, master student. His research inte-rests include image processing.) (CHEN Zhaojiong(Corresponding author), born in 1964, master, professor. Her research interests include intelligent image processing and computational intelligence.) (KE Xiao, born in 1983, Ph.D., lecturer. His research interests include pattern recognition, image processing, computer vision and machine learning.) (YE Dongyi, born in 1964, Ph.D., professor. His research interests include computational intelligence and data mining.)
[1] 黄凯奇,陈晓棠,康运锋,等.智能视频监控技术综述.计算机学报, 2015, 38(6): 1093-1118. (HUANG K Q, CHEN X T, KANG Y F, et al. Intelligent Visual Surveillance: A Review. Chinese Journal of Computers, 2015, 38(6): 1093-1118.) [2] 王 欢,任明武,杨静宇.一种区域级运动目标检测方法.模式识别与人工智能, 2009, 22(5): 689-696. (WANG H, REN M Y, YANG J Y. A Region-Level Moving Object Detection Method. Pattern Recognition and Artificial Intelligence, 2009, 22(5): 689-696.) [3] STAUFFER C, GRIMSON W E L. Adaptive Background Mixture Models for Real-Time Tracking // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 1999, II: 246-252. [4] ZHU Q S, SONG Z, XIE Y Q. An Efficient r-KDE Model for the Segmentation of Dynamic Scenes // Proc of the 21st International Conference on Pattern Recognition. New York, USA: IEEE, 2012: 198-201. [5] LEE D S. Effective Gaussian Mixture Learning for Video Background Subtraction. IEEE Trans on Pattern Analysis and Machine Intelligence, 2005, 27(5): 827-832. [6] ZHANG Q, KLETTE R. Robust Background Subtraction and Maintenance // Proc of the 17th International Conference on Pattern Recognition. New York, USA: IEEE, 2004, II: 90-93. [7] BARNICH O, VAN DROOGENBROECK M. ViBe: A Universal Background Subtraction Algorithm for Video Sequence. IEEE Trans on Image Processing, 2011, 20(6): 1709-1724. [8] VAN DROOGENBROECK M, PAQUOT O. Background Subtraction: Experiments and Improvements for ViBe // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. New York, USA: IEEE, 2012: 32-37. [9] KIM K, CHALIDABHONGSE T H, HARWOOD D, et al. Real-Time Foreground-Background Segmentation Using Codebook Model. Real-Time Imaging, 2005, 11(3): 172-185. [10] 肖 梅,韩崇昭.基于在线聚类的背景减法.模式识别与人工智能, 2007, 20(1): 35-41. (XIAO M, HAN C Z. Background Subtraction Algorithm Based on Online Clustering. Pattern Recognition and Artificial Intelligence, 2007, 20(1): 35-41.) [11] 陈 容,彭 力.基于视觉记忆模型聚类的运动目标检测.计算机工程与应用, 2015, 51(13): 172-175. (CHEN R, PENG L. Moving Target Detection Based on Visual Memory Model and Clustering. Computer Engineering and Applications, 2015, 51(13): 172-175.) [12] 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. [13] MADDALENA L, PETROSINO A. The SOBS Algorithm: What Are the Limits? // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. New York, USA: IEEE, 2012: 21-26.
2016, Vol. 29 
