臺灣博碩士論文加值系統

This thesis presents an effective multi-layer background modelingmethod to detect moving objects by exploiting the advantage of distinctive features and hierarchical structure of the Codebook (CB) model. In the process, two image features are involved, namely the mean RGB feature and the Binary Ordered Dithering (BOD) feature.The mean RGB feature is one of the most fundamental features employed in moving-object detection applications. However, in the block-based structure, the mean-color feature within a block often does not contain sufficient texture information, causing incorrect classification especially in large block size layers.Conversely, binary bitmap generated from the Ordered Dithering (OD) is a more effective candidate for the estimation of texture information within individual blocks. Thus, the BOD feature becomes an important supplement to the mean RGB feature for the formation of a novel discriminative feature in a block-based object detection system. The background model described in this thesis consists of four layers, which can be categorized into three block-based layers and onepixel-based layer. The block-based layers are employed for the efficient removal the background, and the pixel-based layer is for foreground refinement. To further improve the detection results, several additional steps are included, such as the shadow and highlight removal for the identification of the true foreground. Moreover, the Long-term Stationary Foreground Removal (LSFR) method is employed for the determination of the stationary foreground. And the Isolated False Positive Foreground Removal (IFPFR) technique is used for the removal of the isolated foreground pixel to improve the final detected result. In summary, the uniqueness of this approach is the incorporation of the halftoningscheme with the codebook model for superior performance over the existing methods

This thesis presents an effective multi-layer background modelingmethod to detect moving objects by exploiting the advantage of distinctive features and hierarchical structure of the Codebook (CB) model. In the process, two image features are involved, namely the mean RGB feature and the Binary Ordered Dithering (BOD) feature.The mean RGB feature is one of the most fundamental features employed in moving-object detection applications. However, in the block-based structure, the mean-color feature within a block often does not contain sufficient texture information, causing incorrect classification especially in large block size layers.Conversely, binary bitmap generated from the Ordered Dithering (OD) is a more effective candidate for the estimation of texture information within individual blocks. Thus, the BOD feature becomes an important supplement to the mean RGB feature for the formation of a novel discriminative feature in a block-based object detection system. The background model described in this thesis consists of four layers, which can be categorized into three block-based layers and onepixel-based layer. The block-based layers are employed for the efficient removal the background, and the pixel-based layer is for foreground refinement. To further improve the detection results, several additional steps are included, such as the shadow and highlight removal for the identification of the true foreground. Moreover, the Long-term Stationary Foreground Removal (LSFR) method is employed for the determination of the stationary foreground. And the Isolated False Positive Foreground Removal (IFPFR) technique is used for the removal of the isolated foreground pixel to improve the final detected result. In summary, the uniqueness of this approach is the incorporation of the halftoningscheme with the codebook model for superior performance over the existing methods

ABSTRACT ii
ACKNOWLEDGEMENTS iii
TABLE OF CONTENTS iv
LIST OF FIGURES vi
LIST OF TABLES vii
CHAPTER 1 1
INTRODUCTION 1
1.1 Motivation and Problem Statement 1
1.2 Literature Reviews 3
1.3 Proposed Solution 6
1.4 Organization of Thesis 7
CHAPTER 2 8
MULTILAYER BACKGROUND MODEL CONSTRUCTION 8
2.1 Features Extraction 10
2.1.1 Mean Color Feature (mean RGB feature) 11
2.1.2. Binary Ordered Dithering Feature (BOD feature) 12
2.2 Background Model Construction 15
CHAPTER 3: 21
MOVING OBJECT DETECTION BASED ON MULTILAYER BACKGROUND SUBTRACTION 21
3.1 Moving Object Detection with Block-based Codebook 22
3.2. Moving Object Detection with Pixel-based Codebook. 24
CHAPTER 4: 26
ADDITIONAL PROCEDURES TO REFINE DETECTED RESULTS. 26
4.1 Shadow and Highlight Removal 26
4.2 Long-term Stationary Foreground Removal (LSFR) 29
4.3 Isolated False Positive Foreground Removal (IFPFR) 31
CHAPTER 5: 33
EXPERIMENTAL RESULTS 33
5.1 Experimental Setups 33
5.2 Experimental Results Visualization: 34
5.2.1 Feature Extraction 34
5.2.2 Shadow and Highlight Removal 35
5.2.3 Isolated Pixel Foreground Removal 36
5.3 Performance Comparisons 37
5.3.1 Performance Comparison to Former Codebook-based Moving Object Detection 37
5.3.2 Performance Comparison to State-of-the-art Moving Object Detection Approaches. 41
CHAPTER 6: 47
CONCLUSIONS AND DISCUSSIONS 47
LIST OF REFERENCES: 48

[1] A. Elgammal, D.Harwood, L.S. Davis, “Non-parametric model for background subtraction,”in: Proceedings of European Conference on Computer Vision, 2000, pp. 751-767.
