List of Figures

1. Camera(D-Link DCS-G900) used during the course of this work
2. Original Data from a Highly Illuminated Indoor scene
3. Background subtraction results obtained from baseline GMM based method(Stauffer-Grimson)
4. Input data and its corresponding manually marked ground truth images
5. Background subtraction using the variable values corresponding to the minimum error
6. Gradient based background subtraction using the data shown in Figure 2.1
8. Result from the CSIM method using the data set presented in Figure 2.1
9. Pictorial representation of cases involving RA and GMM images
10. Region of Activity frames for data used in Figure 2.1
11. Results of background subtraction for frames in Figure 2.1 using the proposed SMG method. Comparing figure (d) and (e) with (g) and (h), we can see vast improvement in reducing false positives.
12. Background subtraction obtained from the SMG method using the Genetic Algorithm section data
13. Other results using SMG method where a person is switching off lights
14. Actual Background subtraction images from optimized GMM method without using SMG module. Note the high rise in false positives once the light is switched off in frame 1714.
15. Snapshot of Online Query Interface system
16. Conclusion and Future Works