Copy detection of 3D videos

Naghmeh Khodabakhshi, Mohamed Hefeeda

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

We present a novel system to detect copies of 3D videos. The system creates signatures from the depth signals of 3D videos. It also extracts visual features from video frames and creates compact spatial signatures for videos. The system then uses the depth and spatial signatures to compare a given query video versus a reference video database. The system returns a score indicating whether the query video matches any video in the reference video database, and in case of matching, which portion of the reference video matches the query video. The system is computationally efficient and can be implemented in distributed manner. The system can be used, for example, by video content owners, video hosting sites, and third-party companies to find illegally copied 3D videos. To the best of our knowledge, this is the first complete 3D video copy detection system in the literature. We implemented the proposed system and conducted a rigorous evaluation study using 3D videos with diverse properties. Our experimental results show that the proposed system can achieve high accuracy in terms of precision and recall even if the 3D videos are subjected to several transformations at the same time. For example, the proposed system yields 100% precision and recall when copied videos are parts of original videos, and more than 90% precision and recall when copied videos are subjected to different individual transformations.

Original languageEnglish
Title of host publicationMMSys'12 - Proceedings of the 3rd Multimedia Systems Conference
Pages131-142
Number of pages12
DOIs
Publication statusPublished - 28 Mar 2012
Event3rd ACM Multimedia Systems Conference, MMSys'12 - Chapel Hill, NC, United States
Duration: 22 Feb 201224 Feb 2012

Other

Other3rd ACM Multimedia Systems Conference, MMSys'12
CountryUnited States
CityChapel Hill, NC
Period22/2/1224/2/12

Fingerprint

Industry

Keywords

  • 3D video
  • depth features
  • video copy detection
  • video fingerprinting
  • visual features

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Software

Cite this

Khodabakhshi, N., & Hefeeda, M. (2012). Copy detection of 3D videos. In MMSys'12 - Proceedings of the 3rd Multimedia Systems Conference (pp. 131-142) https://doi.org/10.1145/2155555.2155578

Copy detection of 3D videos. / Khodabakhshi, Naghmeh; Hefeeda, Mohamed.

MMSys'12 - Proceedings of the 3rd Multimedia Systems Conference. 2012. p. 131-142.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Khodabakhshi, N & Hefeeda, M 2012, Copy detection of 3D videos. in MMSys'12 - Proceedings of the 3rd Multimedia Systems Conference. pp. 131-142, 3rd ACM Multimedia Systems Conference, MMSys'12, Chapel Hill, NC, United States, 22/2/12. https://doi.org/10.1145/2155555.2155578
Khodabakhshi N, Hefeeda M. Copy detection of 3D videos. In MMSys'12 - Proceedings of the 3rd Multimedia Systems Conference. 2012. p. 131-142 https://doi.org/10.1145/2155555.2155578
Khodabakhshi, Naghmeh ; Hefeeda, Mohamed. / Copy detection of 3D videos. MMSys'12 - Proceedings of the 3rd Multimedia Systems Conference. 2012. pp. 131-142
@inproceedings{8785081bd8dc4597bdf8bccad21b627f,
title = "Copy detection of 3D videos",
abstract = "We present a novel system to detect copies of 3D videos. The system creates signatures from the depth signals of 3D videos. It also extracts visual features from video frames and creates compact spatial signatures for videos. The system then uses the depth and spatial signatures to compare a given query video versus a reference video database. The system returns a score indicating whether the query video matches any video in the reference video database, and in case of matching, which portion of the reference video matches the query video. The system is computationally efficient and can be implemented in distributed manner. The system can be used, for example, by video content owners, video hosting sites, and third-party companies to find illegally copied 3D videos. To the best of our knowledge, this is the first complete 3D video copy detection system in the literature. We implemented the proposed system and conducted a rigorous evaluation study using 3D videos with diverse properties. Our experimental results show that the proposed system can achieve high accuracy in terms of precision and recall even if the 3D videos are subjected to several transformations at the same time. For example, the proposed system yields 100{\%} precision and recall when copied videos are parts of original videos, and more than 90{\%} precision and recall when copied videos are subjected to different individual transformations.",
keywords = "3D video, depth features, video copy detection, video fingerprinting, visual features",
author = "Naghmeh Khodabakhshi and Mohamed Hefeeda",
year = "2012",
month = "3",
day = "28",
doi = "10.1145/2155555.2155578",
language = "English",
isbn = "9781450311311",
pages = "131--142",
booktitle = "MMSys'12 - Proceedings of the 3rd Multimedia Systems Conference",

}

TY - GEN

T1 - Copy detection of 3D videos

AU - Khodabakhshi, Naghmeh

AU - Hefeeda, Mohamed

PY - 2012/3/28

Y1 - 2012/3/28

N2 - We present a novel system to detect copies of 3D videos. The system creates signatures from the depth signals of 3D videos. It also extracts visual features from video frames and creates compact spatial signatures for videos. The system then uses the depth and spatial signatures to compare a given query video versus a reference video database. The system returns a score indicating whether the query video matches any video in the reference video database, and in case of matching, which portion of the reference video matches the query video. The system is computationally efficient and can be implemented in distributed manner. The system can be used, for example, by video content owners, video hosting sites, and third-party companies to find illegally copied 3D videos. To the best of our knowledge, this is the first complete 3D video copy detection system in the literature. We implemented the proposed system and conducted a rigorous evaluation study using 3D videos with diverse properties. Our experimental results show that the proposed system can achieve high accuracy in terms of precision and recall even if the 3D videos are subjected to several transformations at the same time. For example, the proposed system yields 100% precision and recall when copied videos are parts of original videos, and more than 90% precision and recall when copied videos are subjected to different individual transformations.

AB - We present a novel system to detect copies of 3D videos. The system creates signatures from the depth signals of 3D videos. It also extracts visual features from video frames and creates compact spatial signatures for videos. The system then uses the depth and spatial signatures to compare a given query video versus a reference video database. The system returns a score indicating whether the query video matches any video in the reference video database, and in case of matching, which portion of the reference video matches the query video. The system is computationally efficient and can be implemented in distributed manner. The system can be used, for example, by video content owners, video hosting sites, and third-party companies to find illegally copied 3D videos. To the best of our knowledge, this is the first complete 3D video copy detection system in the literature. We implemented the proposed system and conducted a rigorous evaluation study using 3D videos with diverse properties. Our experimental results show that the proposed system can achieve high accuracy in terms of precision and recall even if the 3D videos are subjected to several transformations at the same time. For example, the proposed system yields 100% precision and recall when copied videos are parts of original videos, and more than 90% precision and recall when copied videos are subjected to different individual transformations.

KW - 3D video

KW - depth features

KW - video copy detection

KW - video fingerprinting

KW - visual features

UR - http://www.scopus.com/inward/record.url?scp=84858781681&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858781681&partnerID=8YFLogxK

U2 - 10.1145/2155555.2155578

DO - 10.1145/2155555.2155578

M3 - Conference contribution

AN - SCOPUS:84858781681

SN - 9781450311311

SP - 131

EP - 142

BT - MMSys'12 - Proceedings of the 3rd Multimedia Systems Conference

ER -