The Community for Technology Leaders
RSS Icon
Issue No.12 - Dec. (2013 vol.35)
pp: 3066-3072
Christopher Thorpe , Dept. of Comput. & Inf. Sci., Univ. of Delaware, Newark, DE, USA
Feng Li , Qualcomm Technol., Inc., San Diego, CA, USA
Zijia Li , Doctoral Program Comput. Math., Johannes Kepler Univ., Linz, Austria
Zhan Yu , Dept. of Comput. & Inf. Sci., Univ. of Delaware, Newark, DE, USA
David Saunders , Dept. of Comput. & Inf. Sci., Univ. of Delaware, Newark, DE, USA
Jingyi Yu , Dept. of Comput. & Inf. Sci., Univ. of Delaware, Newark, DE, USA
This paper presents a novel coprime blurred pair (CBP) model to improve data security in camera surveillance. While most previous approaches have focused on completely encrypting the video stream, we introduce a spatial encryption scheme by strategically blurring the image/video contents. Specifically, we form a public stream and a private stream by blurring the original video data using two different kernels. Each blurred stream will provide the user who has lower clearance less access to personally identifiable details while still allowing behavior to be monitored. If the behavior is recognized as suspicious, a supervisor can use both streams to deblur the contents. Our approach is based on a new CBP theory where the two kernels are coprime when mapped to bivariate polynomials in the z domain. We show that coprimality can be derived in terms of the rank of Bézout matrix formed by sampled polynomials, and we present an efficient algorithm to factor the Bézout matrix for recovering the latent image. To make our solution practical, we implement our decryption scheme on a graphics processing unit (GPU) to achieve real-time performance. Extensive experiments demonstrate that our new scheme can effectively protect sensitive identity information in surveillance videos and faithfully reconstruct the unblurred video stream when both CBP sequences are available.
Streaming media, Cameras, Surveillance, Graphics processing units, Visualization, Discrete Fourier transforms,CUDA, Video surveillance, greatest common divisor, image deblurring, visual cryptography
Christopher Thorpe, Feng Li, Zijia Li, Zhan Yu, David Saunders, Jingyi Yu, "A Coprime Blur Scheme for Data Security in Video Surveillance", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.35, no. 12, pp. 3066-3072, Dec. 2013, doi:10.1109/TPAMI.2013.161
[1] P. Agrawal and P. Narayanan, "Person De-Identification in Videos," IEEE Trans. Circuits and Systems for Video Technology, vol. 21, no. 3, pp. 299-310, Mar. 2011.
[2] S. Avidan and M. Butman, "Blind Vision," Proc. European Conf. Computer Vision, 2006.
[3] S. Barnett, "A Note on the Bezoutian Matrix," SIAM J. Applied Math., vol. 22, no. 1, pp. 84-86, 1972.
[4] M. Bayazit, A. Couture-beil, and G. Mori, "Real-Time Motion-Based Gesture Recognition Using the GPU," Proc. IAPR Conf. Machine Vision Applications, pp. 9-12, 2009.
[5] D.A. Bini and P. Boito, "Structured Matrix-Based Methods for Polynomial E-Gcd: Analysis and Comparisons," Proc. Int'l Symp. Symbolic and Algebraic Computation, pp. 9-16, 2007.
[6] W.L. Brogan, Modern Control Theory, third ed. Prentice-Hall Inc., 1991.
[7] Y. Chang, R. Yan, D. Chen, and J. Yang, "People Identification with Limited Labels in Privacy-Protected Video," Proc. IEEE Int'l Conf. Multimedia and Expo, pp. 1005-1008, 2006.
[8] D. Chen, Y. Chang, R. Yan, and J. Yang, "Tools for Protecting the Privacy of Specific Individuals in Video," EURASIP J. Applied Signal Processing, vol. 2007, pp. 107-107, 2007.
[9] J. Chen, L. Yuan, C.-K. Tang, and L. Quan, "Robust Dual Motion Deblurring," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[10] Z. Erkin, M. Franz, J. Guajardo, S. Katzenbeisser, I. Lagendijk, and T. Toft, "Privacy-Preserving Face Recognition," Proc. Ninth Int'l Symp. Privacy Enhancing Technologies, pp. 235-253, 2009.
[11] R. Fergus, B. Singh, A. Hertzmann, S. Roweis, and W. Freeman, "Removing Camera Shake from a Single Photograph," Proc. ACM Siggraph, pp. 787-794, 2006.
