臺灣博碩士論文加值系統

本文提出一種新的方法，適應於區域迭代移動量變化分析之局部背景更新方法。此方法合併兩種技術，分別是利用幀差法做移動向量估計和建立背景模組，該方法能夠容忍大量的動態背景，比如說樹上的葉子晃動或水面上的漣漪甚至持續運作的噴水池。在背景模組中，將會根據每個局部區域的運動情形以不同的速度更新，因此在較複雜的區域將會較頻繁的進行背景模組更新。當移動物體出現時，將可以在連續的幀中觀察到各個局部區域的迭代情形，因此，在每張幀中每個移動物體的運動變化是可以被統計出來的，並且各個區域的更新速度是可以有相對應的調整。實驗結果表示，此方法對於動態背景的情境是可以有很好的表現，因此，此方法有效地改善傳統的背景模組的更新方法。

This thesis presents a novel method for adaptive and iterative updating of background modeling based on local area motion variation analysis. The proposed method involves combining two processes, namely motion vector estimation using frame differences and background modeling. The proposed method allows for a substantial amount of dynamic variation, such as the moving leaves of a tree, ripples on a water surface, and fountains spraying water, in constructing the background. The background is updated at various speeds, depending on the motion conditions in each region; a complex region is adapted by frequently updating the background information. The situation of moving objects can be observed and analyzed iteratively in a few consecutive frames; therefore, the motion variation of each moving object in every region of the frame can be determined and the updating speed of that region can be adjusted accordingly. Experimental results demonstrate that the proposed scheme outperforms the related approach for the dynamic background scenarios dataset. Thus, the proposed method improves the efficiency of traditional updating processes applied in background modeling.

Abstract
Contents
1 Introduction
1.1 Motivation
1.2 Objective
1.3 Thesis Organization
2 Literature Survey
3 Description of the proposed Approach
3.1 System overview
3.2 Motion Detection Algorithm
3.2.1 Principles of local area search and matching
3.2.2 Three-Step Algorithm
3.3 The Background Subtraction with Sigma-Delta Background Estimation
3.3.1 Sigma-delta background estimation
3.3.2 Sigma-delta background, foreground threshold and background subtraction
3.4 Combination of Motion Detection and Background Subtraction
3.4.1 Analysis of the local area iterative image
3.4.2 Local area background and threshold updating
3.4.3 Background subtraction
4 Experimental Results and Performance Comparison
4.1 Discussion of the Parameter T’
4.2 Experimental Results and Performance Comparison
5 Conclusion and Future work

[1] Olivier Barnich and Marc Van Droogenbroeck. Vibe: A universal background subtraction
algorithm for video sequences. IEEE Transactions on Image Processing, 20(6):
1709–1724, 2011.
[2] IEEE Change Detection Workshop in conjunction with CVPR. www.changedetection.
net.
[3] Arun Hampapur, Lisa Brown, Jonathan Connell, Sharat Pankanti, Andrew Senior, and
Yingli Tian. Smart surveillance: applications, technologies and implications. Information,
Communications and Signal Processing, 2:1133–1138, 2003.
[4] V Kastrinaki, M Zervakis, and Kostas Kalaitzakis. A survey of video processing techniques
for traffic applications. Image and vision computing, 21(4):359–381, 2003.
[5] Ji Tao, Mukherjee Turjo, Mun-Fei Wong, Mengdi Wang, and Yap-Peng Tan. Fall
incidents detection for intelligent video surveillance. In Fifth International Conference
on Information, Communications and Signal Processing, pages 1590–1594. IEEE, 2005.
[6] Fredrik Nilsson et al. Intelligent network video: Understanding modern video surveillance
systems. CRC Press, Inc., 2013.
[7] Hongpeng Yin, Yi Chai, Simon X Yang, and Xiaoyan Yang. Fast-moving target tracking
based on mean shift and frame-difference methods. Journal of Systems Engineering and
Electronics, 22(4):587–592, 2011.
[8] Antonio Fernández-Caballero, José Carlos Castillo, Javier Martínez-Cantos, and Rafael
Martínez-Tomás. Optical flow or image subtraction in human detection from infrared
camera on mobile robot. Robotics and Autonomous Systems, 58(12):1273–1281, 2010.
