Patents by Inventor Rajkiran K. Gottumukkal
Rajkiran K. Gottumukkal 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: 20230005238Abstract: Techniques are disclosed for extracting micro-features at a pixel-level based on characteristics of one or more images. Importantly, the extraction is unsupervised, i.e., performed independent of any training data that defines particular objects, allowing a behavior-recognition system to forgo a training phase and for object classification to proceed without being constrained by specific object definitions. A micro-feature extractor that does not require training data is adaptive and self-trains while performing the extraction. The extracted micro-features are represented as a micro-feature vector that may be input to a micro-classifier which groups objects into object type clusters based on the micro-feature vectors.Type: ApplicationFiled: September 13, 2022Publication date: January 5, 2023Applicant: Intellective Ai, Inc.Inventors: Wesley Kenneth COBB, Rajkiran K. GOTTUMUKKAL, Kishor Adinath SAITWAL, Ming-Jung SEOW, Gang XU, Lon W. RISINGER, Jeff GRAHAM
-
Patent number: 11468660Abstract: Techniques are disclosed for extracting micro-features at a pixel-level based on characteristics of one or more images. Importantly, the extraction is unsupervised, i.e., performed independent of any training data that defines particularly objects, allowing a behavior-recognition system to forgo a training phase and for object classification to proceed without being constrained by specify object definitions. A micro-feature extractor that does not require training data is adaptive and self-trains while performing the extraction. The extracted micro-features are represented as a micro-feature vector that may be input to a micro-classifier which groups object into object type clusters based on the micro-feature vectors.Type: GrantFiled: July 17, 2020Date of Patent: October 11, 2022Assignee: Intellective Ai, Inc.Inventors: Wesley Kenneth Cobb, Rajkiran K. Gottumukkal, Kishor Adinath Saitwal, Ming-Jung Seow, Gang Xu, Lon W. Risinger, Jeff Graham
-
Publication number: 20210042556Abstract: Techniques are disclosed for extracting micro-features at a pixel-level based on characteristics of one or more images. Importantly, the extraction is unsupervised, i.e., performed independent of any training data that defines particularly objects, allowing a behavior-recognition system to forgo a training phase and for object classification to proceed without being constrained by specify object definitions. A micro-feature extractor that does not require training data is adaptive and self-trains while performing the extraction. The extracted micro-features are represented as a micro-feature vector that may be input to a micro-classifier which groups object into object type clusters based on the micro-feature vectors.Type: ApplicationFiled: July 17, 2020Publication date: February 11, 2021Applicant: Intellective Ai, Inc.Inventors: Wesley Kenneth COBB, Rajkiran K. GOTTUMUKKAL, Kishor Adinath SAITWAL, Ming-Jung SEOW, Gang XU, Lon W. RISINGER, Jeff GRAHAM
-
Patent number: 10755131Abstract: Techniques are disclosed for extracting micro-features at a pixel-level based on characteristics of one or more images. Importantly, the extraction is unsupervised, i.e., performed independent of any training data that defines particular objects, allowing a behavior-recognition system to forgo a training phase and for object classification to proceed without being constrained by specific object definitions. A micro-feature extractor that does not require training data is adaptive and self-trains while performing the extraction. The extracted micro-features are represented as a micro-feature vector that may be input to a micro-classifier which groups objects into object type clusters based on the micro-feature vectors.Type: GrantFiled: July 12, 2018Date of Patent: August 25, 2020Assignee: Intellective Ai, Inc.Inventors: Wesley Kenneth Cobb, Rajkiran K. Gottumukkal, Kishor Adinath Saitwal, Ming-Jung Seow, Gang Xu, Lon W. Risinger, Jeff Graham
-
Patent number: 10706284Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.Type: GrantFiled: August 20, 2019Date of Patent: July 7, 2020Assignee: AVIGILON PATENT HOLDING 1 CORPORATIONInventors: John Eric Eaton, Wesley Kenneth Cobb, Dennis G. Urech, David S. Friedlander, Gang Xu, Ming-Jung Seow, Lon W. Risinger, David M. Solum, Tao Yang, Rajkiran K. Gottumukkal, Kishor Adinath Saitwal
-
Publication number: 20190377951Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.Type: ApplicationFiled: August 20, 2019Publication date: December 12, 2019Inventors: John Eric EATON, Wesley Kenneth COBB, Dennis G. URECH, David S. FRIEDLANDER, Gang XU, Ming-Jung SEOW, Lon W. RISINGER, David M. SOLUM, Tao YANG, Rajkiran K. GOTTUMUKKAL, Kishor Adinath SAITWAL
-
Patent number: 10423835Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.Type: GrantFiled: December 19, 2018Date of Patent: September 24, 2019Assignee: AVIGILON PATENT HOLDING 1 CORPORATIONInventors: John Eric Eaton, Wesley Kenneth Cobb, Dennis G. Urech, David S. Friedlander, Gang Xu, Ming-Jung Seow, Lon W. Risinger, David M. Solum, Tao Yang, Rajkiran K. Gottumukkal, Kishor Adinath Saitwal
-
