350 rub
Journal Highly available systems №1 for 2016 г.
Article in number:
A method of fuzzy image search in large streams of videodata
Authors:
V.L. Arlazarov - Dr. Sc. (Eng.), Corresponding Member of RAS, Head of Department, Institute for Systems Analysis of FRC CSC RAS (Moscow). E-mail: vladimir.arlazarov@gmail.com K.B. Bulatov - Junior Research Scientist, Institute for Systems Analysis of FRC CSC RAS (Moscow). E-mail: hpbuko@gmail.com T.S. Chernov - Junior Research Scientist, Institute for Systems Analysis of FRC CSC RAS (Moscow). E-mail: chernov.tim@gmail.com
Abstract:
In this paper questions are discussed regarding fuzzy search of images and their fragments in streams of videodata in conditions of distorted query. Presented method is based on «bag of points» approach to construction of robust and compact image descriptors, hierarchical clusterization method for primary search and RANSAC method for secondary qualifying search. In intermediary experiments performed with streams of television broadcasting data, when applied for search of video frame fragments, projectively distorted frames and frames with scene shifted in time, the method shows promising results from search «precision» point of view as well as from the point of view of computational efficiency. The research is performed with financial support of RFBR (projects проекты 15-29-06086 ofi_m, 15-29-06083 ofi_m, 16-07-00616 A).
Pages: 53-58
References

 

  1. Alcantarilla P., Bartolli A., Davison A. KAZE features // European Conference on Computer Vision. 2012. P. 214-227.
  2. Andoni A., Indyk P. Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions // Communications of the ACM. 2008. 51(1). P. 117−122.
  3. Bay H., Ess A., Tuytelaars T., Gool L.V. Speeded-Up Robust Features (SURF) // Computer Vision and Image Understanding Archive. 2008. V. 110. № 3. P. 346−359.
  4. Bentley J.L. Multidimensional binary search trees used for associative searching // Communications of the ACM. 1975. V. 19. № 9. P. 509−517.
  5. Beygelzimer A., Kakade S., Langford J. Cover trees for nearest neighbor // Proceedings of the 23rd international conference on Machine Learning. 2006. P. 97−104.
  6. Bilaniuk O., Bazargani H., Laganiere R. Fast Target Recognition on Mobile Devices: Revisiting Gaussian Elimination for the Estimation of Planar Homographies // IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2014. P. 119−125.
  7. Calonder M., Lepetit V., Ozuysal M., Trzchinski T., Strecha C., Fua P. BRIEF: Computing a local binary descriptor very fast // IEEE Transaction on Pattern Analysis and Machine Intelligence. 2012. V. 33. № 7. P. 1281−1298.
  8. Chum O., Matas J. Matching with PROSAC - progressive sample consensus // IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). 2005. V. 1. P. 220−226.
  9. Fan B., Kong Q., Trzcinski T., Wang Z., Pan C., Fua P. Receptive Fields Selection for Binary Feature Description // IEEE Transactions on Image Processing. 2014. V. 23. № 6. P. 2583−2595.
  10. Fischler M.A., Bolles R.C. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography // Communications of the ACM. 1981. V. 24. P. 381−395.
  11. Ionescu B., Coquin D., Lambert P., Buzuloiu V. An Approach to Scene Detection in Animation Movies and its Applications // U.P.B. Scientific Bulletin. SeriesC. 2005. V. 67. № 2. P. 45−57.
  12. Juah L., Oubong G. SURF applied in panorama image stitching // 2nd International Conference on Image Processing Theory Tools and Applications (IPTA). 2010. P. 495−499.
  13. Ke Y., Sukthankar R. PCA-SIFT: a more distinctive representation for local image descriptors // Proc. of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2004). 2004. V. 2. P. 506−513.
  14. Lepetit V., Fua P. Towards Recognizing Feature Points using Classification Trees // Technical Report IC/2004/74. ÉcolepolytechniquefédéraledeLausanne. 2004.
  15. Liu W., etal. Listen, look, andgotcha: instantvideosearchwithmobilephonesbylayeredaudio-videoindexing // Proceedingsofthe 21stACMinternationalconferenceonMultimedia. ACM. 2013.
  16. Lowe D.G. Distinctive Image Features from Scale-Invariant Keypoints // International Journal of Computer Vision Archive. 2004. V. 60. № 2. P. 91−110.
  17. Norouzi M., Punjani A., Fleet D.J. Fast search in Hamming space with multi-index hashing // IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2012). 2012. P. 3108−3115.
  18. Ortiz R., Alahi A., Vandergheynst P. FREAK: Fast Retina Keypoint // IEEE Conference on Computer Vision and Pattern Recognition. 2012. P. 510−517.
  19. Rocach L., Maimon O. Clustering methods. Data mining and knowledge discovery handbook // Springer US. 2005. P. 321−352.
  20. Yang Y., Shan M. Complex Events Detection using Data-driven Concepts // Computer Vision - ECCV 2012. V. 7574 of the series Lecture Notes in Computer Science. 2012. P. 722−735.
  21. Yeh C.-Y., etal. Me-link: link me to the media-fusing audio and visual cues for robust and efficient mobile media interaction // Proceedings of the companion publication of the 23rd international conference on World wide web companion. International World Wide Web Conferences Steering Committee. 2014.