[9] Caroline Rougier, Jean Meunier, Alain St-Arnaud, and Jacqueline Rousseau. Fall detection
from human shape and motion history using video surveillance. In AINAW’07.
21st International Conference on Advanced Information Networking and Applications
Workshops, volume 2, pages 875–880. IEEE, 2007.
[10] Berthold K Horn and Brian G Schunck. Determining optical flow. In Technical Symposium
East, pages 319–331. International Society for Optics and Photonics, 1981.
[11] Hyungkwan Son and Suyoung Chi. Moving user segmentation for sports simulator using
frame difference and edge detection. 2013.
[12] Mark Monmonier. Spying with maps: Surveillance technologies and the future of privacy.
University of Chicago Press, 2004.
[13] Massimo Piccardi. Background subtraction techniques: a review. In IEEE international
conference on Systems, man and cybernetics, volume 4, pages 3099–3104. IEEE, 2004.
[14] Pierre-Luc St-Charles, Guillaume-Alexandre Bilodeau, and Robert Bergevin. Flexible
background subtraction with self-balanced local sensitivity.
[15] Bin Wang and Piotr Dudek. A fast self-tuning background subtraction algorithm. In
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops,
pages 395–398, 2014.
[16] Shu-Te Su and Yung-Yaw Chen. Moving object segmentation using improved running
gaussian average background model. In Digital Image Computing: Techniques and
Applications (DICTA), pages 24–31. IEEE, 2008.
[17] Chris Stauffer and W Eric L Grimson. Adaptive background mixture models for realtime
tracking. In IEEE Computer Society Conference on Computer Vision and Pattern
Recognition, volume 2. IEEE, 1999.
[18] Ahmed Elgammal, David Harwood, and Larry Davis. Non-parametric model for background
subtraction. In Computer Vision—ECCV, pages 751–767. Springer, 2000.
[19] X Zhao, P Liu, J Liu, and X Tang. Background subtraction using semantic-based
hierarchical gmm. Electronics letters, 48(14):825–827, 2012.
[20] Lucia Maddalena and Alfredo Petrosino. The sobs algorithm: what are the limits?
In IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Workshops (CVPRW), pages 21–26. IEEE, 2012.
[21] Massimo Gregorio and Maurizio Giordano. Change detection with weightless neural
networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern
Recognition Workshops, pages 403–407, 2014.
[22] Antoine Manzanera and Julien C Richefeu. A new motion detection algorithm based
on< i> –< i>  background estimation. Pattern Recognition Letters, 28(3):
320–328, 2007.
[23] Daw-tung Lin and Yi-Shun Kao. Real-time non-background motion-based object detection
in dsp implementation and application for people counting. National Taipei
University of Electrical Engineering Dissertation, pages 1–61, 2010.
[24] NGN Prasad and JNK Rao. The estimation of the mean squared error of small-area
estimators. Journal of the American statistical association, 85(409):163–171, 1990.
[25] Yariv Ephraim and David Malah. Speech enhancement using a minimum-mean square
error short-time spectral amplitude estimator. IEEE Transactions on Acoustics, Speech
and Signal Processing, 32(6):1109–1121, 1984.
[26] Renxiang Li, Bing Zeng, and Ming L Liou. A new three-step search algorithm for block
motion estimation. IEEE Transactions on Circuits and Systems for Video Technology,
4(4):438–442, 1994.
[27] Shan Zhu and Kai-Kuang Ma. A new diamond search algorithm for fast block-matching
motion estimation. IEEE Transactions on Image Processing, 9(2):287–290, 2000.
[28] Lai-Man Po and Wing-Chung Ma. A novel four-step search algorithm for fast block
motion estimation. IEEE Transactions on Circuits and Systems for Video Technology,
6(3):313–317, 1996.
[29] Lurng-Kuo Liu and Ephraim Feig. A block-based gradient descent search algorithm for
block motion estimation in video coding. IEEE Transactions on Circuits and Systems
for Video Technology, 6(4):419–422, 1996.
[30] Michael Brunig and Wolfgang Niehsen. Fast full-search block matching. IEEE Transactions
on Circuits and Systems for Video Technology, 11(2):241–247, 2001.
