Improved background subtraction techniques for security in video applications

Authors:
K. Srinivasan;K. Porkumaran;G. Sainarayanan
Affiliations:
Dept. of EEE, Sri Ramakrishna Engineering College, Coimbatore, India;Dept. of BME, Sri Ramakrishna Engineering College, Coimbatore, India;Dept. of EEE, New Horizon College of Engineering, Bangalore, India
Venue:
ASID'09 Proceedings of the 3rd international conference on Anti-Counterfeiting, security, and identification in communication
Year:
2009

Citing 4
Cited 0

Person-on-Person Violence Detection in Video Data

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
Posture and Activity Recognition Using Projection Histogram and PCA Methods

CISP '08 Proceedings of the 2008 Congress on Image and Signal Processing, Vol. 2 - Volume 02
Mixture models based background subtraction for video surveillance applications

CAIP'07 Proceedings of the 12th international conference on Computer analysis of images and patterns
Combining motion segmentation with tracking for activity analysis

FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper attempts to find moving objects by subtracting the background images from static single camera video sequences in security systems. It aims to improve the background subtraction techniques for indoor video surveillance applications. For dynamic video sequences, the object focus and object tracking are very difficult due to changing of various parameters such as camera noise, illumination changes, motion changes, and geometry of background changes. The background subtraction algorithm provides the solution to detect moving objects in the static scene. The recursive and nonrecursive algorithms are discussed in an improved way. The novel automatic threshold updating (ATU) algorithm is also developed and tested for various indoor video sequences which gives better efficiency. The statistical and temporal differencing methods are also presented. Finally, our novel approach is compared with the existing methods.