Abstract
In the cloud era, a large amount of data is uploaded to and processed by public clouds. The risk of privacy leakage has become a major concern for cloud users. Cloud-based video surveillance requires motion detection, which may reveal the privacy of people in a surveillance video. Privacy-preserving video surveillance allows motion detection while protecting privacy. The existing scheme [25], designed to detect motion on encrypted and H.264-compressed surveillance videos, does not work well on more advanced video compression schemes such as HEVC.
In this article, we propose the first motion detection method on encrypted and HEVC-compressed videos. It adopts a novel approach that exploits inter-prediction reference relationships among coding blocks to detect motion regions. The partition pattern and the number of coding bits of each detection block used in prior art are also used to help detect motion regions. Spatial and temporal consistency of a moving object and Kalman filtering are applied to segment connected/merged motion regions, remove noise and background motions, and refine trajectories and shapes of detected moving objects. Experimental results indicate that our detection method achieves high detection recall, precision, and F1-score for surveillance videos of both high and low resolutions with various scenes. It has a similarly high detection accuracy on encrypted and HEVC-compressed videos as that of the existing motion detection method [25] on encrypted and H.264-compressed videos. Our proposed method incurs no bit-rate overhead and has a very low computational complexity for both motion detection and encryption of HEVC videos.
- [1] . 2018. Efficient privacy-preserving motion detection for HEVC compressed video in cloud video surveillance. In Proceedings of the IEEE Conference on Computer Communications Workshops: The 4thth International Workshop on Security and Privacy in Big Data (BigSecurity’18).Google Scholar
Cross Ref
- [2] . 2014. W3-privacy: Understanding what, when, and where inference channels in multi-camera surveillance video. Multim. Tools Applic. 68, 1 (2014), 135–158. Google Scholar
Digital Library
- [3] . 2016. Big privacy: Challenges and opportunities of privacy study in the age of big data. IEEE Access 4 (2016), 2751–2763.Google Scholar
Cross Ref
- [4] . 2018. Image disguising for privacy-preserving deep learning. In Proceedings of the ACM SIGSAC Conference on Computer and Communications Security. 2291–2293. Google Scholar
Digital Library
- [5] 2018. JPEG decompression in the homomorphic encryption domain. In Proceedings of the ACM Multimedia Conference. 905–913. Google Scholar
Digital Library
- [6] . 2019. Decoding homomorphically encrypted FLAC audio without decryption. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. 675–679.Google Scholar
Cross Ref
- [7] . 2015. Privacy protection in biometric-based recognition systems: A marriage between cryptography and signal processing. IEEE Sig. Process. Mag. 32, 5 (2015), 66–76.Google Scholar
Cross Ref
- [8] . 2015. CloudBI: Practical privacy-preserving outsourcing of biometric identification in the cloud. In Proceedings of the European Symposium on Research in Computer Security. 186–205.Google Scholar
Cross Ref
- [9] . 2018. Smart monitoring cameras driven intelligent processing to big surveillance video data.IEEE Trans. Big Data 4, 1 (2018), 105–116.Google Scholar
Cross Ref
- [10] . 2016. Lossless ROI privacy protection of H.264/AVC compressed surveillance videos. IEEE Trans. Emerg. Topics Comput. 4, 3 (2016), 349–362.Google Scholar
Cross Ref
- [11] . 2014. Using mutual information for multi-anchor tracking of human beings. In Proceedings of the International Workshop on Biometric Authentication. 28–39.Google Scholar
Cross Ref
- [12] . 2012. Tracking-learning-detection. IEEE Trans. Pattern Anal. Mach. Intell. 34, 7 (2012), 1409–1422. Google Scholar
Digital Library
- [13] . 2009. Moving object detection in the H.264/AVC compression domain for video surveillance applications. J. Vis. Commun. Image Represent. 20, 6 (2009), 428–437. Google Scholar
Digital Library
- [14] . 2009. Fast compression domain motion detection in H.264 video streams for video surveillance applications. In Proceedings of the IEEE International Conference on Advanced Video and Signal Based Surveillance. 478–483. Google Scholar
Digital Library
- [15] . 2013. Compression domain moving object detection based on H.264/AVC macroblock types. In Proceedings of the Conference on Computer Vision Imaging and Applications. 219–228.Google Scholar
- [16] . 2015. Compression domain moving object detection by spatio-temporal analysis of H.264/AVC syntax elements. In Proceedings of the Picture Coding Symposium. 282–286.Google Scholar
- [17] . 2014. A rapid abnormal event detection method for surveillance video based on a novel feature in compression domain of HEVC. In Proceedings of the IEEE Conference on Multimedia and Expo. 1–6.Google Scholar