[31] K Sam Shanmugam. Digital and analog communication systems. NASA STI/Recon
Technical Report A, 80:23225, 1979.
[32] John E Hopcroft. Data structures and algorithms. Pearson education, 1983.
[33] Rui Wang, Filiz Bunyak, Guna Seetharaman, and Kannappan Palaniappan. Static and
moving object detection using flux tensor with split gaussian models. In Proceedings of
the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages
414–418, 2014.
[34] Dmitry Kit, Brian Sullivan, and Dana Ballard. Novelty detection using growing neural
gas for visuo-spatial memory. In IEEE/RSJ International Conference on Intelligent
Robots and Systems (IROS), pages 1194–1200. IEEE, 2011.
[35] Dong Liang and Shun’ichi Kaneko. Improvements and experiments of a compact statistical
background model. arXiv preprint arXiv:1405.6275, 2014.
[36] Mohamed Sedky, Mansour Moniri, and Claude Chibelushi. Spectral-360: A physicsbased
technique for change detection. In Proceedings of the IEEE Conference on Computer
Vision and Pattern Recognition Workshops, pages 399–402, 2014.
[37] Yannick Benezeth, Pierre-Marc Jodoin, Bruno Emile, Christophe Rosenberger, and
Hélène Laurent. Comparative study of background subtraction algorithms. Journal
of Electronic Imaging, 19(3):033003–033003, 2010.
[38] Francisco J Hernandez-Lopez and Mariano Rivera. Change detection by probabilistic
segmentation from monocular view. Machine Vision and Applications, pages 1–21, 2012.
[39] Zoran Zivkovic and Ferdinand van der Heijden. Efficient adaptive density estimation
per image pixel for the task of background subtraction. Pattern recognition letters,
27(7):773–780, 2006.
[40] Rubén Heras Evangelio, Michael Patzold, and Thomas Sikora. Splitting gaussians in
mixture models. In IEEE Ninth International Conference on Advanced Video and Signal-
Based Surveillance (AVSS), pages 300–305. IEEE, 2012.
[41] D-S Lee. Effective gaussian mixture learning for video background subtraction. IEEE
Transactions on Pattern Analysis and Machine Intelligence, 27(5):827–832, 2005.
[42] Fatih Porikli and Oncel Tuzel. Bayesian background modeling for foreground detection.
In Proceedings of the third ACM international workshop on Video surveillance & sensor
networks, pages 55–58. ACM, 2005.
[43] Jian Yao and Jean-Marc Odobez. Multi-layer background subtraction based on color and
texture. In CVPR’07. IEEE Conference on Computer Vision and Pattern Recognition,
pages 1–8. IEEE, 2007.
[44] Yosuke Nonaka, Atsushi Shimada, Hajime Nagahara, and Rin-ichiro Taniguchi. Evaluation
report of integrated background modeling based on spatio-temporal features.
In IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Workshops (CVPRW), pages 9–14. IEEE, 2012.
[45] Satoshi Yoshinaga, Atsushi Shimada, Hajime Nagahara, and Rin-ichiro Taniguchi. Background
model based on intensity change similarity among pixels. In 19th Korea-Japan
Joint Workshop on Frontiers of Computer Vision,(FCV), pages 276–280. IEEE, 2013.
[46] X Lu. multiscale spatio-temporal background model for motion detection. 2014.
[47] Zoran Zivkovic. Improved adaptive gaussian mixture model for background subtraction.
In Proceedings of the 17th International Conference on Pattern Recognition, volume 2,
pages 28–31. IEEE, 2004.
[48] Lucia Maddalena and Alfredo Petrosino. A fuzzy spatial coherence-based approach to
background/foreground separation for moving object detection. Neural Computing and
Applications, 19(2):179–186, 2010.
[49] Jianyang Zheng, Yinhai Wang, Nancy L Nihan, and Mark E Hallenbeck. Extracting
roadway background image: Mode-based approach. Transportation Research Record:
Journal of the Transportation Research Board, 1944(1):82–88, 2006.
[50] Jean-Philippe Jodoin, Guillaume-Alexandre Bilodeau, and Nicolas Saunier. Background
subtraction based on local shape. arXiv preprint arXiv:1204.6326, 2012.
[51] Rafael C Gonzalez and Richard E Woods. Digital image processing. 2002.