1.College of Computer Science, Hangzhou Dianzi University, Hangzhou 3100182. College of Computer Science and Technology, Zhejiang University, Hangzhou 3100273. Department of Computer Science, Zhejiang Industry Polytechnic College, Shaoxing 312000
Abstract:Moving cast shadows are factors affecting segmentation quality. Efficient shadow detection and removal is a difficult problem in video segmentation. A method based on discriminative model for video foreground and shadow segmentation is proposed. It has capability of shadow detection and removal under different scenes. The proposed algorithm models background, shadows and foreground at pixel levels. These models are constrained by using 2-dimensional conditional random fields. Inference algorithm of probabilistic graphical models is adopted to obtain globally optimal segmentation results. The experimental results demonstrate the validity of the proposed algorithm, and the results are compared with other algorithms by using outdoor and indoor video data.
[1] Yang Tao, Li S Z, Pan Quan, et al. Real-Time and Accurate Segmentation of Moving Objects in Dynamic Scene // Proc of the 2nd ACM International Workshop on Video Surveillance and Sensor Networks. New York, USA, 2004: 136-143 [2] Stauffer C, Grimson W. Learning Patterns of Activity Using Real-Time Tracking. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000, 22(8): 747-757 [3] Stenger B, Ramesh V, Paragios N, et al. Topology Free Hidden Markov Models: Application to Background Modeling // Proc of the 8th IEEE International Conference on Computer Vision. Vancouver, Canada, 2001, Ⅰ: 294-301 [4] Martel-Brisson N, Zaccarin A. Moving Cast Shadow Detection from a Gaussian Mixture Shadow Model // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA, 2005, Ⅱ: 643-648 [5] Porikli F, Thornton J. Shadow Flow: A Recursive Method to Learn Moving Cast Shadows // Proc of the 10th IEEE International Conference on Computer Vision. Beijing, China, 2005, Ⅰ: 891-898 [6] Yoneyama A, Yeh C H, Kuo C C J. Moving Cast Shadow Elimination for Robust Vehicle Extraction Based on 2D Joint Vehicle/Shadow Models // Proc of the IEEE Conference on Advanced Video and Signal Based Surveillance. Miami, USA, 2003: 229-236 [7] Chen Baisheng, Lei Yunqi. Indoor and Outdoor People Detection and Shadow Suppression by Exploiting HSV Color Information // Proc of the 4th International Conference on Computer and Information Technology. Wuhan, China, 2004: 137-142 [8] Salvador E, Cavallaro A, Ebrahimi T. Cast Shadow Segmentation Using Invariant Color Features. Computer Vision and Image Understanding, 2004, 95(2): 238-259 [9] Zha Yufei, Chu Ying, Wang Xun, et al. A Boosting Discriminative Model for Moving Cast Shadow Detection. Chinese Journal of Computers, 2007, 30(8): 1295-1301 (in Chinese) (查宇飞,楚 瀛,王 勋,等. 一种基于Boosting判别模型的运动阴影检测方法.计算机学报, 2007, 30(8): 1295-1301) [10] Chu Yiping, Zhang Yin, Huang Yejue, et al. A Spatiotemporal Algorithm for Video Foreground and Shadow Segmentation. Pattern Recognition and Artificial Intelligence, 2008, 21(4): 546-551 (in Chinese) (褚一平,张 引,黄叶珏, 等.融合时空信息的前景/阴影视频分割算法.模式识别与人工智能, 2008, 21(4): 546-551) [11] Migdal J, Grimson E. Background Subtraction Using Markov Thresholds // Proc of the IEEE Workshop on Motion and Video Computing. Breckenridge, USA, 2005, Ⅱ: 58-65 [12] Zhou Yue, Gong Yihong, Tao Hai. Background Modeling Using Time Dependent Markov Random Field with Image Pyramid // Proc of the IEEE Workshop on Motion and Video Computing. Breckenridge, USA, 2005, Ⅱ: 8-13 [13] Elgammal A, Duraiswami R, Harwood D, et al. Background and Foreground Modeling Using Nonparametric Kernel Density Estimation for Visual Surveillance. Proc of the IEEE, 2002, 90(7): 1151-1163 [14] Chen Rui, Deng Yu, Xiang Shimin, et al. A Non-Parametric Foreground/Background Segmentation Method by Fusion of Intensity and Edge Feature. Journal of Computer-Aided Design & Computer Graphics, 2005, 17(6): 1278-1284 (in Chinese) (陈 睿,邓 宇,向世明,等.结合强度和边界信息的非参数前景/背景分割方法.计算机辅助设计与图形学学报, 2005, 17(6): 1278-1284) [15] Sheikh Y, Shah M. Bayesian Modeling of Dynamic Scenes for Object Detection. IEEE Trans on Pattern Analysis and Machine Intelligence, 2005, 27(11): 1778-1792 [16] Lafferty J, McCallum A, Pereira F. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data // Proc of the 18th International Conference on Machine Learning. Williams College, USA, 2001: 282-289 [17] Sha Fei, Pereira F. Shallow Parsing with Conditional Random Fields // Proc of the Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology. Edmonton, Canada, 2003: 134-141 [18] Kumar S, Hebert M. A Hierarchical Field Framework for Unified Context-Based Classification // Proc of the IEEE International Conference on Computer Vision. Beijing, China, 2005, Ⅱ: 1284-1291 [19] Wang Yang, Ji Qiang. A Dynamic Conditional Random Field Model for Object Segmentation in Image Sequences // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA, 2005, Ⅰ: 264-270 [20] Leone A, Distante C. Shadow Detection for Moving Objects Based on Texture Analysis. Pattern Recognition, 2007, 40(4): 1222-1233 [21] Yedidia J S, Freeman W T, Weiss Y. Understanding Belief Propagation and Its Generalizations // Lakemeyer G, Nebel B, eds. Exploring Artificial Intelligence in the New Millennium. San Francisco, USA: Morgan Kaufmann, 2003: 239-269 [22] Berthod M, Kato Z, Yu S, et al. Bayesian Image Classification Using Markov Random Fields. Image and Vision Computing, 1996, 14(4): 285-295