Skip to main content
SpringerLink
Log in

Design and implementation of a secure and trustworthy platform for privacy-aware video surveillance

  • Regular Contribution
  • Published:
International Journal of Information Security Aims and scope Submit manuscript

Abstract

Worldwide, thousands of video surveillance cameras record our daily activities. People are aware that video surveillance is deployed for the sake of security. However, the privacy of individuals would be endangered if the proper measures were not considered. Privacy-aware video surveillance has historically been addressed by proposals based on detecting individuals and other sensitive parts of the video and hiding them using a variety of techniques. In this paper, we present a comprehensive solution tackling video processing, video protection and management of the Information System. We claim that a video surveillance system can protect our safety and, at the same time, guarantee our privacy. We describe the design and implementation of a privacy-aware video surveillance platform that, in order to be trustworthy, accomplishes with the properties of high detection accuracy, real-time performance and protected video utility. We have tested the proposed platform, and we demonstrate the feasibility of our approach for privacy protection.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Notes

  1. News published in The Telegraph (10 Jul 2013)—one surveillance camera for every 11 people in Britain, says CCTV survey, by David Barrett, Home Affairs Correspondent.

  2. Covert Cameras at Discount Retailer: Aldi Store Managers Secretly Filmed Female Shoppers. SIEGEL Online International. April 30, 2012. http://www.spiegel.de/international/germany/aldi-spied-on-female-shoppers-with-hidden-cameras-a-830690.html.

  3. Edward Snowden: Leaks that exposed US spy programme. BBC News. January 14, 2014. http://www.bbc.co.uk/news/world-us-canada-23123964.

  4. There are state-of-the-art surveillance cameras whose design is focused on the security and tamper-proofing [9] to provide image authentication properties.

  5. Each GOP starts with an I-frame (intra-coded) and contains several P-frames (predicted) and B-frames (bi-predictive). Hence, a GOP might be defined by a succession of frames, usually 12 or 15 frames long. I-frames are stored and compressed entirely: the frame is divided into \(8\times 8\)-pixel blocks to which a frequency transform is applied (e.g. discrete cosine transform, DCT). The obtained \(8\times 8\)-coefficient blocks describe the pixel block in terms of texture and details. For each block, there is one DC and 63 AC coefficients.Footnote 6 Quantisation is applied to each block, i.e. each coefficient is divided by a number, aiming at reducing the number of discrete symbols but resulting in a lossy compression and, also, a set of zero coefficients. Finally, entropy encoding (for the nonzero coefficients) and run-length encoding (for the zero coefficients) are applied for a lossless compression of the blocks. The information needed to reconstruct the frame is stored in a specific and standardised data structure. In addition, P- and B-frames are not stored entirely: they just consist of the changing blocks between frames in the GOP.

  6. The DC coefficient is that with zero frequency while the AC coefficients are those with nonzero frequencies.

  7. For instance, /videos/2012/11/15/video023.mp4, where folder /videos/2012/ contains all the videos recorded in 2012.

  8. Note that the zero coefficients will remain unaltered.

  9. http://www.multimediaeval.org/mediaeval2014/visualprivacy2014/.

  10. Note that the video is compressed by the hardware of the camera and it is not considered. Also, the time to uncompress the video has not been considered because it is negligible.

  11. Note that we do not use MD5 as a cryptographic function but as a digest. Hence, according to [16] its use is still viable, although it is considered insecure from a cryptographic perspective.

  12. The information to compare depends on which of the three coefficient alteration schemes has been applied to protect the video.

