Patents by Inventor Prashant Ramanathan
Prashant Ramanathan has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 10579668Abstract: 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.Type: GrantFiled: October 8, 2019Date of Patent: March 3, 2020Assignee: Gracenote, Inc.Inventors: Prashant Ramanathan, Mihailo M. Stojancic
-
Publication number: 20190384786Abstract: 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.Type: ApplicationFiled: August 28, 2019Publication date: December 19, 2019Inventors: Prashant Ramanathan, Jose Pio Pereira, Shashank Merchant, Mihailo M. Stojancic
-
Publication number: 20190379931Abstract: A mobile device responds in real time to media content presented on a media device, such as a television. The mobile device captures temporal fragments of audio-video content on its microphone, camera, or both and generates corresponding audio-video query fingerprints. The query fingerprints are transmitted to a search server located remotely or used with a search function on the mobile device for content search and identification. Audio features are extracted and audio signal global onset detection is used for input audio frame alignment. Additional audio feature signatures are generated from local audio frame onsets, audio frame frequency domain entropy, and maximum change in the spectral coefficients. Video frames are analyzed to find a television screen in the frames, and a detected active television quadrilateral is used to generate video fingerprints to be combined with audio fingerprints for more reliable content identification.Type: ApplicationFiled: June 14, 2019Publication date: December 12, 2019Inventors: Mihailo M. Stojancic, Daniel H. Eakins, Shashank Merchant, Prashant Ramanathan, Jose Pio Pereira
-
Publication number: 20190379929Abstract: A mobile device responds in real time to media content presented on a media device, such as a television. The mobile device captures temporal fragments of audio-video content on its microphone, camera, or both and generates corresponding audio-video query fingerprints. The query fingerprints are transmitted to a search server located remotely or used with a search function on the mobile device for content search and identification. Audio features are extracted and audio signal global onset detection is used for input audio frame alignment. Additional audio feature signatures are generated from local audio frame onsets, audio frame frequency domain entropy, and maximum change in the spectral coefficients. Video frames are analyzed to find a television screen in the frames, and a detected active television quadrilateral is used to generate video fingerprints to be combined with audio fingerprints for more reliable content identification.Type: ApplicationFiled: June 14, 2019Publication date: December 12, 2019Inventors: Mihailo M. Stojancic, Daniel H. Eakins, Shashank Merchant, Prashant Ramanathan, Jose Pio Pereira
-
Publication number: 20190379930Abstract: A mobile device responds in real time to media content presented on a media device, such as a television. The mobile device captures temporal fragments of audio-video content on its microphone, camera, or both and generates corresponding audio-video query fingerprints. The query fingerprints are transmitted to a search server located remotely or used with a search function on the mobile device for content search and identification. Audio features are extracted and audio signal global onset detection is used for input audio frame alignment. Additional audio feature signatures are generated from local audio frame onsets, audio frame frequency domain entropy, and maximum change in the spectral coefficients. Video frames are analyzed to find a television screen in the frames, and a detected active television quadrilateral is used to generate video fingerprints to be combined with audio fingerprints for more reliable content identification.Type: ApplicationFiled: June 14, 2019Publication date: December 12, 2019Inventors: Mihailo M. Stojancic, Daniel H. Eakins, Shashank Merchant, Prashant Ramanathan, Jose Pio Pereira
-
Patent number: 10423654Abstract: 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.Type: GrantFiled: March 16, 2019Date of Patent: September 24, 2019Assignee: Gracenote, Inc.Inventors: Prashant Ramanathan, Jose Pio Pereira, Shashank Merchant, Mihailo M. Stojancic
-
Patent number: 10402443Abstract: 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.Type: GrantFiled: September 14, 2016Date of Patent: September 3, 2019Assignee: Gracenote, Inc.Inventors: Prashant Ramanathan, Jose Pio Pereira, Shashank Merchant, Mihailo M. Stojancic
-
Patent number: 10387482Abstract: 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.Type: GrantFiled: April 18, 2019Date of Patent: August 20, 2019Assignee: Gracenote, Inc.Inventors: Prashant Ramanathan, Mihailo M. Stojancic
-
Publication number: 20190251112Abstract: 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.Type: ApplicationFiled: April 16, 2019Publication date: August 15, 2019Inventors: Mihailo M. Stojancic, Prashant Ramanathan, Peter Wendt, Jose Pio Pereira
-
Publication number: 20190251114Abstract: 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.Type: ApplicationFiled: April 17, 2019Publication date: August 15, 2019Inventors: Jose Pio Pereira, Sunil Suresh Kulkarni, Shashank Merchant, Prashant Ramanathan, Pradipkumar Dineshbhai Gajjar
-
Publication number: 20190251116Abstract: 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.Type: ApplicationFiled: April 18, 2019Publication date: August 15, 2019Inventors: Prashant Ramanathan, Mihailo M. Stojancic
-
Publication number: 20190251115Abstract: 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.Type: ApplicationFiled: April 18, 2019Publication date: August 15, 2019Inventors: Prashant Ramanathan, Mihailo M. Stojancic
-
Publication number: 20190251113Abstract: 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.Type: ApplicationFiled: April 17, 2019Publication date: August 15, 2019Inventors: Jose Pio Pereira, Sunil Suresh Kulkarni, Shashank Merchant, Prashant Ramanathan, Pradipkumar Dineshbhai Gajjar
-
Publication number: 20190243851Abstract: 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.Type: ApplicationFiled: April 17, 2019Publication date: August 8, 2019Inventors: Jose Pio Pereira, Sunil Suresh Kulkarni, Shashank Merchant, Prashant Ramanathan, Pradipkumar Dineshbhai Gajjar
-
Publication number: 20190243852Abstract: 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.Type: ApplicationFiled: April 18, 2019Publication date: August 8, 2019Inventors: Prashant Ramanathan, Mihailo M. Stojancic
-
Publication number: 20190228030Abstract: 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.Type: ApplicationFiled: March 28, 2019Publication date: July 25, 2019Inventors: Prashant Ramanathan, Jose Pio Pereira, Shashank Merchant, Mihailo M. Stojancic
-
Publication number: 20190220478Abstract: 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.Type: ApplicationFiled: March 26, 2019Publication date: July 18, 2019Inventors: Prashant Ramanathan, Jose Pio Pereira, Shashank Merchant, Mihailo M. Stojancic
-
Publication number: 20190213210Abstract: 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.Type: ApplicationFiled: March 16, 2019Publication date: July 11, 2019Inventors: Prashant Ramanathan, Jose Pio Pereira, Shashank Merchant, Mihailo M. Stojancic
-
Patent number: 9785708Abstract: An architecture for a multimedia search system is described. To perform similarity matching of multimedia query frames against reference content, reference database comprising of a cluster index using cluster keys to perform similarity matching and a multimedia index to perform sequence matching is built. Methods to update and maintain the reference database that enables addition and removal of the multimedia contents, including portions of multimedia content, from the reference database in a running system are described. Hierarchical multi-level partitioning methods to organize the reference database are presented. Smart partitioning of the reference multimedia content according to the nature of the multimedia content, and according to the popularity among the social media, that supports scalable fast multimedia identification is also presented.Type: GrantFiled: May 21, 2015Date of Patent: October 10, 2017Assignee: GRACENOTE, INC.Inventors: Sunil Suresh Kulkarni, Jose Pio Pereira, Pradipkumar Dineshbhai Gajjar, Shashank Merchant, Prashant Ramanathan, Mihailo M. Stojancic
-
Publication number: 20170201793Abstract: 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.Type: ApplicationFiled: October 19, 2016Publication date: July 13, 2017Applicant: Gracenote, Inc.Inventors: Jose Pio Pereira, Sunil Suresh Kulkarni, Oleksiy Bolgarov, Prashant Ramanathan, Shashank Merchant, Mihailo M. Stojancic