A Multi-object Segmentation Algorithm Based on Background Modeling and Region Growing

A multi-object segmentation algorithm based on Background Modeling and Region Growing (named as BMRG) algorithm is proposed in this paper. For multi-object segmentation, the algorithm uses Chebyshev inequality and the kernel density estimation method to do background modeling firstly. Then in order to classify image pixels as background points, foreground points and suspicious points, an adaptive threshold algorithm is proposed accordingly. After using background subtraction to get the ideal foreground image, region growing method is used for multi-object segmentation. Here, we improved the region growing method by introducing the growth seed concept for multi-object segmentation, which is calculated from the sparse matrix of quad-tree decomposition. Experimental results show that Chebyshev inequalities can quickly distinguish the foreground and background points. Multi-object segmentation results are satisfactory through seed-based region growing method. Comparison and analysis the experimental results show that the proposed BMRG algorithm is feasible, rapid and effective.

[1]  Csaba Beleznai,et al.  Multiple object tracking by hierarchical association of spatio-temporal data , 2010, 2010 IEEE International Conference on Image Processing.

[2]  Ying Gao,et al.  Semi-Supervised K -Means Clustering Algorithm for Multi-Type Relational Data: Semi-Supervised K -Means Clustering Algorithm for Multi-Type Relational Data , 2009 .

[3]  Liu Xiaofang,et al.  Multi-object segmentation based on pulse coupled neural network , 2008, 2008 IEEE Conference on Cybernetics and Intelligent Systems.

[4]  Madasu Hanmandlu,et al.  A Simple Single Seeded Region Growing Algorithm for Color Image Segmentation using Adaptive Thresholding , 2011, 2011 International Conference on Communication Systems and Network Technologies.

[5]  Avinash C. Kak,et al.  A multi-Kalman filtering approach for video tracking of human-delineated objects in cluttered environments , 2005, Comput. Vis. Image Underst..

[6]  David A. Clausi,et al.  Multivariate Image Segmentation Using Semantic Region Growing With Adaptive Edge Penalty , 2010, IEEE Transactions on Image Processing.

[7]  Kenji Terabayashi,et al.  Multi-object Segmentation in a Projection Plane Using Subtraction Stereo , 2010, 2010 20th International Conference on Pattern Recognition.

[8]  L. Davis,et al.  Background and foreground modeling using nonparametric kernel density estimation for visual surveillance , 2002, Proc. IEEE.

[9]  Filiberto Pla,et al.  Segmenting Traffic Scenes from Grey Level and Motion Information , 2014, Pattern Analysis & Applications.

[10]  Avinash C. Kak,et al.  A multi-Kalman filtering approach for video tracking of human-delineated objects in cluttered environments , 2005, Computer Vision and Image Understanding.