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.
KeywordsBackground subtraction GMM Adaptive thresholding Visual surveillance Computer vision
This work was supported by Guangdong provincial scientific and technological project (ID: 2017B020210005), Student’s Platform for Innovation and Entrepreneurship Training Program (ID: 201711078010), and the National Natural Science of Foundation of China (No. 61501177).
- 2.Stauffer C, Grimson W. Adaptive background mixture models for real-time tracking. In: IEEE international conference on computer vision and pattern recognition; 1999. p. 246–52.Google Scholar
- 3.Chen CC, Aggarwal J. An adaptive background model initialization algorithm with objects moving at different depths. In: IEEE international conference on image processing; 2008; p. 2664–7.Google Scholar
- 4.Bevilacqua A, Stefano LD, Lanza A. An effective multi-stage background generation algorithm. In: IEEE international conference on video and signal based surveillance; 2005. p. 388–93.Google Scholar
- 5.Farin D, De With PHN, Effelsberg W. Robust background estimation for complex video sequences. In: IEEE international conference on image processing, vol. 1; 2003. p. I-145–8.Google Scholar
- 8.Goyette N et al. Changedetection.net: a new change detection benchmark dataset. In: IEEE international conference on computer vision and pattern recognition workshops (CVPRW); 2012. p. 1–8.Google Scholar
- 10.Zivkovic Z. Improved adaptive Gaussian mixture model for background subtraction. In: IEEE international conference on pattern recognition; 2004. p. 28–31.Google Scholar
- 11.Jodoin J-P, Bilodeau G, Saunier N. Background subtraction based on local shape. Technical report; 2012. arXiv:1204.6326v1.