[2] N. Martel-Brisson, A. Zaccarim, “Moving cast shadow detection from a Gaussian mixture shadow model,”in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2005, pp. 643-648.
[3] L. Li, W. Huang, I. Y. H. Gu, Q. Tian, “Statistical modeling of complex backgrounds for foreground object detection,”IEEE Trans. Image Processing, 2004, pp. 1459-1472.
[4] K. Toyama, J. Krumm, B. Brumitt, B. Meyers, Wallflower: “Principles and practice of background maintenance,” in: Proceedings of International Conference on Computer Vision, 1999, pp. 255-261.
[5] T. Horprasert, D. Harwood, L.S Davis, “A statistical approach for real-time robust background subtraction and shadow detection,”in: Proceedings of IEEE ICCV Frame-Rate Workshop, 1999, pp. 1-19.
[6]E. J. Carmona, J. Martinez-Cantos, and J. Mira, “A new video segmentation method of moving objects based on blob-level knowledge,” Pattern Recognit.Lett, 2008, pp. 272–285.
[7]R. Cucchiara, C. Grana, M. Piccardi, A. Prati, and S. Sirotti, “Improving shadow suppression in moving object detection with HSV color information,”in Proc. IEEE Conf. Intell. Transportation Syst., Aug. 2001,pp. 334–339.
[8]R. Cucchiara, C. Grana, M. Piccardi, and A. Prati, “Detection moving objects, ghosts, and shadows in video streams,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, no. 10, pp. 1337–1342, Oct. 2003.
[9]M. Izadi and P. Saeedi, “Robust region-based background subtraction and shadow removing using color and gradient information,” in Proc. Int. Conf. Pattern Recognit., Dec. 2008, pp. 1–5.
[10]M. Shoaib, R. Dragon, and J. Ostermann, “Shadow detection for moving humans using gradient-based background subtraction,” in Proc. IEEE Int. Conf. Acoust. Speech Signal Process., Apr. 2009, no. 4959698, pp. 773–776.
[11]C. Stauffer and W. E. L. Grimson, “Adaptive background mixture models for real-time tracking,” in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2. Jun. 1999, pp. 246–252.
[12]C. Benedek and T. Sziranyi, “Bayesian foreground and shadow detection in uncertain frame rate surveillance videos,” IEEE Trans. Image Process., vol. 17, no. 4, pp. 608–621, Apr. 2008.
[13]J.-S. Hu and T.-M. Su, “Robust background subtraction with shadow and highlight removal for indoor surveillance,” EURASIP J. Adv. Signal Process., vol. 2007, no. 1, pp. 1–14, Jan. 2007.
[14]G. Xue, J. Sun, and L. Song, “Background subtraction based on phase and distance transform under sudden illumination change,” in Proc. IEEE Int. Conf. Image Process., Sep. 2010, pp. 3465–3468.
[15]Y.-T. Chen, C.-S. Chen, C.-R. Huang, and Y.-P. Hung, “Efficient hierarchical method for background subtraction,” Pattern Recognit., vol. 40, no. 10, pp. 2706–2715, Oct. 2007.
[16] K. Kim, T. H. Chalidabhongse, D. Harwood, and L. Davis, “Real-time foreground-background segmentation using codebook model,”Real-Time Image, vol. 11, no. 3, pp. 172-185, Jun. 2005
[17] M. Wu and X. Peng, “Spatio-temporal context for codebook-based dynamic background subtraction,”AEU – Int. J. Electron. Commun., vol. 64, no. 8, pp. 739-747, Aug. 2010
[18] J.-M. Guo, Y.-F. Liu, C.-H. Hsia, M.-H. Shih, and C.-S.Hsu, “Hierarchical method for foreground detection using codebook model,” IEEE Trans. Circuits Syst. Video Technol., vol. 21, no. 6, pp. 804-815, Jun. 2011
[19] M. Heikkila and M. Pietikainen, “A texture-based method for modeling the background and detecting moving object,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 28, no. 4, pp. 657-662, Apr. 2006
[20] J.-M Guo, C.-H Hsia, Y.-F. Liu, M.-H. Shih, C.-H. Chang, and J.-Y. Wu, “Fast Background Subtraction Based on a Multilayer Codebook Model for Moving Object Detection”, IEEE Trans. Circuits SYst. Video Technol, vol. 23, no. 10, Oct. 2013
[21] E. J. Carmona, J. Martinez-Cantos, and J. Mira, “A new video segmentation method of moving objects based on blob-level knowledge,” Pattern Recognit. Lett., vo. 29, no. 3, pp. 272-285, Feb. 2008.
