-
公开(公告)号:US20190243851A1
公开(公告)日:2019-08-08
申请号:US16387443
申请日:2019-04-17
Applicant: Gracenote, Inc.
Inventor: Jose Pio Pereira , Sunil Suresh Kulkarni , Shashank Merchant , Prashant Ramanathan , Pradipkumar Dineshbhai Gajjar
IPC: G06F16/48 , G06F16/901 , G06F16/783 , G06F16/22 , G06F16/951 , G06K9/00 , G06F16/28 , G06F16/41 , G06K9/46
CPC classification number: G06F16/48 , G06F16/2255 , G06F16/285 , G06F16/41 , G06F16/783 , G06F16/7847 , G06F16/9014 , G06F16/951 , G06K9/00744 , G06K9/4671 , Y10S707/913
Abstract: The overall architecture and details of a scalable video fingerprinting and identification system that is robust with respect to many classes of video distortions is described. In this system, a fingerprint for a piece of multimedia content is composed of a number of compact signatures, along with traversal hash signatures and associated metadata. Numerical descriptors are generated for features found in a multimedia clip, signatures are generated from these descriptors, and a reference signature database is constructed from these signatures. Query signatures are also generated for a query multimedia clip. These query signatures are searched against the reference database using a fast similarity search procedure, to produce a candidate list of matching signatures. This candidate list is further analyzed to find the most likely reference matches. Signature correlation is performed between the likely reference matches and the query clip to improve detection accuracy.
-
12.
公开(公告)号:US20170201793A1
公开(公告)日:2017-07-13
申请号:US15297658
申请日:2016-10-19
Applicant: Gracenote, Inc.
Inventor: Jose Pio Pereira , Sunil Suresh Kulkarni , Oleksiy Bolgarov , Prashant Ramanathan , Shashank Merchant , Mihailo M. Stojancic
IPC: H04N21/44 , H04N21/442 , H04H60/59 , H04N21/845 , H04N21/8352 , H04H60/37
CPC classification number: H04N21/44008 , G06F21/10 , G06F2221/0704 , G06K9/00758 , H04H20/106 , H04H60/37 , H04H60/56 , H04H60/59 , H04H2201/90 , H04N21/44204 , H04N21/8352 , H04N21/8456
Abstract: A content segmentation, categorization and identification method on consumer devices (clients) is described. Methods for content tracking are illustrated that are suitable for large scale deployment and applications such as broadcast monitoring, novel content publishing and interaction. Time-aligned (synchronous) applications such as multi-language selection, customized advertisements, second screen services and content monitoring applications can be economically deployed at large scales. The client performs fingerprinting, scene change detection, audio turn detection, and logo detection on incoming video and gathers database search results, logos and text to identify and segment video streams into content, promos, and commercials. A learning engine is configured to learn rules for optimal identification and segmentation at each client for each channel and program. Content sensed at the client site is tracked with reduced computation and applications are executed with timing precision. A method and user interface for time-aligned publishing of content and subsequent usage and interaction on one or more displays is described.
-
公开(公告)号:US09646007B2
公开(公告)日:2017-05-09
申请号:US15163004
申请日:2016-05-24
Applicant: Gracenote, Inc.
Inventor: Jose Pio Pereira , Shashank Merchant , Prashant Ramanathan , Sunil Suresh Kulkarni , Mihailo M. Stojancic
IPC: G06F17/30
CPC classification number: G06F17/30038 , G06F17/3002 , G06F17/30029 , G06F17/30377 , G06F17/3056
Abstract: An efficient large scale search system for video and multi-media content using a distributed database and search, and tiered search servers is described. Selected content is stored at the distributed local database and tier1 search server(s). Content matching frequent queries, and frequent unidentified queries are cached at various levels in the search system. Content is classified using feature descriptors and geographical aspects, at feature level and in time segments. Queries not identified at clients and tier1 search server(s) are queried against tier2 or lower search server(s). Search servers use classification and geographical partitioning to reduce search cost. Methods for content tracking and local content searching are executed on clients. The client performs local search, monitoring and/or tracking of the query content with the reference content and local search with a database of reference fingerprints. This shifts the content search workload from central servers to the distributed monitoring clients.
-
公开(公告)号:US09471674B2
公开(公告)日:2016-10-18
申请号:US15073858
申请日:2016-03-18
Applicant: Gracenote, Inc.
