Probabilistic static foreground elimination for background subtraction

ABSTRACT

Background subtraction is generally used to detect moving objects, because it has low complexity, and it is easy to implement. However, the detection error increases when the background is changing. Therefore, adaptive background subtraction is applied to overcome this problem, and it continuously requires updating the background with a fixed learning rate. The learning rate should be tuned for a consistently evolving background. This paper proposes the Probabilistic Static Foreground Elimination for Background Subtraction (PSFE) algorithm. It consisted of two parameters: the number of frames for static foreground elimination, and the probability of changes in background pixels. These two parameters can tune the learning rate and update background for better detection. The average results of the detection error rate from Wallflower datasets were tested with PSFE and well-known method. They demonstrated that PSFE provides moving object detection with minimum detection error (5.95%), especially in Camouflage, Moved object, and Light switch dataset.

KEYWORDS:

• Adaptive background subtraction
• moving object detection
• learning rate
• probability
• foreground elimination

Acknowledgements

This research was supported by PSU-Ph.D. Scholarship. The Department of Electrical Engineering, Faculty of Engineering, Prince of Songkla University is gratefully acknowledged for support. The authors also would like to thank Assoc. Prof. Dr. Seppo Karrila for valuable comments on the manuscript. In addition, the authors would like to thank anonymous reviewers for their valuable comments.

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes on contributors

Sunthorn Rungruangbaiyok, he received Master Engineering from the Department of Electrical Engineering, Faculty of Engineering, Prince of Songkla University, Thailand. He is now a Ph.D. candidate. His interesting research is Image processing.

Rakkrit Duangsoithong, he received Ph.D degree from University of Surrey, United Kingdom. He is now an assistant professor of Department of Electrical Engineering, Faculty of Engineering, Prince of Songkla University, Thailand. His interesting researches are Data mining, Signal & Image processing, and Deep learning.

Kanadit Chetpattananondh, he received Master Engineering from Tokyo Institute of Technology, Japan. He is now an associate professor of Department of Electrical Engineering, Faculty of Engineering, Prince of Songkla University, Thailand. His interesting researches are Sensors, Instrumentation & Measurement, Signal and Image processing.

Additional information

Funding

This work was supported by Research fund of Faculty of Engineering, Prince of Songkla University via grant number ENG6104050S, fiscal year 2018.