DISTRIBUTED VIDEO IDENTIFICATION WITH PERCEPTUAL TAGS IN PEER-TO-PEER NETWORKS

Yıl 2018, Cilt: 19 Sayı: 1, 132 - 143, 31.03.2018

Alper Koz

https://doi.org/10.18038/aubtda.330958

Öz

Existing methods in Peer-to-Peer (P2P)
networks mainly use file tags or cryptographic hashes of the entire file for
video searching and identification. These methods however become insufficient
to correctly identify a video when the name and format of the files are
changed. In this paper, a distributed solution is proposed for video
identification and copy detection in P2P networks, which represents a video file
in the network with a set of (64-256) bits, named as perceptual tags. As such
information is derived from the perceptual content of the video rather than its
bitstream representation as in the case of cryptographic hashes, it provides a
robust identification after the alterations in the file names and formats provided
that the visual quality of the video is at acceptable levels. The paper first
briefly discusses the requirements for a distributed perceptual tagging system
considering the low computational power and low bandwidth of internet users.
Then, it presents the proposed perceptual tag extraction method using the
temporal differences between the video frame averages and the proposed
distributed searching scheme for a P2P implementation. The proposed extraction
and searching methods provide robustness to the alterations in video formats
and small additions and cuttings in the video content as the typical processing
in P2P environment and also achieve uniform distribution and storage load
between the peers.

Anahtar Kelimeler

Perceptual tags, peer to peer networks, content search, distributed video identification, distributed hash tables

Kaynakça

• [1] B. Cohen, “The BitTorrent Protocol Specification”, [Online]. Available: http://www.bittorrent.org/
• [2] J.A. Pouwelse, P. Garbacki, D.H.J. Epema, H.J. Sips, “The Bittorrent P2P File-sharing System: Measurements and Analysis”, IPTPS'05, Feb 2005.
• [3] Cisco Visual Networking Index: Forecast and Methodology, 2013-2018 (White paper). [Online]: https://www.cisco.com/c/en/us/solutions/collateral/service-provider/ip-ngn-ip-next-generation-network/white_paper_c11-481360.pdf
• [4] T. Kalker, D.H.J. Epema, P.H. Hartel, R.L. Lagendijk, M. van Steen, “Music2Share—Copyright-Compliant Music Sharing in P2P Systems”, PIEEE, 92(6):961-970 (2004).
• [5] D. Kundur, Z. Liu, M. Merabti, and H. Yu, “Advances in Peer-to-Peer Content Search”, in Proc. IEEE Int. Conf. Multimedia and Expo, 2007, pp. 404-407.
• [6] A. Jantunen, S. Peltotalo, J. Peltotalo, “Peer-to-Peer Analysis: State-of-the-art”, Tech. Rep., February 2006, Tampere University of Technology, [Online]. Available: http://delco.cs.tut.fi/doc/other/p2p_analysis_v01.pdf
• [7] Y. Kulbak and D. Bickson, “ The eMule Protocol Specification”, Technical Report, DANSS Lab, The Hebrew University of Jerusalem, Israel, Jan. 2005.
• [8] A.Koz and R.(Inald) L. Lagendijk, “Distributed Content Based Video Identification in P2P Networks: Requirements and Solutions”, in IEEE Trans. on Multimedia, pp. ,Vol. 19, No. 3, pp. 475-491, March 2017.
• [9] J. Law-To, L. Chen, A. Joly, I. Laptev, O. Buisson, V. Gouet-Brunet, N. Boujemaa, F. Stentiford, “Video Copy Detection: A Comparative Study”, in Proc. 6th ACM Conference on Image and Video Retrieval - CIVR , pp. 371-378, 2007.
• [10] W.-L. Zhao and C.-W. Ngo, “Flip-Invariant SIFT for Copy and Object Detection”, IEEE Trans. on Image Processing, Vol. 22, No. 3, March 2013.
• [11] B. Coskun, B. Sankur, and N. Memon, “Spatio-temporal transform-based video hashing”, IEEE TMM, 8(6):1190–1208, 2006.
• [12] A.Koz and R.(Inald) L. Lagendijk, “Perceptual Tagging of Video Files in P2P Networks”, in Proc. IEEE Int. Conf. on Image Proc., pp. 193-196, Sept.2010.
• [13] S.-C.Cheung, A. Zakhor, “Estimation of web video multiplicity”, Proc. SPIE, vol. 3964, p. 34-46, Jan. 2000.
• [14] A. Hampapur and R. Balle, “VideoGREP: Video Copy Detection using Inverted File Indices”, Tech. Rep., IBM Research 2002.
• [15] J. Oostveen, T. Kalker, J. Haitsma, “Feature Extraction and a Database Strategy for Video Fingerprinting”, VISUAL 2002: 117-128.
• [16] S. Ratnasamy, P. Francis, M. Handley, R. M. Karp, S. Shenker, “A scalable content-addressable network”, SIGCOMM 2001: 161-172.
• [17] Clay Shirky, “Listening to Naspter”, Chapter 2 in “Peer-to-Peer: Harnessing the Power of Distruptive Technologies”, Editor: Andy Oram, 2001, O’Reilly.
• [18] J. Liang, R. Kumar and K.W.Ross, “The Kazaa Overlay: A measurement Study”, Computer Networks (Special Issue on Overlays), 2005
• [19] J. Pouwelse, P. Garbacki, J. Wang, A. Bakker, J. Yang, A. Losup, D. H. J. Epema, M. Reinders, M. R. van Steen, H. J. Sips, “Tribler: A Social-Based Peer-to-Peer System”, Concurrency and Computation: Practice and Experience, pp. 127-138, 2008.
• [20] I. Stoica, R. Morris, D. Liben-Nowell, D. R. Karger, M. F. Kaashoek, F. Dabek and H. Balakrishnan, “Chord: A Scalable Peer-to-peer Lookup Protocol for Internet Applications”, IEEE/ACM Trans. on Networking, Vol. 11, No. 1, pp. 17-32, 2003.
• [21] Z. Xinxing, T. Zhihong, and Z. Luchen, “A measurement Study on Mainline DHT and Magnet Link”, in Proc. IEEE Int. Conf. on Data Science in Cyberspace, 2016.