Patents by Inventor Vivek Jayaram
Vivek Jayaram 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).
-
Publication number: 20240031619Abstract: Methods and systems for finding and ranking video sequences that contain tactical sequences (e.g., an uninterrupted portion of a sporting event) that are similar to tactical event content in a target video sequence, such as those occurring in sports, include learning and labelling (e.g., through use of metadata and the like) tactically significant sequences in a plurality of video segments, including a plurality of such tactically significant sequences in a single video segment.Type: ApplicationFiled: September 29, 2023Publication date: January 25, 2024Inventors: Vivek JAYARAM, Nikhil MITRA, Kevin SQUIRE
-
Patent number: 11856318Abstract: Systems and methods are described for detecting a triggering event in a gaming environment and recording a segment of video. In some aspects, the method may include obtaining a camera projection matrix associated with the gaming environment that correlates points in the gaming environment between a two-dimensional pixel space and a three-dimensional physical representation. An input video may be obtained from the gaming environment. Pose coordinates, including two-dimensional pixel space location, of a body part of a person in the input video may be estimated, and converted to three-dimensional pose coordinates using the camera projection matrix. A person of interest having a body part located within a region of interest in the gaming environment may be identified to determine if a triggering event has occurred. Storage of an input video segment that includes the trigger movement may be initiated on a storage device in communication with the user device.Type: GrantFiled: April 27, 2022Date of Patent: December 26, 2023Assignee: MAIDEN AI, INC.Inventors: Vivek Jayaram, Arjun Verma, Brogan McPartland, Vaikkunth Mugunthan
-
Patent number: 11778244Abstract: Methods and systems for finding and ranking video sequences that contain tactical sequences (e.g., an uninterrupted portion of a sporting event) that are similar to tactical event content in a target video sequence, such as those occurring in sports, include learning and labelling (e.g., through use of metadata and the like) tactically significant sequences in a plurality of video segments, including a plurality of such tactically significant sequences in a single video segment.Type: GrantFiled: September 3, 2021Date of Patent: October 3, 2023Assignee: Genius Sports SS, LLCInventors: Vivek Jayaram, Nikhil Mitra, Kevin Squire
-
Publication number: 20230298210Abstract: Data processing systems are disclosed for determining semantic and person keypoints for an environment and an image and matching the keypoints for the image to the keypoints for the environment. A homography is generated based on the keypoint matching and decomposed into a matrix. Camera parameters are then determined from the matrix. A plurality of random camera poses can be generated and used to project keypoints for an environment using image keypoints. The projected keypoints can be compared to the actual keypoints for the environment to determine an error and weighting for each of the random camera poses.Type: ApplicationFiled: May 22, 2023Publication date: September 21, 2023Inventors: Leonardo Citraro, Pablo Márquez Neila, Stefano Savarè, Vivek Jayaram, Charles Xavier Quentin Dubout, Felix Constant Marc Renaut, Andres Michael Levering Hasfura, Horesh Beny Ben Shitrit, Pascal Fua
-
Publication number: 20230289982Abstract: Systems and methods are described for generating a three-dimensional track a ball in a gaming environment from a single camera. In some examples, an input video including frames of a ball moving in a gaming environment recorded by a camera may be obtained, along with a camera projection matrix associated with at least one frame that maps a two-dimensional pixel space representation to a three-dimensional representation of the gaming environment. Candidate two-dimensional image locations of the ball across the plurality of frames may be identified using a neural network or a computer vision algorithm. An optimization algorithm may be performed that uses a 3D ball physics model, the camera projection matrix and a subset of the candidate two-dimensional image locations of the ball to generate a three-dimensional track of the ball in the gaming environment. The three-dimensional track of the ball may then be provided to a user device.Type: ApplicationFiled: March 8, 2023Publication date: September 14, 2023Inventors: Vivek Jayaram, Arjun Verma, Brogan McPartland, Vaikkunth Mugunthan
-
Patent number: 11694362Abstract: Data processing systems are disclosed for determining semantic and person keypoints for an environment and an image and matching the keypoints for the image to the keypoints for the environment. A homography is generated based on the keypoint matching and decomposed into a matrix. Camera parameters are then determined from the matrix. A plurality of random camera poses can be generated and used to project keypoints for an environment using image keypoints. The projected keypoints can be compared to the actual keypoints for the environment to determine an error and weighting for each of the random camera poses.Type: GrantFiled: April 7, 2021Date of Patent: July 4, 2023Assignee: Genius Sports SS, LLCInventors: Leonardo Citraro, Pablo Márquez Neila, Stefano Savarè, Vivek Jayaram, Charles Xavier Quentin Dubout, Felix Constant Marc Renaut, Andres Michael Levering Hasfura, Horesh Beny Ben Shitrit, Pascal Fua
-
Publication number: 20230100572Abstract: Systems and methods are described for generating a three-dimensional track of a ball in a gaming environment from multiple cameras. In some examples, at least two input videos, each including frames of a ball moving in a gaming environment recorded by a camera, may be obtained, along with a camera projection matrix that maps a two-dimensional pixel space representation to a three-dimensional representation of the gaming environment. Candidate two-dimensional image locations of the ball across the plurality of frames of the at least two input videos may be identified using neural network or computer vision techniques. An optimization algorithm may be performed that uses a 3D ball physics model, the camera projection matrix and a subset of the candidate two-dimensional image locations of the ball from the at least two input videos to generate a three-dimensional track of the ball in the gaming environment.Type: ApplicationFiled: September 23, 2022Publication date: March 30, 2023Inventors: Vivek Jayaram, Brogan McPartland, Arjun Verma
-
Patent number: 11615540Abstract: Systems and methods are described for generating a three-dimensional track a ball in a gaming environment from a single camera. In some examples, an input video including frames of a ball moving in a gaming environment recorded by a camera may be obtained, along with a camera projection matrix associated with at least one frame that maps a two-dimensional pixel space representation to a three-dimensional representation of the gaming environment. Candidate two-dimensional image locations of the ball across the plurality of frames may be identified using a neural network or a computer vision algorithm. An optimization algorithm may be performed that uses a 3D ball physics model, the camera projection matrix and a subset of the candidate two-dimensional image locations of the ball to generate a three-dimensional track of the ball in the gaming environment. The three-dimensional track of the ball may then be provided to a user device.Type: GrantFiled: April 27, 2022Date of Patent: March 28, 2023Assignee: MAIDEN AI, INC.Inventors: Vivek Jayaram, Arjun Verma, Brogan McPartland, Vaikkunth Mugunthan
-
Publication number: 20220345660Abstract: Systems and methods are described for detecting a triggering event in a gaming environment and recording a segment of video. In some aspects, the method may include obtaining a camera projection matrix associated with the gaming environment that correlates points in the gaming environment between a two-dimensional pixel space and a three-dimensional physical representation. An input video may be obtained from the gaming environment. Pose coordinates, including two-dimensional pixel space location, of a body part of a person in the input video may be estimated, and converted to three-dimensional pose coordinates using the camera projection matrix. A person of interest having a body part located within a region of interest in the gaming environment may be identified to determine if a triggering event has occurred. Storage of an input video segment that includes the trigger movement may be initiated on a storage device in communication with the user device.Type: ApplicationFiled: April 27, 2022Publication date: October 27, 2022Inventors: Vivek Jayaram, Arjun Verma, Brogan McPartland, Vaikkunth Mugunthan
-
Publication number: 20220343514Abstract: Systems and methods are described for generating a three-dimensional track a ball in a gaming environment from a single camera. In some examples, an input video including frames of a ball moving in a gaming environment recorded by a camera may be obtained, along with a camera projection matrix associated with at least one frame that maps a two-dimensional pixel space representation to a three-dimensional representation of the gaming environment. Candidate two-dimensional image locations of the ball across the plurality of frames may be identified using a neural network or a computer vision algorithm. An optimization algorithm may be performed that uses a 3D ball physics model, the camera projection matrix and a subset of the candidate two-dimensional image locations of the ball to generate a three-dimensional track of the ball in the gaming environment. The three-dimensional track of the ball may then be provided to a user device.Type: ApplicationFiled: April 27, 2022Publication date: October 27, 2022Inventors: Vivek Jayaram, Arjun Verma, Brogan McPartland, Vaikkunth Mugunthan
-
Publication number: 20210397847Abstract: Methods and systems for finding and ranking video sequences that contain tactical sequences (e.g., an uninterrupted portion of a sporting event) that are similar to tactical event content in a target video sequence, such as those occurring in sports, include learning and labelling (e.g., through use of metadata and the like) tactically significant sequences in a plurality of video segments, including a plurality of such tactically significant sequences in a single video segment.Type: ApplicationFiled: September 3, 2021Publication date: December 23, 2021Inventors: Vivek Jayaram, Nikhil Mitra, Kevin Squire
-
Patent number: 11113535Abstract: Methods and systems for finding and ranking video sequences that contain tactical sequences (e.g., an uninterrupted portion of a sporting event) that are similar to tactical event content in a target video sequence, such as those occurring in sports, include learning and labelling (e.g., through use of metadata and the like) tactically significant sequences in a plurality of video segments, including a plurality of such tactically significant sequences in a single video segment.Type: GrantFiled: November 8, 2019Date of Patent: September 7, 2021Assignee: Second Spectrum, Inc.Inventors: Vivek Jayaram, Nikhil Mitra, Kevin Squire
-
Publication number: 20210225034Abstract: Data processing systems are disclosed for determining semantic and person keypoints for an environment and an image and matching the keypoints for the image to the keypoints for the environment. A homography is generated based on the keypoint matching and decomposed into a matrix. Camera parameters are then determined from the matrix. A plurality of random camera poses can be generated and used to project keypoints for an environment using image keypoints. The projected keypoints can be compared to the actual keypoints for the environment to determine an error and weighting for each of the random camera poses.Type: ApplicationFiled: April 7, 2021Publication date: July 22, 2021Inventors: Leonardo Citraro, Pablo Márquez Neila, Stefano Savarè, Vivek Jayaram, Charles Xavier Quentin Dubout, Felix Constant Marc Renaut, Andres Michael Levering Hasfura, Horesh Beny Ben Shitrit, Pascal Fua
-
Publication number: 20210142066Abstract: Methods and systems for finding and ranking video sequences that contain tactical sequences (e.g., an uninterrupted portion of a sporting event) that are similar to tactical event content in a target video sequence, such as those occurring in sports, include learning and labelling (e.g., through use of metadata and the like) tactically significant sequences in a plurality of video segments, including a plurality of such tactically significant sequences in a single video segment.Type: ApplicationFiled: November 8, 2019Publication date: May 13, 2021Inventors: Vivek Jayaram, Nikhil Mitra, Kevin Squire
-
Patent number: 10991125Abstract: Data processing systems are disclosed for determining semantic and person keypoints for an environment and an image and matching the keypoints for the image to the keypoints for the environment. A homography is generated based on the keypoint matching and decomposed into a matrix. Camera parameters are then determined from the matrix. A plurality of random camera poses can be generated and used to project keypoints for an environment using image keypoints. The projected keypoints can be compared to the actual keypoints for the environment to determine an error and weighting for each of the random camera poses.Type: GrantFiled: February 24, 2020Date of Patent: April 27, 2021Assignee: Second Spectrum, Inc.Inventors: Leonardo Citraro, Pablo Márquez Neila, Stefano Savarè, Vivek Jayaram, Charles Xavier Quentin Dubout, Felix Constant Marc Renaut, Andres Michael Levering Hasfura, Horesh Beny Ben Shitrit, Pascal Fua
-
Publication number: 20210027493Abstract: Data processing systems are disclosed for determining semantic and person keypoints for an environment and an image and matching the keypoints for the image to the keypoints for the environment. A homography is generated based on the keypoint matching and decomposed into a matrix. Camera parameters are then determined from the matrix. A plurality of random camera poses can be generated and used to project keypoints for an environment using image keypoints. The projected keypoints can be compared to the actual keypoints for the environment to determine an error and weighting for each of the random camera poses.Type: ApplicationFiled: February 24, 2020Publication date: January 28, 2021Inventors: Leonardo Citraro, Pablo Márquez Neila, Stefano Savarè, Vivek Jayaram, Charles Xavier Quentin Dubout, Felix Constant Marc Renaut, Andres Michael Levering Hasfura, Horesh Beny Ben Shitrit, Pascal Fua
-
Patent number: 10600210Abstract: Data processing systems are disclosed for determining semantic and person keypoints for an environment and an image and matching the keypoints for the image to the keypoints for the environment. A homography is generated based on the keypoint matching and decomposed into a matrix. Camera parameters are then determined from the matrix. A plurality of random camera poses can be generated and used to project keypoints for an environment using image keypoints. The projected keypoints can be compared to the actual keypoints for the environment to determine an error and weighting for each of the random camera poses.Type: GrantFiled: July 25, 2019Date of Patent: March 24, 2020Assignee: Second Spectrum, Inc.Inventors: Leonardo Citraro, Pablo Márquez Neila, Stefano Savaré, Vivek Jayaram, Charles Xavier Quentin Dubout, Felix Constant Marc Renaut, Andres Michael Levering Hasfura, Horesh Beny Ben Shitrit, Pascal Fua