Background Subtraction in Surveillance systems- A Neural Fuzzy Approach
Surveillance systems mostly deal with moving object detection. In this paper we propose a neural-fuzzy based method to detect object in the dynamic background. The neural approach is based on self-organizing map (SOM) architecture (unsupervised learning) in which every pixel is mapped to the 3x3 neural map. The threshold parameters required to consider a pixel as an object or part of background are calculated by fuzzy inference system independent of human intervention. The proposed approach gives robust results of the videos taken by stationery cameras considering scenes containing moving ackground, illumination changes, camouflage and has no bootstrapping limitations. The results obtained by using SOM with fuzzy inference system (mamdani) are compared with SOM with manual parameters in terms of detection accuracy.
Disclaimer/Regarding indexing issue:
We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.