220 likes | 376 Views
Robust video fingerprinting system. Daniel Pereira d.pereira@skillupjapan.co.jp Luis Loyola loyola@skillupjapan.co.jp. Robust video fingerprinting system. Summary Purpose of the system What is video fingerprinting Practical problems to solve Proposed solution Results analysis. 2.
E N D
Robust video fingerprinting system Daniel Pereira d.pereira@skillupjapan.co.jp Luis Loyola loyola@skillupjapan.co.jp
Robust video fingerprinting system • Summary • Purpose of the system • What is video fingerprinting • Practical problems to solve • Proposed solution • Results analysis 2
Robust video fingerprinting system • Purpose of the system • SkillUpJapan distributes digital contents • FujiTV, TV Tokyo, SkyPerfecTV, Warner Brothers Japan, … • Our platform, Uliza, is an extensible digital content management system • Piracy and DRM are of importance to digital contents rights holders 3
Robust video fingerprinting system • Video fingerprinting • A way to effectively tie a video, or a segment of it, to a unique hash value • Information needs to be stored and searched efficiently • Avoid to store original contents provided by clients • Contents should not be recreated from said fingerprint 4
Robust video fingerprinting system • Key technical aspects about video • Measured characteristics • Luma and chroma (brightness and color components) • Edge detection, gradient orientation • Time variance • A movie is, after all, a sequence of images that change over time at a defined rate • Amount of data per frame 5
Robust video fingerprinting system • Efficiency metrics • Uniqueness • Accurately find videos we search; not return videos that are not what we search • Database • Efficiently index the results in a database • Solution must be fast • Find the clip among many other videos in fastest time 6
Robust video fingerprinting system • Some practical problems to solve • Current solutions have relatively accurate algorithms, however the process is computationally expensive • Partitioning of frames, complex algorithm • Database storage is not taken seriously • It is unaffordable to store information for every frame, or large arrays of information for each fingerprint • Slow search times when database grows 7
Robust video fingerprinting system • Proposed solution • Lowers the needed resources and process time, while improving upon results (Luma and time based indexes) • Addresses algorithmic complexity by using simple methods (Euclidean distance of vectors and Tanimoto correlation) • Stores information in an efficient way, allowing for quick retrievals, with use of Look-up Tables 8
Robust video fingerprinting system Luma Luma Threshold • Proposed solution (video properties): • Average the Luma value of each frame • Luma values show prolonged, relatively constant, values that can be indexed to an interval of time Time Time 9
Robust video fingerprinting system • Proposed solution (video properties): • Average Luma calculated according to Luma …… Time 10
Robust video fingerprinting system Luma 140 120 85 • Proposed solution (database): • Using those indexes to store only segments we can save lots of space • Each segment of several seconds has a value of 2 bytes • Luma values range from 0 to 255 • Look-up table for segments 16.0 85 Luma Time 19.4 110 2.0 120 2.0 10.3 16.0 19.4 21.4 time 21.4 120 10.3 140 11
Robust video fingerprinting system Fingerprints on database Fingerprint A Comparisons • Proposed solution (database): Luma 9 85 19 125 Luma 9 85 Luma Time Time Time 2 120 12 110 4 10 32 13 2 120 12 110 5 140 … … … … 15 160 5 140 … … … Fingerprint A Fingerprint 1 Fingerprint 3 Time 12
B A C Robust video fingerprinting system • Proposed solution (algorithm): • Tanimoto • Tanimoto makes a correlation between C and the remaining elements outside C • Euclidean vector distance 13
Robust video fingerprinting system • Proposed solution (algorithm): • Hierarchical approach • Look-up Table of segments • Compares the time indexes • & 4. Tanimoto Correlation and Vector Distance of Luma • Look-up Tables discard perceptually different movies efficiently • Comparison of time indexes also behaves efficiently • The number of movies that are ultimately analyzed with Tanimoto Correlation and Euclidean Vector Distance is very low 14
Robust video fingerprinting system • Evaluation of algorithm: • 220 movies were analyzed with each other • Quality varies from FullHD to SD • Duration ranges from 15 second commercials to full length movies • Frame-rate of movies varies from 15fps to 30fps • Comparison against C.G.O. (Centroids of Gradient Orientation) [1] • Tests were conducted by searching scenes of 10 seconds • Evaluation compares algorithm, database size and robustness of solutions [1] Sunil Lee and Chang D. Yoo, “Robust Video Fingerprinting for Content-Based Video Identification”, IEEE Trans. Circuits and Systems for Video Technology, vol. 18, no. 7, pp983-988, July, 2008 15
Robust video fingerprinting system • Obtained results (database size): 16
Robust video fingerprinting system • Obtained results (run-time): 17
Robust video fingerprinting system • Obtained results (robustness): 18
Robust video fingerprinting system • Summary • State of the art solutions need to better address practical issues • The proposed algorithm can improve upon state of the art algorithms on storage and speed of analysis • Evaluation shows that the proposed solution also provides higher robustness 20
Robust video fingerprinting system Questions? Daniel Pereira d.pereira@skillupjapan.co.jp Luis Loyola loyola@skillupjapan.co.jp 21
Robust video fingerprinting system Daniel Pereira d.pereira@skillupjapan.co.jp Luis Loyola loyola@skillupjapan.co.jp