An Adaptive Thresholding Method for Background Subtraction Based on Model Variation

Background subtraction is an important task in computer vision. Pixel-based methods have a high processing speed and low complexity. But when the video frame with camouflage problem is processed, this kind of methods usually output incomplete foreground. In addition, the parameters of many algorithms are invariable. These methods cannot tackle non-static background. In this paper, we present an adaptive background subtraction algorithm derived from ViBe. Gaussian Kernel template is used to model initialization and update. Standard deviation is used to measure background dynamics. We test our algorithm on a public dataset, named changedetection.net. The results show that we can handle most of scenarios. Compared to ViBe, we achieve better result generally, especially in dynamic background and camera jitter categories.

[1]  Lucia Maddalena,et al.  Scene background initialization: A taxonomy , 2017, Pattern Recognit. Lett..

[2]  Andrea Fusiello,et al.  Patch-Based Background Initialization in Heavily Cluttered Video , 2010, IEEE Transactions on Image Processing.

[3]  Z. Zivkovic Improved adaptive Gaussian mixture model for background subtraction , 2004, ICPR 2004.

[4]  Jen-Hui Chuang,et al.  Learning a Scene Background Model via Classification , 2009, IEEE Transactions on Signal Processing.

[5]  Guillaume-Alexandre Bilodeau,et al.  Background subtraction based on Local Shape , 2012, ArXiv.

[6]  Wolfgang Effelsberg,et al.  Robust background estimation for complex video sequences , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[7]  Jake K. Aggarwal,et al.  An adaptive background model initialization algorithm with objects moving at different depths , 2008, 2008 15th IEEE International Conference on Image Processing.

[8]  Marc Van Droogenbroeck,et al.  ViBe: A Universal Background Subtraction Algorithm for Video Sequences , 2011, IEEE Transactions on Image Processing.

[9]  Fatih Murat Porikli,et al.  Changedetection.net: A new change detection benchmark dataset , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.