Moving object detection using a background modeling based on entropy theory and quad-tree decomposition

Abstract. A particular algorithm for moving object detection using a background subtraction approach is proposed. We generate the background model by combining quad-tree decomposition with entropy theory. In general, many background subtraction approaches are sensitive to sudden illumination change in the scene and cannot update the background image in scenes. The proposed background modeling approach analyzes the illumination change problem. After performing the background subtraction based on the proposed background model, the moving targets can be accurately detected at each frame of the image sequence. In order to produce high accuracy for the motion detection, the binary motion mask can be computed by the proposed threshold function. The experimental analysis based on statistical measurements proves the efficiency of our proposed method in terms of quality and quantity. And it even outperforms substantially existing methods by perceptional evaluation.

[1]  Yong Wang,et al.  Compressive Background Modeling for Foreground Extraction , 2015, J. Electr. Comput. Eng..

[2]  Hamid Tairi,et al.  Motion detection based on the combining of the background subtraction and spatial color information , 2015, 2015 Intelligent Systems and Computer Vision (ISCV).

[3]  Wei Liu,et al.  Effective background modelling and subtraction approach for moving object detection , 2015, IET Comput. Vis..

[4]  Jamal Riffi,et al.  Motion estimation using the fast and adaptive bidimensional empirical mode decomposition , 2012, Journal of Real-Time Image Processing.

[5]  Gian Luca Foresti,et al.  Vehicle recognition and tracking from road image sequences , 1999 .

[6]  Wayne Niblack,et al.  An introduction to digital image processing , 1986 .

[7]  Antoine Manzanera,et al.  A new motion detection algorithm based on Sigma-Delta background estimation , 2007, Pattern Recognit. Lett..

[8]  Dazhen Lin,et al.  Improving motion state change object detection by using block background context , 2014, 2014 14th UK Workshop on Computational Intelligence (UKCI).

[9]  Hélène Laurent,et al.  Comparative study of background subtraction algorithms , 2010, J. Electronic Imaging.

[10]  T. Xiang.  Background Subtraction with Dirichlet Process Mixture Models , 2013 .

[11]  Brian C. Lovell,et al.  Adaptive Patch-Based Background Modelling for Improved Foreground Object Segmentation and Tracking , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[12]  Shanq-Jang Ruan,et al.  Illumination-Sensitive Background Modeling Approach for Accurate Moving Object Detection , 2011, IEEE Transactions on Broadcasting.

[13]  Hamid Tairi,et al.  Motion detection based on the combining of the background subtraction and the structure–texture decomposition , 2015 .

[14]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[15]  Tao Xiang,et al.  Background Subtraction with DirichletProcess Mixture Models , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Lianghai Jin,et al.  Characteristic analysis of Otsu threshold and its applications , 2011, Pattern Recognit. Lett..

[17]  Li Dong-dong.  Tracking method of moving target based on detection of feature optical flow , 2005 .

[18]  Hamid Tairi,et al.  An Effective Foreground Detection Approach Using a Block-Based Background Modeling , 2016, 2016 13th International Conference on Computer Graphics, Imaging and Visualization (CGiV).

[19]  Feng Sun,et al.  Fast background subtraction for moving cameras based on nonparametric models , 2016, J. Electronic Imaging.

[20]  N.B. Rais,et al.  Adaptive thresholding technique for document image analysis , 2004, 8th International Multitopic Conference, 2004. Proceedings of INMIC 2004..

[21]  Kahlil Muchtar,et al.  Real-time background modeling based on a multi-level texture description , 2014, Inf. Sci..

[22]  B. Shoushtarian.  A PRACTICAL APPROACH TO REAL-TIME DYNAMIC BACKGROUND GENERATION BASED ON A TEMPORAL MEDIAN FILTER , 2003 .

[23]  Alex Pentland,et al.  Pfinder: Real-Time Tracking of the Human Body , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Shih-Chia Huang,et al.  Motion detection with pyramid structure of background model for intelligent surveillance systems , 2012, Eng. Appl. Artif. Intell..

[25]  Chen Zhen,et al.  Motion Detection Based on Temporal Difference Method and Optical Flow field , 2009, 2009 Second International Symposium on Electronic Commerce and Security.

[26]  Mohammad Hossein Ghaeminia,et al.  Adaptive background model for moving objects based on PCA , 2010, 2010 6th Iranian Conference on Machine Vision and Image Processing.

[27]  Mustafa Oral,et al.  Centre of mass model - A novel approach to background modelling for segmentation of moving objects , 2007, Image Vis. Comput..

[28]  Yi-Ping Hung,et al.  Efficient hierarchical method for background subtraction , 2007, Pattern Recognit..

[29]  Amitava Das,et al.  Adaptive contour-based statistical background subtraction method for moving target detection in infrared video sequences , 2014 .

[30]  Stanley Osher,et al.  Modeling Textures with Total Variation Minimization and Oscillating Patterns in Image Processing , 2003, J. Sci. Comput..

[31]  Nikos Paragios,et al.  Background modeling and subtraction of dynamic scenes , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.