Inventor: Prashant Ramanathan , Jose Pio Pereira , Shashank Merchant , Mihailo M. Stojancic
CPC classification number: G06F17/30038 , G06F17/3002 , G06F17/3033 , G06F17/30598 , G06F17/30784 , G06F17/30799 , G06F17/30864 , G06F17/30949 , G06K9/00744 , G06K9/4671 , Y10S707/913
Abstract: The overall architecture and details of a scalable video fingerprinting and identification system that is robust with respect to many classes of video distortions is described. In this system, a fingerprint for a piece of multimedia content is composed of a number of compact signatures, along with traversal hash signatures and associated metadata. Numerical descriptors are generated for features found in a multimedia clip, signatures are generated from these descriptors, and a reference signature database is constructed from these signatures. Query signatures are also generated for a query multimedia clip. These query signatures are searched against the reference database using a fast similarity search procedure, to produce a candidate list of matching signatures. This candidate list is further analyzed to find the most likely reference matches. Signature correlation is performed between the likely reference matches and the query clip to improve detection accuracy.
-
公开(公告)号:US09323754B2
公开(公告)日:2016-04-26
申请号:US14885110
申请日:2015-10-16
Applicant: Gracenote, Inc.
Inventor: Prashant Ramanathan , Jose Pio Pereira , Shashank Merchant , Mihailo M. Stojancic
IPC: G06F17/30
CPC classification number: G06F17/30038 , G06F17/3002 , G06F17/3033 , G06F17/30598 , G06F17/30784 , G06F17/30799 , G06F17/30864 , G06F17/30949 , G06K9/00744 , G06K9/4671 , Y10S707/913
Abstract: The overall architecture and details of a scalable video fingerprinting and identification system that is robust with respect to many classes of video distortions is described. In this system, a fingerprint for a piece of multimedia content is composed of a number of compact signatures, along with traversal hash signatures and associated metadata. Numerical descriptors are generated for features found in a multimedia clip, signatures are generated from these descriptors, and a reference signature database is constructed from these signatures. Query signatures are also generated for a query multimedia clip. These query signatures are searched against the reference database using a fast similarity search procedure, to produce a candidate list of matching signatures. This candidate list is further analyzed to find the most likely reference matches. Signature correlation is performed between the likely reference matches and the query clip to improve detection accuracy.
-
公开(公告)号:US09262421B2
公开(公告)日:2016-02-16
申请号:US14589366
申请日:2015-01-05
Applicant: Gracenote, Inc.
Inventor: Jose Pio Pereira , Shashank Merchant , Prashant Ramanathan , Sunil Suresh Kulkarni , Mihailo Stojancic
IPC: G06F17/30
CPC classification number: G06F17/30038 , G06F17/3002 , G06F17/30029 , G06F17/30377 , G06F17/3056
Abstract: An efficient large scale search system for video and multi-media content using a distributed database and search, and tiered search servers is described. Selected content is stored at the distributed local database and tier1 search server(s). Content matching frequent queries, and frequent unidentified queries are cached at various levels in the search system. Content is classified using feature descriptors and geographical aspects, at feature level and in time segments. Queries not identified at clients and tier1 search server(s) are queried against tier2 or lower search server(s). Search servers use classification and geographical partitioning to reduce search cost. Methods for content tracking and local content searching are executed on clients. The client performs local search, monitoring and/or tracking of the query content with the reference content and local search with a database of reference fingerprints. This shifts the content search workload from central servers to the distributed monitoring clients.
-
公开(公告)号:US20160034452A1
公开(公告)日:2016-02-04
申请号:US14885110
申请日:2015-10-16
Applicant: GRACENOTE, INC.
Inventor: Prashant Ramanathan , Jose Pio Pereira , Shashank Merchant , Mihailo M. Stojancic
IPC: G06F17/30
CPC classification number: G06F17/30038 , G06F17/3002 , G06F17/3033 , G06F17/30598 , G06F17/30784 , G06F17/30799 , G06F17/30864 , G06F17/30949 , G06K9/00744 , G06K9/4671 , Y10S707/913
Abstract: The overall architecture and details of a scalable video fingerprinting and identification system that is robust with respect to many classes of video distortions is described. In this system, a fingerprint for a piece of multimedia content is composed of a number of compact signatures, along with traversal hash signatures and associated metadata. Numerical descriptors are generated for features found in a multimedia clip, signatures are generated from these descriptors, and a reference signature database is constructed from these signatures. Query signatures are also generated for a query multimedia clip. These query signatures are searched against the reference database using a fast similarity search procedure, to produce a candidate list of matching signatures. This candidate list is further analyzed to find the most likely reference matches. Signature correlation is performed between the likely reference matches and the query clip to improve detection accuracy.
-
公开(公告)号:US20190384786A1
公开(公告)日:2019-12-19
申请号:US16553658
申请日:2019-08-28
Applicant: Gracenote, Inc.
Inventor: Prashant Ramanathan , Jose Pio Pereira , Shashank Merchant , Mihailo M. Stojancic
IPC: G06F16/48 , G06K9/46 , G06K9/00 , G06F16/901 , G06F16/783 , G06F16/22 , G06F16/951 , G06F16/28 , G06F16/41
Abstract: The overall architecture and details of a scalable video fingerprinting and identification system that is robust with respect to many classes of video distortions is described. In this system, a fingerprint for a piece of multimedia content is composed of a number of compact signatures, along with traversal hash signatures and associated metadata. Numerical descriptors are generated for features found in a multimedia clip, signatures are generated from these descriptors, and a reference signature database is constructed from these signatures. Query signatures are also generated for a query multimedia clip. These query signatures are searched against the reference database using a fast similarity search procedure, to produce a candidate list of matching signatures. This candidate list is further analyzed to find the most likely reference matches. Signature correlation is performed between the likely reference matches and the query clip to improve detection accuracy.
-
公开(公告)号:US10402443B2
公开(公告)日:2019-09-03
申请号:US15265002
申请日:2016-09-14
Applicant: Gracenote, Inc.
Inventor: Prashant Ramanathan , Jose Pio Pereira , Shashank Merchant , Mihailo M. Stojancic
IPC: G06F16/00 , G06F16/48 , G06F16/41 , G06F16/28 , G06F16/783 , G06F16/951 , G06F16/22 , G06F16/901 , G06K9/00 , G06K9/46
Abstract: The overall architecture and details of a scalable video fingerprinting and identification system that is robust with respect to many classes of video distortions is described. In this system, a fingerprint for a piece of multimedia content is composed of a number of compact signatures, along with traversal hash signatures and associated metadata. Numerical descriptors are generated for features found in a multimedia clip, signatures are generated from these descriptors, and a reference signature database is constructed from these signatures. Query signatures are also generated for a query multimedia clip. These query signatures are searched against the reference database using a fast similarity search procedure, to produce a candidate list of matching signatures. This candidate list is further analyzed to find the most likely reference matches. Signature correlation is performed between the likely reference matches and the query clip to improve detection accuracy.
-
公开(公告)号:US20190251116A1
公开(公告)日:2019-08-15
申请号:US16388750
申请日:2019-04-18
Applicant: Gracenote, Inc.
Inventor: Prashant Ramanathan , Mihailo M. Stojancic
IPC: G06F16/48 , G06F16/901 , G06F16/783 , G06F16/22 , G06F16/951 , G06K9/00 , G06F16/28 , G06F16/41 , G06K9/46
CPC classification number: G06F16/48 , G06F16/2255 , G06F16/285 , G06F16/41 , G06F16/783 , G06F16/7847 , G06F16/9014 , G06F16/951 , G06K9/00744 , G06K9/4671 , Y10S707/913
Abstract: The overall architecture and details of a scalable video fingerprinting and identification system that is robust with respect to many classes of video distortions is described. In this system, a fingerprint for a piece of multimedia content is composed of a number of compact signatures, along with traversal hash signatures and associated metadata. Numerical descriptors are generated for features found in a multimedia clip, signatures are generated from these descriptors, and a reference signature database is constructed from these signatures. Query signatures are also generated for a query multimedia clip. These query signatures are searched against the reference database using a fast similarity search procedure, to produce a candidate list of matching signatures. This candidate list is further analyzed to find the most likely reference matches. Signature correlation is performed between the likely reference matches and the query clip to improve detection accuracy.
-
-
-
-
-
-
-
-
-