Adaptive Background Subtraction using Fuzzy based Gaussian Mixture Model
Keywords:
BGS,T2-FGMM,GMM,Covariance,intervalued T-2 FSAbstract
Background Subtraction is one of the initial steps in object tracking in visual surveillance which we all know holds a great importance in today’s world. BGS involves the segmentation of foreground objects by differencing the current frame from the background image or the reference image, but it is not always as simple as that. BGS in practice involves environmental challenges like camera jitter, shadows, camouflage, illumination changes, occlusion, night videos, changing weather etc. A lot of work has been done over the years for coming up with techniques which are robust to these challenges. Here, in this paper we try to study various background subtraction techniques. A study on Gaussian Mixture Model (GMM) has been made and its drawback of uncertain and noisy data are studied and an approach is proposed for overcoming this drawback.
References
- Massimo Piccardi,” Background subtraction techniques: a review”, 2004 IEEE International Conference on Systems, Man and Cybernetics
- Chris Stauffer and W.E.L Grimson,” Adaptive background mixture models for real-time tracking”, The Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge
- Kalpana Goyal, Jyoti Singhai,”Review of background subtraction methods using Gaussian Mixture Model for visual surveillance”, artificial intelligence review
- Sivabalakrishnan.M “adaptive background subtraction in dynamic environments using fuzzy logic”, Sivabalakrishnan.M. et al. / (IJCSE) International Journal on Computer Science and Engineering
- Dat Tran and Michael Wagner “Fuzzy Gaussian Mixture Models for Speaker Recognition”, Human-Computer Communication Laboratory School of Computing, University of Canberra, ACT 2601, Australia
- Zoran Zivkovic "Improved Adaptive Gaussian Mixture Model for Background Subtraction", In Proc. ICPR, 2004.
- Massimo Piccardi,” Background subtraction techniques: a review”, 2004 IEEE International Conference on Systems, Man and Cybernetics
- Chris Stauffer and W.E.L Grimson,” Adaptive background mixture models for real-time tracking”, The Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge
- Kalpana Goyal, Jyoti Singhai,”Review of background subtraction methods using Gaussian Mixture Model for visual surveillance”, artificial intelligence review
- Sivabalakrishnan.M “adaptive background subtraction in dynamic environments using fuzzy logic”, Sivabalakrishnan.M. et al. / (IJCSE) International Journal on Computer Science and Engineering
- Dat Tran and Michael Wagner “Fuzzy Gaussian Mixture Models for Speaker Recognition”, Human-Computer Communication Laboratory School of Computing, University of Canberra, ACT 2601, Australia
- Zoran Zivkovic "Improved Adaptive Gaussian Mixture Model for Background Subtraction", In Proc. ICPR, 2004.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT
This work is licensed under a Creative Commons Attribution 4.0 International License.