350 rub
Journal Neurocomputers №9 for 2015 г.
Article in number:
Near-duplicate video retrieval methods
Keywords: MSA Gale-Church algorithm frame bag of visual words locality-sensitive hashing movement measure ordinal measure scenes shot descriptor video mining
Authors:
I.K. Nikitin - Рost-graduate student, Moscow Aviation Institute. E-mail: w@w-495.ru
Abstract:
Near duplicate video retrieval techniques implement the following steps. 1. Video is divided into segments. 2. Keyframes are extracted from each segment. 3. Features are extracted from keyframes. Keyframe features represent the whole video. 4. The similarity between the videos is calculated as a similarity between keyframe features. There are methods using global features and the local ones. Local methods reduce the problem of finding similar videos to the problem of finding image duplicates. The paper discusses the local methods: tracing the trajectories of the points of interest in the frame; comparison of the points of interest in keyframes; bag of visual keywords. Global methods simulate the spatial, temporal and color information of frames and scenes. The similarity between the video query and the videos from database is defined as the similarity of video signatures. Global features are useful for retrieve «almost identical» videos and can identify minor changes in the space-time domain. In this paper we consider several ways to built global signatures: locally sensitive hashing; ordinal measure; video DNA-representation; shot change positions; the shot change tree. At the end the combination of methods within a novel shot descriptor is 0proposed. The descriptor consists of: a vector of the relations of shot lengths to lengths of other shots (relative shot lengths) as a global feature; features of initial and final frames as local ones.
Pages: 60-66
References

 

  1. Law-ToJ., BuissonO., Gouet-BrunetV., BoujemaaN. Robust voting algorithm based on labels of behavior for video copy detection // InProceedings of the 14th Annual ACM International Conference on Multimedia, MULTIMEDIA - 06.New York. NY. USA. 2006. ACM. P. 835-844.
  2. VaiapuryK., AtreyP.K., KankanhalliM.S., RamakrishnanK. Non identical duplicate video detection using the sift method // In Visual Information Engineering. IET International Conference on.2006. P.537-542.
  3. DouzeM., GaidonA., JégouH., MarszalekM., SchmidC. INRIA-LEARs video copy detection system // In TREC Video Retrieval Evaluation (TRECVID Workshop), Gaithersburg, United States. 2008.
  4. Wei Dong, Zhe Wang, Moses Charikar, Kai Li. Efficiently matching sets of features with random histograms // In Proceedings of the 16th ACM International Conference on Multimedia, MM - 08. New York. USA. 2008. ACM. 13. P. 179-188.
  5. Wan-Lei Zhao, Song Tan, and Chong-Wah Ngo. Large-scale near-duplicate web video search: Challenge and opportunity // In Multimedia and Expo. 2009. ICME June 2009. IEEE International Conference on. P. 1624-1627.
  6. Xian-Sheng Hua, Xian Chen, and Hong-Jiang Zhang. Robust video signature based on ordinal measure // In Image Processing, 2004. ICIP - 04. International Conference on. 2004. V. 1. P. 685-688.
  7. Hyun K. Hampapur A., Bolle R. Comparison of sequence matching techniques for video copy detection // In Storage and Retrieval for Media Databases. 2002. P.194-201.
  8. WangY., BelkhatirM., TahaynaB. Near-duplicate video retrieval based on clustering by multiple sequence alignment // In Proceedings of the 20th ACM International Conference on Multimedia, MM - 12.2012. P. 941-944. New York. USA. ACM.
  9. EdgarR.C. Muscle: multiple sequence alignment with high accuracy and high throughput // Nucleic Acids Res.2004. V. 14. № 32. P. 1792-1797.
  10. WuP.-H., ThaipanichT.,Kuo C.-C.J. A suffix array approach to video copy detection in video sharing social networks // In Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on. April 2009.P. 3465-3468.
  11. ManberU.,MyersG.. Suffix arrays: A new method for on-line string searches // In Proceedings of the First Annual ACM-SIAM Symposium on Discrete Algorithms, SODA - 90. Philadelphia, PA, USA. Society for Industrial and Applied Mathematics. 1990. P. 319-327.
  12. Parshin A.E. Glazistov I.V. Algoritm poiska dublikatov v baze videoposledovatelnostejj na osnove sopostavlenija ierarkhii smen scen. M.: VMiKMGU. 2010.
  13. GaleW.A.,ChurchK.W. A program for aligning sentences in bilingual corpora // Comput. Linguist. 1993.V.19. №1. P.75-102.