Background Modeling Adaptive to Outdoor IlluminationVariation and Foreground Detection Approach
-
摘要: 针对户外视频监控存在光照变化这一问题, 提出一个用于准确完成目标检测的实时背景建模框架. 考虑到目标检测的准确性要求, 建立基于帧间像素亮度差统计直方图的像素亮度扰动阈值. 在此基础上, 针对背景建模的实时性要求, 提出一种基于自回归背景模型的参数快速更新方法. 鉴于不同光照变化的适应性要求, 定义对光照变化不敏感的背景纹理模型. 上述模型统称为自回归--纹理 (Auto regression and texture, ART) 模型, 该模型适应于户外光照变化. 基于该模型构建像素亮度和纹理置信区间用于目标检测. 实验结果表明, 该框架能适应和实时跟踪户外背景的光照变化, 并对目标进行准确检测.Abstract: Considering the appearance of illumination variation in outdoor video surveillance, a real-time background modeling framework, which is also composed of accurate foreground detection, is established. In view of the accuracy of foreground detection, a threshold based on the histogram of pixel0s intensity difference between neighboring frames is proposed. On account of the real-time background modeling, a fast estimation approach on parameters of autoregressive model is presented. Considering the adaptability to variable illumination, a texture background model insensitive to outdoor illumination variation is designed. Thus, a uniform model named auto regression and texture (ART) is obtained. According to the established confidence intervals with perturbation of pixel's intensity and its local texture, foreground in scenes with different illumination variations is successfully detected. The experimental results indicate that the framework is adaptive to and can exactly track outdoor illumination variation in real time. Moreover, foreground detection is successfully accomplished.
-
[1] Takagi M, Shimoda H [Author], Sun Wei-Dong [Translator]. Handbook of Image Analysis. Beijing: Science Press, 2007(Takagi M, Shimoda H [著], 孙卫东 [译]. 图像处理技术手册. 北京: 科学出版社, 2007)[2] Stauffer C, Grimson W E L. Adaptive background mixture models for real-time tracking. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Fort Collins, USA: IEEE, 1999. 246-252[3] Elgammal A M, Harwood D, Davis L S. Non-parametric model for background substraction. In: Proceedings of the 6th European Conference on Computer Vision. London, UK: Springer-Verlag, 2000. 751-767[4] Elgammal A, Duraiswami R, Harwood D, Davis L S. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proceedings of IEEE, 2002, 90(7): 1151-1163[5] Parag T, Elgammal A, Mittal A. A framework for feature selection for background subtraction. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE, 2006. 1916-1923[6] Perez A, Larranaga P, Inza I. Bayesian classifiers based on kernel density estimation: flexible classifiers. International Journal of Approximate Reasoning, 2009, 50(2): 341-362[7] Banerjee A, Burlina P. Efficient particle filtering via sparse kernel density estimation. IEEE Transactions on Image Processing, 2010, 19(9): 2480-2490[8] Kristan M, Skocaj D, Leonardis A. Online kernel density estimation for interactive learning. Image and Vision Computing, 2010, 28(7): 1106-1116[9] Monnet A, Mittal A, Paragios N, Visvanathan R. Background modeling and subtraction of dynamic scenes. In: Proceedings of the 9th IEEE International Conference on Computer Vision. Washington D. C., USA: IEEE, 2003. 1305-1312[10] Bravo I, Mazo M, Lazaro J L, Gardel A, Jimenez P, Pizarro D. An intelligent architecture based on field programmable gate arrays designed to detect moving objects by using principal component analysis. Sensors, 2010, 10(10): 9232-9251[11] Guo L H, Li J H, Chen L Y, Yang S T. Gibbs distributions and Markov random field model: application on background modeling in video surveillance. In: Proceedings of the SPIE Real Time Imaging VIII. San Jose, USA: SPIE, 2004. 264-270[12] Xu Jian, Ding Xiao-Qing, Wang Sheng-Jin. Object occupancy probabilistic field based multi-view moving object detection and correspondence. Acta Automatica Sinica, 2008, 34(5): 609-612(徐剑, 丁晓青, 王生进. 基于目标存在概率场的多视角运动目标检测与对应算法. 自动化学报, 2008, 34(5): 609-612)[13] Hwang Y, Kim J S, Kweon I S. Change detection using a statistical model in an optimally selected color space. Computer Vision and Image Understanding, 2008, 122(3): 231-242[14] Chang M C, Cheng Y J. Motion detection by using entropy image and adaptive state-labeling technique. In: Proceedings of the IEEE International Symposium on Circuits and Systems. New Orleans, USA: IEEE, 2007. 3667-3670[15] Liu Peng, Xu Jing, Liu Jia-Feng, Tang Xiang-Long. An algorithm for real-time analysis of rain-affected videos. Acta Automatica Sinica, 2010, 36(10): 1371-1378(刘鹏, 徐晶, 刘家锋, 唐降龙. 一种受雨滴污染视频的快速分析方法. 自动化学报, 2010, 36(10): 1371-1378)[16] Li L Y, Huang W M, Gu I Y H, Tian Q. Statistical modeling of complex backgrounds for foreground object detection. IEEE Transactions on Image Processing, 2004, 13(11): 1459-1472[17] Kim K, Chalidabhongse T H, Harwood D, Davis L. Background modeling and subtraction by codebook construction. In: Proceedings of the IEEE International Conference on Image Processing. Washington D. C., USA: IEEE, 2004. 3061-3064[18] Culibrk D, Marques O, Socke D, Kalva H, Furht B. Neural network approach to background modeling for video object segmentation. IEEE Transactions on Neural Networks, 2007, 18(11): 1614-1627[19] Xu Jian, Ding Xiao-Qing, Wang Sheng-Jin, Wu You-Shou. Background subtraction based on a combination of local texture and color. Acta Automatica Sinica, 2009, 35(9): 1145-1150(徐剑, 丁晓青, 王生进, 吴佑寿. 一种融合局部纹理和颜色信息的背景减除方法. 自动化学报, 2009, 35(9): 1145-1150)[20] Toyama K, Krumm J, Brumitt B, Meyers B. Wallflower: principles and practice of background maintenance. In: Proceedings of the 7th IEEE International Conference on Computer Vision. Washington D. C., USA: IEEE, 1999. 256-261[21] Tian Y L, Lu M, Hampapur A. Robust and efficient foreground analysis for real-time video surveillance. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE, 2005. 1182-1187[22] Heikkil M, Pietikainen M. A texture-based method for modeling the background and detecting moving objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(4): 657-662[23] Manzanera A, Richefeu J C. A new motion detection algorithm based on Σ -Δ background estimation. Pattern Recognition Letters, 2007, 28(3): 320-328[24] Fan Jian-Qing, Yao Qi-Wei [Author], Chen Min [Translator]. Non-linear Time Series: Nonparametric and Parametric Methods. Beijing: Higher Education Press, 2005(范剑青, 姚琦伟 [著], 陈敏 [译]. 非线性时间序列: 建模、预报及应用. 北京: 高等教育出版社, 2005)
点击查看大图
计量
- 文章访问数: 2133
- HTML全文浏览量: 62
- PDF下载量: 1360
- 被引次数: 0