- [18] . 2017. Abnormal event detection in surveillance video: A compression domain approach for HEVC. In Proceedings of the Data Compression Conference. 475–475.Google Scholar
Cross Ref
- [19] . 2018. Real-time moving object segmentation and classification from HEVC Compressed surveillance video. IEEE Trans. Circ. Syst. Video Technol. 28, 6 (2018), 1346–1357. Google Scholar
Digital Library
- [20] . 2010. Privacy-preserving watch list screening in video surveillance system. In Proceedings of the Pacific-Rim Conference on Multimedia. 622–632. Google Scholar
Digital Library
- [21] . 2009. Efficient privacy preserving video surveillance. In Proceedings of the IEEE International Conference on Computer Vision. 1639–1646. Google Scholar
Digital Library
- [22] . 2014. A privacy preserving human tracking scheme in centralized cloud based camera networks. In Proceedings of the IEEE International Conference on Communications. 793–798.Google Scholar
Cross Ref
- [23] . 2017. Moving object detection in the encrypted domain. Multim. Tools Applic. 76, 2 (2017), 9759–9783. Google Scholar
Digital Library
- [24] . 2013. Real-time privacy-preserving moving object detection on the cloud. In Proceedings of the ACM International Conference on Multimedia. 597–600. Google Scholar
Digital Library
- [25] . 2017. An efficient motion detection and tracking scheme for encrypted surveillance videos. ACM Trans. Multim. Comput., Commun. Applic. 13, 4 (2017), 1–23. Google Scholar
Digital Library
- [26] . 2020. Efficient privacy-preserving anomaly detection and localization in bitstream video. IEEE Trans. Circ. Syst. Video Technol. 30, 9 (2020), 3268–3281.Google Scholar
Digital Library
- [27] . 2018. Privacy-preserving cloud-based video surveillance with adjustable granularity of privacy protection. In Proceedings of the 25th IEEE International Conference on Image Processing (ICIP). 4133–4137.Google Scholar
Cross Ref
- [28] . 2014. High Efficiency Video Coding (HEVC): Algorithms and Architectures. Springer Publishing Company Inc., New York, 113–140. Google Scholar
Digital Library
- [29] . 2013. Visual protection of HEVC video by selective encryption of CABAC binstrings. IEEE Trans. Multim. 16, 1 (2013), 24–36.Google Scholar
Cross Ref
- [30] . 1970. Least-squares estimation: From Gauss to Kalman. IEEE Spectrum 7, 7 (1970), 63–68. Google Scholar
Digital Library
- [31] , the EC Funded CAVIAR project/IST 2001. Retrieved from http://homepages.inf.ed.ac.uk/rbf/CAVIAR/.Google Scholar
- [32] . 2015. VAIS: A dataset for recognizing maritime imagery in the visible and infrared spectrums. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 10–16.Google Scholar
Cross Ref
- [33] . LIMU Dataset. Retrieved from http://limu.ait.kyushu-u.ac.jp/dataset/en. (2008).Google Scholar
- [34] . 2011. A large-scale benchmark dataset for event recognition in surveillance video. In Proceedings of the IEEE Computer Vision and Pattern Recognition. 3153–3160. Google Scholar
Digital Library
- [35] . High Efficiency Video Coding (HEVC) Retrieved from https://hevc.hhi.fraunhofer.de/. (2013).Google Scholar
- [36] . 2012. changedetection.net: A new change detection benchmark dataset. In Proceedings of the IEEE Workshop on Change Detection (CDW’12) at CVPR’12.Google Scholar
Cross Ref
- [37] . 2012. changedetection.net: A new change detection benchmark dataset. In Proceedings of the Workshop on Change Detection (CDW-2012) at CVPR-2012. IEEE, 1–8.Google Scholar
Cross Ref
- [38] . 2012. IEEE Change Detection Workshop in conjunction with CVPR. Retrieved from http://jacarini.dinf.usherbrooke.ca/cdw2012/.Google Scholar
Index Terms
Privacy-preserving Motion Detection for HEVC-compressed Surveillance Video
Recommendations
A new encryption scheme for surveillance videos
In this paper, we propose a novel framework to encrypt surveillance videos. Although a few encryption schemes have been proposed in the literature, they are not sufficiently efficient due to the lack of full consideration of the characteristics of ...
Motion detection with pyramid structure of background model for intelligent surveillance systems
This paper proposes a pyramidal background matching structure for motion detection. The proposed method utilizes spectral, spatial, and temporal features to generate a pyramidal structure of the background model. After performing the background ...
Reliable real-time foreground detection for video surveillance applications
VSSN '05: Proceedings of the third ACM international workshop on Video surveillance & sensor networksForeground segmentation is usually needed as an initial step in video surveillance applications. Background subtraction is typically used to segment moving regions by comparing each new frame to a model of the scene background. We present a segmentation ...






Comments