Peter David Wendt, Age 68651 Addison St UNIT 223, Berkeley, CA 94710

8189945, May 29, 2012

Nov 5, 2009

12/612729

Mihailo Stojancic - San Jose CA, US
Prashant Ramanathan - Mountain View CA, US
Peter Wendt - San Jose CA, US
Jose Pio Pereira - Cupertino CA, US

Zeitera, LLC - Mountain View CA

G06K 9/00
G06K 9/46
G06K 9/40

382264, 382154, 382190

Video sequence processing is described with various filtering rules applied to extract dominant features for content based video sequence identification. Active regions are determined in video frames of a video sequence. Video frames are selected in response to temporal statistical characteristics of the determined active regions. A two pass analysis is used to detect a set of initial interest points and interest regions in the selected video frames to reduce the effective area of images that are refined by complex filters that provide accurate region characterizations resistant to image distortion for identification of the video frames in the video sequence. Extracted features and descriptors are robust with respect to image scaling, aspect ratio change, rotation, camera viewpoint change, illumination and contrast change, video compression/decompression artifacts and noise. Compact, representative signatures are generated for video sequences to provide effective query video matching and retrieval in a large video database.

2012020, Aug 16, 2012

Apr 25, 2012

13/455560

Mihailo Stojancic - San Jose CA, US
Prashant Ramanathan - Mountain View CA, US
Peter Wendt - San Jose CA, US
Jose Pio Pereira - Cupertino CA, US

ZEITERA, LLC - Mountain View CA

G06K 9/40

382260

Video sequence processing is described with various filtering rules applied to extract dominant features for content based video sequence identification. Active regions are determined in video frames of a video sequence. Video frames are selected in response to temporal statistical characteristics of the determined active regions. A two pass analysis is used to detect a set of initial interest points and interest regions in the selected video frames to reduce the effective area of images that are refined by complex filters that provide accurate region characterizations resistant to image distortion for identification of the video frames in the video sequence. Extracted features and descriptors are robust with respect to image scaling, aspect ratio change, rotation, camera viewpoint change, illumination and contrast change, video compression/decompression artifacts and noise. Compact, representative signatures are generated for video sequences to provide effective query video matching and retrieval in a large video database.

2022023, Jul 28, 2022

Apr 18, 2022

17/722523

- San Jose CA, US
Jose Pio Pereira - Cupertino CA, US
Peter Wendt - San Jose CA, US
Shashank Merchant - Sunnyvale CA, US
Sunil Suresh Kulkarni - San Jose CA, US

H04N 21/439
H04N 1/32
H04N 21/8352
G10H 1/00
H04N 21/414
H04N 21/422
H04N 21/4223
H04N 21/433
H04N 21/84
H04N 21/845

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.

2021038, Dec 9, 2021

Aug 20, 2021

17/408248

- San Jose CA, US
Prashant Ramanathan - Mountain View CA, US
Peter Wendt - San Jose CA, US
Jose Pio Pereira - Cupertino CA, US

G06F 16/48
G06F 16/41
G06F 16/28
G06F 16/783
G06F 16/951
G06F 16/22
G06F 16/901
G06K 9/00
G06K 9/46

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.

2021037, Dec 2, 2021

Aug 12, 2021

17/444946

- San Jose CA, US
Sunil Suresh Kulkarni - San Jose CA, US
Mihailo M. Stojancic - San Jose CA, US
Shashank Merchant - Sunnyvale CA, US
Peter Wendt - San Jose CA, US

G10L 15/20
G10L 15/06
G10L 25/81
G10L 15/02
G10L 15/10
G10L 21/0232
G10L 15/14

Audio distortion compensation methods to improve accuracy and efficiency of audio content identification are described. The method is also applicable to speech recognition. Methods to detect the interference from speakers and sources, and distortion to audio from environment and devices, are discussed. Additional methods to detect distortion to the content after performing search and correlation are illustrated. The causes of actual distortion at each client are measured and registered and learnt to generate rules for determining likely distortion and interference sources. The learnt rules are applied at the client, and likely distortions that are detected are compensated or heavily distorted sections are ignored at audio level or signature and feature level based on compute resources available. Further methods to subtract the likely distortions in the query at both audio level and after processing at signature and feature level are described.

2020037, Nov 26, 2020

Apr 7, 2020

16/841681

- Emeryville CA, US
Kyle Brocklehurst - Mountain View CA, US
Sunil Suresh Kulkarni - San Jose CA, US
Peter Wendt - San Jose CA, US

G06T 7/33
G06K 9/46
G06T 7/60
G06K 9/62
G06T 7/11

Methods, apparatus, systems and articles of manufacture of logo recognition in images and videos are disclosed. An example method to detect a specific brand in images and video streams comprises accepting luminance images at a scale in an x direction Sx and a different scale in a y direction Sy in a neural network, and training the neural network with a set of training images for detected features associated with a specific brand.

2019025, Aug 15, 2019

Apr 16, 2019

16/385575

- Emeryville CA, US
Prashant Ramanathan - Mountain View CA, US
Peter Wendt - San Jose CA, US
Jose Pio Pereira - Cupertino CA, US

G06F 16/48
G06F 16/901
G06F 16/783
G06F 16/22
G06F 16/951
G06K 9/00
G06F 16/28
G06F 16/41
G06K 9/46

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.

2018030, Oct 25, 2018

Jun 25, 2018

16/018011

- Emeryville CA, US
Kyle Brocklehurst - Mountain View CA, US
Sunil Suresh Kulkarni - San Jose CA, US
Peter Wendt - San Jose CA, US

G06K 9/62
G06K 9/46
G06T 7/60
G06K 9/66
G06T 7/33
G06K 9/52

Methods, apparatus, systems and articles of manufacture of logo recognition in images and videos are disclosed. An example method to detect a specific brand in images and video streams comprises accepting luminance images at a scale in an x direction Sx and a different scale in a y direction Sy in a neural network, and training the neural network with a set of training images for detected features associated with a specific brand.