[12] S. Greiner and J. Yang, "Privacy Protection in an Electronic Chronicle System," Proc. 34th Ann. IEEE Northeast Bioeng. Conf., 2008.
[13] N. Hu, S. Cheung, and T. Nguyen, "Secure Image Filtering," Proc. Int'l Conf. Image Processing, pp. 1553-1556, 2007.
[14] N. Joshi, C. Zitnick, R. Szeliski, and D. Kriegman, "Image Deblurring and Denoising Using Color Priors," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1550-1557, 2009.
[15] A. Levin, "Blind Motion Deblurring Using Image Statistics," Proc. Neural Information Processing Systems, 2007.
[16] A. Levin, Y. Weiss, F. Durand, and W. Freeman, "Understanding and Evaluating Blind Deconvolution Algorithms," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1964-1971, 2009.
[17] F. Li, Z. Li, D. Saunders, and J. Yu, "A Theory of Coprime Blurred Pairs," Proc. IEEE Int'l Conf. Computer Vision, pp. 217-224, 2011.
[18] E. Myodo, K. Takagi, S. Miyaji, and Y. Takishima, "Halftone Visual Cryptography Embedding a Natural Grayscale Image Based on Error Diffusion Technique," Proc. IEEE Int'l Conf. Multimedia and Expo, pp. 2114-2117, 2007.
[19] M. Naor and A. Shamir, "Visual Cryptography," Proc. Advances in Cryptology, 1995.
[20] E.M. Newton, L. Sweeney, and B. Malin, "Preserving Privacy by De-Identifying Face Images," IEEE Trans. Knowledge and Data Eng., vol. 17, no. 2, pp. 232-243, Feb. 2005.
[21] A. Rav-Acha and S. Peleg, "Two Motion-Blurred Images Are Better Than One," Pattern Recognition Letters, vol. 26, no. 3, pp. 311-317, 2005.
[22] W. Richardson, "Bayesian-Based Iterative Method of Image Restoration," J. Optical Soc. Am., vol. 62, no. 1, pp. 55-59, 1972.
[23] Q. Shan et al., "High-Quality Motion Deblurring from a Single Image," ACM Trans. Graphics, vol. 27, no. 3, p. 73, 2008.
[24] J. Shashank, P. Kowshik, K. Srinathan, and C. Jawahar, "Private Content Based Image Retrieval," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[25] D. Sun and L. Zhi, "Structured Low Rank Approximation of a Bezout Matrix," Math. in Computer Science, vol. 1, no. 2, pp. 427-437, 2007.
[26] Y.-W. Tai, P. Tan, and M.S. Brown, "Richardson-Lucy Deblurring for Scenes Under a Projective Motion Path," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 33, no. 8, pp. 1603-1618, Aug. 2011.
[27] M. Upmanyu, A.M. Namboodiri, K. Srinathan, and C. Jawahar, "Efficient Privacy Preserving Video Surveillance," Proc. IEEE Int'l Conf. Computer Vision, pp. 1639-1646, 2009.
[28] J.V.Z. Gathen, M. Mignotte, and I. Shparlinski, "Approximate Polynomial: Small Degree and Small Height Perturbations," J. Symbolic Computation, vol. 45, pp. 879-886, 2010.
[29] Z. Wang and G. Arce, "Halftone Visual Cryptography through Error Diffusion," Proc. IEEE Int'l Conf. Image Processing, pp. 109-112, 2006.
[30] J. Weir and W. Yan, "A Comprehensive Study of Visual Cryptography," Trans. Data Hiding and Multimedia Security, vol. 5, pp. 70-105, 2010.
[31] L. Xu and J. Jia, "Two-Phase Kernel Estimation for Robust Motion Deblurring," Proc. 11th European Conf. Computer Vision, pp. 157-170, 2010.
[32] L. Yuan, J. Sun, L. Quan, and H. Shum, "Image Deblurring with Blurred/Noisy Image Pairs," ACM Trans. Graphics, vol. 26, no. 3, p. 1, 2007.
[33] Z. Zhou, G. Arce, and G.D. Crescenzo, "Halftone Visual Cryptography," IEEE Trans. Image Processing, vol. 15, no. 8, pp. 2441-2453, Aug. 2006.
164 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool