DOI: https://doi.org/10.33099/2311-7249/2019-36-3-97-102

The justification of optimal algorithms index choice for the background subtraction in video sequences derived from stationary cameras of video surveillance systems

Anatolii Babaryka

Abstract


The background subtraction is an important stage in the process of detecting moving objects in video sequences derived from stationary cameras of video surveillance systems (VSS cameras). A variety of approaches to addressing the background selection problem in video sequences from stationary cameras of video surveillance systems has created the need for research on the choice of optimal algorithms.

In this paper, we described the problem factors that complicate the background allocation process and described the basic background subtraction algorithms classifications.

After analyzing the location of VSS cameras for certain objects within the Information and Telecommunication Systems of the State Border Guard Service and their inspection sectors, we have identified the features of the use of cameras from these systems.

We researched the most common algorithms of background subtraction in video sequences, methods of comparative analysis and methodes for selecting optimal background subtraction algorithms in video sequences from stationary VSS cameras.

We developed an improved efficiency index for the choice optimal algorithms for the  background subtraction in video sequences derived from stationary cameras of video surveillance systems оn the basis method proposed Sobral Andrews and Vacavant Antoine in the "Comprehensive review of subtraction algorithms evaluated using synthetic and real video".

The essence of the improved method is that we propose to calculate the overall performance of the background subtraction algorithm using Matthews correlation coefficient, because this coefficient takes into account all possible variants of the matrix of algorithm responses (TP, TN, FP, FN).

The proposed method was tested by calculating the results of the experimental study in the "A comprehensive review of the subtraction algorithms evaluated using synthetic and real videos".

As a result, we have developed the index of efficiency of an algorithm of background subtraction, that differs from that offered gathered Sobral Andrews and Vacavant Antoine (FSD), because it takes into account all options matrix classifier responses, and therefore is more accurate than the FSD.


Keywords


video surveillance; VSS; background; foreground; moving objects; frame difference; MOG; dataset; algorithm; Matthews correlation coefficient; Sobral Andrews; Vacavant Antoine

References


1. A. Benchmark. Dataset for Outdoor Foreground/Background Extraction. Computer Vision - ACCV 2012 Workshops: ACCV 2012 International Workshops. Part I. / Antoine Vacavant,Thierry Chateau, Alexis Wilhelm, Laurent Lequièvre. Daejeon, Korea, 2012. С. 291–300.

2. Babaee M., Dinh D.T., Rigoll G. A deep convolutional neural network for video sequence background subtraction. Pattern Recognition. Elsevier, 2018. Вип. 76. С. 635–649. URL : hhttps://doi.org/10.1016/j.patcog.2017.09.040. (дата звернення : 16.01.2019).

3. Background Subtraction Website. веб-сайт. URL : https://sites.google.com/site/backgroundsubtraction/test-sequences/human-activities (дата звернення: 25.12.2018).

4. Borgefors G. Distance Transformations in digital images. Computer Vision, Graphics, and Image Processing. 1986. Вип. 34. С. 344–371. URL : https://www.sciencedirect.com/science/article/pii/S0734189X86800470?via%3Dihub. (дата звернення : 22.01.2019).

5. Bouwmans T. Traditional and recent approaches in background modeling for foreground detection: An overview. Computer Science Review. Elsevier, 2014. № 11. С. 31–66. URL: https://doi.org/10.1016/j.cosrev.2014.04.001. (дата звернення : 20.01.2019).

6. Brutzer S., Hoferlin B., Heidemann G. Evaluation of Background Subtraction Techniques for VideoSurveillance. In Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition. Colorado Springs, CO, USA, 2011. С. 1937–1944.

7. CDnet 2014: An Expanded Change Detection Benchmark Dataset. 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops. / Wang Yi та ін. Columbus, OH, 2014. С. 393–400.

8. ChangeDetection.NET (CDNET). веб-сайт. URL : http://www.changedetection.net (дата звернення: 25.12.2018).

9. Comparative study of background subtraction algorithms. Journal of Electronic Imaging. / Yannick Benezeth, Pierre-Marc Jodoin, Bruno Emile, Hélène Laurent, Christophe Rosenberger. 2010. № 19 (3). URL : https://doi.org/10.1117/1.3456695. (дата звернення : 20.01.2019).

10. Hayman Eric, Eklundh Jan-Olof. Statistical background subtraction for a mobile observer. Proceedings Ninth IEEE International Conference on Computer Vision. Nice, France : IEEE, 2003. С. 67–74. URL : https://ieeexplore.ieee.org/document/1238315. (дата звернення : 01.11.2019).

11. Matthews B.W. Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochimica et Biophysica Acta (BBA)-Protein Structure. Elsevier, 1975. № 405 (2). С. 442–451.

12. Sobral Andrews, Vacavant Antoine. A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos. Computer Vision and Image Understanding. 2014. Вип. 122. С. 4–21. URL : https://doi.org/10.1016/j.cviu.2013.12.005. (дата звернення: 22.01.2019).

13. Stauffer C., Grimson W. E. L. Adaptive background mixture models for real-time tracking. Computer Society Conference on Computer Vision and Pattern Recognition : 1999 Conference on Computer Vision and Pattern Recognition (CVPR ’99). Ft. Collins, CO, USA : IEEE Computer Society, 1999. С. 2246–2252. URL : https://dblp.uni-trier.de/db/conf/cvpr/cvpr1999.html. (дата звернення : 16.01.2019).

14. Stuttgart Artificial Background Subtraction Dataset. Institute for Visualisation and Interactive Systems (VIS) : веб-сайт. URL : https://www.vis.uni-stuttgart.de/forschung/visual_analytics/visuelle_analyse_videostroeme/stuttgart_artificial_background_subtraction_dataset/index.en.html (дата звернення: 25.12.2018).

15. Zivkovic Z., F. van der Heijden. Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recognition Letters. 2006. № 27. С. 773–780. URL : https://doi.org/10.1016/j.patrec.2005.11.005. (дата звернення : 30.12.2018).

16. Zivkovic Z. Improved Adaptive Gaussian Mixture Model for Background Subtraction. Proceedings of the 17th International Conference on Pattern Recognition. Cambridge, UK : IEEE, 2004. Вип. 2. С. 28–31


GOST Style Citations


1. A. Benchmark. Dataset for Outdoor Foreground/Background Extraction. Computer Vision - ACCV 2012 Workshops: ACCV 2012 International Workshops. Part I. / Antoine Vacavant,Thierry Chateau, Alexis Wilhelm, Laurent Lequièvre. Daejeon, Korea, 2012. С. 291–300.

2. Babaee M., Dinh D.T., Rigoll G. A deep convolutional neural network for video sequence background subtraction. Pattern Recognition. Elsevier, 2018. Вип. 76. С. 635–649. URL : hhttps://doi.org/10.1016/j.patcog.2017.09.040. (дата звернення : 16.01.2019).

3. Background Subtraction Website. веб-сайт. URL : https://sites.google.com/site/backgroundsubtraction/test-sequences/human-activities (дата звернення: 25.12.2018).

4. Borgefors G. Distance Transformations in digital images. Computer Vision, Graphics, and Image Processing. 1986. Вип. 34. С. 344–371. URL : https://www.sciencedirect.com/science/article/pii/S0734189X86800470?via%3Dihub. (дата звернення : 22.01.2019).

5. Bouwmans T. Traditional and recent approaches in background modeling for foreground detection: An overview. Computer Science Review. Elsevier, 2014. № 11. С. 31–66. URL: https://doi.org/10.1016/j.cosrev.2014.04.001. (дата звернення : 20.01.2019).

6. Brutzer S., Hoferlin B., Heidemann G. Evaluation of Background Subtraction Techniques for VideoSurveillance. In Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition. Colorado Springs, CO, USA, 2011. С. 1937–1944.

7. CDnet 2014: An Expanded Change Detection Benchmark Dataset. 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops. / Wang Yi  та ін. Columbus, OH, 2014. С. 393–400.

8. ChangeDetection.NET (CDNET). веб-сайт. URL : http://www.changedetection.net (дата звернення: 25.12.2018).

9. Comparative study of background subtraction algorithms. Journal of Electronic Imaging. / Yannick Benezeth, Pierre-Marc Jodoin, Bruno Emile, Hélène Laurent, Christophe Rosenberger. 2010. № 19 (3). URL : https://doi.org/10.1117/1.3456695. (дата звернення : 20.01.2019).

10. Hayman Eric, Eklundh Jan-Olof. Statistical background subtraction for a mobile observer. Proceedings Ninth IEEE International Conference on Computer Vision. Nice, France : IEEE, 2003. С. 67–74. URL : https://ieeexplore.ieee.org/document/1238315. (дата звернення : 01.11.2019). 

11. Matthews B.W. Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochimica et Biophysica Acta (BBA)-Protein Structure. Elsevier, 1975. № 405 (2). С. 442–451.

12. Sobral Andrews, Vacavant Antoine. A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos. Computer Vision and Image Understanding. 2014. Вип. 122. С. 4–21. URL : https://doi.org/10.1016/j.cviu.2013.12.005. (дата звернення: 22.01.2019).

13. Stauffer C., Grimson W. E. L. Adaptive background mixture models for real-time tracking. Computer Society Conference on Computer Vision and Pattern Recognition : 1999 Conference on Computer Vision and Pattern Recognition (CVPR ’99). Ft. Collins, CO, USA : IEEE Computer Society, 1999. С. 2246–2252. URL : https://dblp.uni-trier.de/db/conf/cvpr/cvpr1999.html. (дата звернення : 16.01.2019).

14. Stuttgart Artificial Background Subtraction Dataset. Institute for Visualisation and Interactive Systems (VIS) : веб-сайт. URL : https://www.vis.uni-stuttgart.de/forschung/visual_analytics/visuelle_analyse_videostroeme/stuttgart_artificial_background_subtraction_dataset/index.en.html (дата звернення: 25.12.2018).

15. Zivkovic Z., F. van der Heijden. Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recognition Letters. 2006. № 27. С. 773–780. URL : https://doi.org/10.1016/j.patrec.2005.11.005. (дата звернення : 30.12.2018).

16. Zivkovic Z. Improved Adaptive Gaussian Mixture Model for Background Subtraction. Proceedings of the 17th International Conference on Pattern Recognition. Cambridge, UK : IEEE, 2004. Вип. 2. С. 28–31





ISSN 2410-7336 (Online)

ISSN 2311-7249 (Print)