Processing

Please wait...

Settings

Settings

Goto Application

1. WO2011045424 - METHOD FOR DETECTING AUDIO AND VIDEO COPY IN MULTIMEDIA STREAMS

Publication Number WO/2011/045424
Publication Date 21.04.2011
International Application No. PCT/EP2010/065551
International Filing Date 15.10.2010
IPC
G06F 17/30 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
17Digital computing or data processing equipment or methods, specially adapted for specific functions
30Information retrieval; Database structures therefor
G06K 9/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
CPC
G06F 16/7834
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
70of video data
78Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
783using metadata automatically derived from the content
7834using audio features
G06F 16/7847
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
70of video data
78Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
783using metadata automatically derived from the content
7847using low-level visual features of the video content
G06K 9/00536
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
00496Recognising patterns in signals and combinations thereof
00536Classification; Matching
G06K 9/00758
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
00711Recognising video content, e.g. extracting audiovisual features from movies, extracting representative key-frames, discriminating news vs. sport content
00758Matching video sequences
G10L 25/00
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
25Speech or voice analysis techniques not restricted to a single one of groups G10L15/00-G10L21/00
G10L 25/06
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
25Speech or voice analysis techniques not restricted to a single one of groups G10L15/00-G10L21/00
03characterised by the type of extracted parameters
06the extracted parameters being correlation coefficients
Applicants
  • TELEFONICA, S.A. [ES]/[ES] (AllExceptUS)
  • ANGUERA MIRO, Xavier [ES]/[ES] (UsOnly)
  • OBRADOR ESPINOSA, Pere [ES]/[ES] (UsOnly)
  • OLIVER RAMIREZ, Nuria [ES]/[ES] (UsOnly)
Inventors
  • ANGUERA MIRO, Xavier
  • OBRADOR ESPINOSA, Pere
  • OLIVER RAMIREZ, Nuria
Agents
  • CARPINTERO LOPEZ, Francisco
Priority Data
09382213.816.10.2009EP
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) METHOD FOR DETECTING AUDIO AND VIDEO COPY IN MULTIMEDIA STREAMS
(FR) PROCÉDÉ DE DÉTECTION DE COPIE AUDIO ET VIDÉO DANS DES FLUX MULTIMÉDIAS
Abstract
(EN)
This invention proposes a multimodal detection of video copies. It first extracts independent audio and video fingerprints representing the changes in the content. It then proposes two alternative copy detection strategies. The full-query matching considers that the query video appears entirely in the queried video. The partial-query matching considers that only part of the query appears. Either for the full query or for each subsegment in the partial-query algorithm, the cross-correlation with phase transform is computed between all signature pairs and accumulated to form a fused cross-correlation signal. In the full-query algorithm, the best alignment candidates are retrieved and a normalized scalar product is used to obtain a final matching score. In the partial query, a histogram is created with optimum alignments for each subsegment and only the best ones are considered and further processed as in the full-query. A threshold is used to determine whether a copy exists.
(FR)
Cette invention propose une détection multimodale de copies vidéo. Des empreintes numériques audio et vidéo indépendantes représentant les changements dans le contenu sont d'abord extraites. Deux stratégies de détection de copie différentes sont ensuite proposées. L'appariement de requête complète considère que la vidéo d'interrogation apparaît entièrement dans la vidéo interrogée. L'appariement de requête partielle considère qu'une partie seulement de l'interrogation apparaît. Soit pour la requête complète soit pour chaque sous-segment dans l'algorithme de requête partielle, l'intercorrélation avec transformation de phase est calculée entre toutes les paires de signatures et accumulée pour former un signal d'intercorrélation fusionné. Dans l'algorithme de requête complète, les candidats de meilleur alignement sont récupérés et un produit scalaire normalisé est utilisé pour obtenir un score d'appariement final. Dans la requête partielle, un histogramme est créé avec des alignements optimaux pour chaque sous-segment et seuls les meilleurs sont considérés et ensuite traités comme dans la requête complète. Un seuil est utilisé pour déterminer si une copie existe ou non.
Latest bibliographic data on file with the International Bureau