[22] Statistical Modeling of Complex Background for Foreground Object Detection.[Online]. Available: http://perception.i2r.a-star.edu.sg/bk_model/bk_index.html
[23] Performance Evaluation of Surveillance System. [Online].Available: http://www.research.ibm.com/peoplevision/performanceevaluation.html.
[24] Shadow Detection. [Online]. Available : http://cvrr.ucsd.edu/aton/shadow/index.html
[25]A change Detection Benchmark Dataset. [Online]. Available:http://www.changedetection.net
[26] M. Hofmann, P.Tiefenbacher, G. Rigoll "Background Segmentation with Feedback: The Pixel-Based Adaptive Segmenter", in proc of IEEE Workshop on Change Detection, 2012
[27] A. Schick, M.Bauml, R.Stiefelhagen "Improving Foreground Segmentations with Probabilistic Superpixel Markov Random Fields", in proc of IEEE Workshop on Change Detection, 2012
[28] L. Maddalena, A. Petrosino, "The SOBS algorithm: what are the limits?",in proc of IEEE Workshop on Change Detection, CVPR 2012
[29] A. Morde, X. Ma, S. Guler [IntuVision] "Learning a background model for change detection", in proc of IEEE Workshop on Change Detection, 2012
[30] HerasEvangelio, R. and Patzold, M. and Sikora, T. "Splitting Gaussians in Mixture Models", Proceedings of the 9th IEEE International Conference on Advanced Video and Signal-Based Surveillance, 2012
[31]Z. Zivkovic , F. van der Heijden, “Efficient adaptive density estimation per image pixel for the task of background subtraction" Pattern Recognition Letters, vol. 27, no. 7, pages 773-780, 2006
[32] L. Maddalena, A. Petrosino, “A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications,” IEEE Transactions on Image Processing, Vol. 17, no.7, 2008, p1168-1177
[33] Y.Nonaka, A. Shimada, H.Nagahara, R. Taniguchi "Evaluation Report of Integrated Background Modeling Based on Spatio-temporal Features", in proc of IEEE Workshop on Change Detection, 2012
[34] A. Elgammal, D. Harwood, and L. Davis, "Non-parametric model for background subtraction," in Proc. Eur. Conf. on Computer Vision, Lect. Notes Comput. Sci. 1843, 751-767 2000.
[35]M. Van Droogenbroeckand O. Barnich. “ViBe: A Disruptive Method for Background Subtraction.” In T. Bouwmans, F. Porikli, B. Hoferlin, and A. Vacavant, editors, Background Modeling and Foreground Detection for Video Surveillance, chapter 7. Chapman and Hall/CRC, June 2014
[36] P. KaewTraKulPong and R. Bowden, "An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection", in proc of Workshop on Advanced Video Based Surveillance Systems, 2001
[37] SatoshiYoshinaga, Atsushi Shimada, Hajime Nagahara, Rin-ichiro Taniguchi, “Background Model Based on Intensity Change Similarity Among Pixels,”the 19th Japan-Korea Joint Workshop on Frontiers of Computer Vision, pp.276-280, 2013.01
[38] F. Porikli and O. Tuzel. "Bayesian background modeling for foreground detection" in proc. of ACM Visual Surveillance and Sensor Network, 2005.
[39]Riahi, D., St-Onge, P.L., Bilodeau, G.A. (2012). RECTGAUSS-Tex: “Block-based Background Subtraction,”Technical Report, EcolePolytechnique de Montreal, EPM-RT-2012-03
[40] Z. Zivkovic, "Improved adaptive Gaussian mixture model for back-ground subtraction," in Proc. Int. Conf. Pattern Recognition, pp. 28-31, IEEE, Piscataway, NJ 2004
[41] J-P Jodoin, G-A Bilodeau, N Saunier "Background subtraction based on Local Shape", arXiv:1204.6326v1
[42] Y. Benezeth, P.-M. Jodoin, B. Emile, H. Laurent, and C. Rosenberger. “Comparative study of background subtraction algorithms”.J. of Elec. Imaging, 19(3):1–12, 2010.