International Journal of Engineering Research in Electronics and Communication Engineering

Overview of Background Subtraction Algorithms

Author : Prachi A. Joshi ¹ Dr.R.A.Khan ² S.C.Nandedkar ³

Date of Publication :21st February 2018

Abstract: Understanding the human activity from the video is proved to be important research area in computer vision since last few years. Background subtraction is a widely used technique for detecting moving objects in videos from static cameras. This approach is said to be the fast way of localizing moving objects in a video frame shot by the static camera which can be used for various computer vision applications. The mentioned technique is used for calculating the foreground mask performing a subtraction between the current frame and a background model, containing the static part of the scene. Here regions of interest are objects like humans, cars, text etc. in its foreground. The objective here is of detecting the moving objects from the difference between the current frame and a reference frame, frequently called as background model or image. Background subtraction algorithms are more popular nowadays because of its computational efficiency in applications like video surveillance, traffic monitoring, human-computer interaction etc. The conditions like moving background, temporarily stationary objects, objects shadows, illumination variation can affect the background subtraction. This paper focuses on the comparative study of different background subtraction algorithms

Reference :

1. Mr. Deepjoy Das and Dr. Sarat Saharia, “Implementation and Performance Evaluation of Background Subtraction Algorithms”, International Journal on Computational Sciences & Applications (IJCSA) Vol. 4, No. 2, April 2014
2. Birgi Tamersoy,” Background Subtraction”, The University of Texas at Austin, September 2009
3. A. Singh, S. Sawan, M. Hanmandlu, V. K. Madasu, and B. C. Lovell, “An abandoned object detection system based on dual background segmentation,” in Proceedings of the 6th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS ’09), pp. 352–357, IEEE Press, September 2009
4. Farah Yasmin, Aini Hussain, Wan Mimi Diyana Wan Zaki, Halimah Badioze Zaman and Nooritawati Md Tahir, “Enhancement of Background Subtraction Techniques Using a Second Derivative in Gradient Direction Filter”, Journal of Electrical and Computer Engineering, Volume 2013, Article ID 598708,12 pages