References

  1. Daniel, J., Solove, D.J.: I’ve got nothing to hide and other misunderstandings of privacy. San Diego Law Rev. 44, 745–757 (2007)

    Google Scholar 

  2. Mordini, E.: Nothing to hide biometrics, privacy and private sphere. In: BIOID 2008. LNCS, vol. 5372, pp. 247–257 (2008)

  3. Directive 95/46/EC of the European Parliament and of the Council of 24 October 1995. http://europa.eu/legislation_summaries/information_society/data_protection/l14012_en.htm

  4. Senior, A. (ed.): Protecting Privacy in Video Surveillance. Springer, Berlin (2009)

    Google Scholar 

  5. Winkler, T., Rinner, B.: A systematic approach towards user-centric privacy and security for smart camera networks. In: Proceedings of the Fourth ACM/IEEE International Conference on Distributed Smart Cameras, pp. 133–141. ACM, New York (2010)

  6. Rashwan, H.A., Martínez-Ballesté, A., Solanas, A., Puig, D.: Understanding trust in privacy-aware video surveillance systems. Int. J. Inf. Secur. 14(2), 225–234 (2015)

    Google Scholar 

  7. Kim, K., Chalidabhongse, T.H., Harwood, D., Davis, L.S.: Background modeling and subtraction by codebook construction. In: International Conference on Image Processing, vol. V, pp. 3061–3064 (2004)

  8. Farnebäck, G.: Fast and accurate motion estimation using orientation tensors and parametric motion models. In: International Conference on Pattern Recognition, vol. I, pp. 135–139 (2000)

  9. Winkler, T., Rinner, B.: TrustCAM: security and privacy-protection for an embedded smart camera based on trusted computing. In: Seventh IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 593–600 (2010)

  10. Rashwan, H.A., Garcia, M.A., Puig, D.: Variational optical flow estimation based on stick tensor voting. IEEE Trans. Image Process. 22(7), 2589–2599 (2013)

    Article  Google Scholar 

  11. Dufaux, F., Navarro, A., Ebrahimi, T.: Privacy enabling technology for video surveillance. In: Proceeding of SPIE—The International Society for Optics and Photonics, vol. 6250, no. 1 (2006)

  12. Dufaux, F., Ebrahimi, T.: Scrambling for privacy protection in video surveillance systems. IEEE Trans. Circuits Syst. Video Technol. 18(8), 1168–1174 (2008)

    Article  Google Scholar 

  13. Crises Research Group, Universitat Rovira i Virgili: The VIPP Project (Vigilància Informatitzada amb Protecció de la Privadesa, Privacy-Aware Computerised Video Surveillance). http://crises-deim.urv.cat/vipp/

  14. INRIA Labs: CAVIAR test case scenarios. http://homepages.inf.ed.ac.uk/rbf/CAVIARDATA1/

  15. Korshunov, P., Araimo, C., de Simone, F., Velardo, C., Dugelay, J., Ebrahimi, T.: Subjective study of privacy filters in video surveillance. In: 2012 IEEE 14th International Workshop on Multimedia Signal Processing (MMSP), pp. 378-382 (2012)

  16. IETF: Updated security considerations for the MD5 message-digest and the HMAC-MD5 algorithms (RFC 6151). https://tools.ietf.org/html/rfc6151

Download references

Acknowledgements

This work was partly funded by the Spanish Government through Project CONSOLIDER INGENIO 2010 CSD2007-0004 ARES, Project TIN2011-27076-C03-01 CO-PRIVACY and by the Rovira i Virgili University through Project 2012R2B-01 VIPP.

Author information

Authors and Affiliations

  1. Dept. Enginyeria Informàtica i Matemàtiques, Universitat Rovira i Virgili, Tarragona, Catalonia, Spain

    Antoni Martínez-Ballesté, Hatem Rashwan, Domenec Puig & Agusti Solanas

Authors
  1. Antoni Martínez-Ballesté
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hatem Rashwan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Domenec Puig
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Agusti Solanas
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Antoni Martínez-Ballesté.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Martínez-Ballesté, A., Rashwan, H., Puig, D. et al. Design and implementation of a secure and trustworthy platform for privacy-aware video surveillance. Int. J. Inf. Secur. 17, 279–290 (2018). https://doi.org/10.1007/s10207-017-0370-4

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10207-017-0370-4

Keywords

Search

Navigation