Publication number: 20190180135Abstract: Techniques are disclosed for extracting micro-features at a pixel-level based on characteristics of one or more images. Importantly, the extraction is unsupervised, i.e., performed independent of any training data that defines particular objects, allowing a behavior-recognition system to forgo a training phase and for object classification to proceed without being constrained by specific object definitions. A micro-feature extractor that does not require training data is adaptive and self-trains while performing the extraction. The extracted micro-features are represented as a micro-feature vector that may be input to a micro-classifier which groups objects into object type clusters based on the micro-feature vectors.Type: ApplicationFiled: July 12, 2018Publication date: June 13, 2019Applicant: Omni AI, Inc.Inventors: Wesley Kenneth COBB, Rajkiran K. GOTTUMUKKAL, Kishor Adinath SAITWAL, Ming-Jung SEOW, Gang XU, Lon W. RISINGER, Jeff GRAHAM
-
Publication number: 20190122048Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.Type: ApplicationFiled: December 19, 2018Publication date: April 25, 2019Inventors: John Eric EATON, Wesley Kenneth COBB, Dennis G. URECH, David S. FRIEDLANDER, Gang XU, Ming-Jung SEOW, Lon W. RISINGER, David M. SOLUM, Tao YANG, Rajkiran K. GOTTUMUKKAL, Kishor Adinath SAITWAL
-
Patent number: 10198636Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.Type: GrantFiled: March 14, 2018Date of Patent: February 5, 2019Assignee: AVIGILON PATENT HOLDING 1 CORPORATIONInventors: John Eric Eaton, Wesley Kenneth Cobb, Dennis G. Urech, David S. Friedlander, Gang Xu, Ming-Jung Seow, Lon W. Risinger, David M. Solum, Tao Yang, Rajkiran K. Gottumukkal, Kishor Adinath Saitwal
-
Patent number: 10049293Abstract: Techniques are disclosed for extracting micro-features at a pixel-level based on characteristics of one or more images. Importantly, the extraction is unsupervised, i.e., performed independent of any training data that defines particular objects, allowing a behavior-recognition system to forgo a training phase and for object classification to proceed without being constrained by specific object definitions. A micro-feature extractor that does not require training data is adaptive and self-trains while performing the extraction. The extracted micro-features are represented as a micro-feature vector that may be input to a micro-classifier which groups objects into object type clusters based on the micro-feature vectors.Type: GrantFiled: March 16, 2017Date of Patent: August 14, 2018Assignee: Omni Al, Inc.Inventors: Wesley Kenneth Cobb, Rajkiran K. Gottumukkal, Kishor Adinath Saitwal, Ming-Jung Seow, Gang Xu, Lon W. Risinger, Jeff Graham
-
Publication number: 20180204068Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.Type: ApplicationFiled: March 14, 2018Publication date: July 19, 2018Inventors: John Eric EATON, Wesley Kenneth COBB, Dennis G. URECH, David S. FRIEDLANDER, Gang XU, Ming-Jung SEOW, Lon W. RISINGER, David M. SOLUM, Tao YANG, Rajkiran K. GOTTUMUKKAL, Kishor Adinath SAITWAL
-
Patent number: 9946934Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.Type: GrantFiled: April 21, 2017Date of Patent: April 17, 2018Assignee: AVIGILON PATENT HOLDING 1 CORPORATIONInventors: John Eric Eaton, Wesley Kenneth Cobb, Dennis G. Urech, David S. Friedlander, Gang Xu, Ming-Jung Seow, Lon W. Risinger, David M. Solum, Tao Yang, Rajkiran K. Gottumukkal, Kishor Adinath Saitwal
-
Publication number: 20180032834Abstract: Techniques are disclosed for extracting micro-features at a pixel-level based on characteristics of one or more images. Importantly, the extraction is unsupervised, i.e., performed independent of any training data that defines particular objects, allowing a behavior-recognition system to forgo a training phase and for object classification to proceed without being constrained by specific object definitions. A micro-feature extractor that does not require training data is adaptive and self-trains while performing the extraction. The extracted micro-features are represented as a micro-feature vector that may be input to a micro-classifier which groups objects into object type clusters based on the micro-feature vectors.Type: ApplicationFiled: March 16, 2017Publication date: February 1, 2018Inventors: Wesley Kenneth COBB, Rajkiran K. GOTTUMUKKAL, Kishor Adinath SAITWAL, Ming-Jung SEOW, Gang XU, Lon W. RISINGER, Jeff GRAHAM
-
Publication number: 20170228598Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.Type: ApplicationFiled: April 21, 2017Publication date: August 10, 2017Inventors: John Eric EATON, Wesley Kenneth COBB, Dennis G. URECH, David S. FRIEDLANDER, Gang XU, Ming-Jung SEOW, Lon W. RISINGER, David M. SOLUM, Tao YANG, Rajkiran K. GOTTUMUKKAL, Kishor Adinath SAITWAL
-
Patent number: 9665774Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.Type: GrantFiled: October 28, 2016Date of Patent: May 30, 2017Assignee: Avigilon Patent Holding 1 CorporationInventors: John Eric Eaton, Wesley Kenneth Cobb, Dennis G. Urech, David S. Friedlander, Gang Xu, Ming-Jung Seow, Lon W. Risinger, David M. Solum, Tao Yang, Rajkiran K. Gottumukkal, Kishor Adinath Saitwal
-
Patent number: 9633275Abstract: Techniques are disclosed for extracting micro-features at a pixel-level based on characteristics of one or more images. Importantly, the extraction is unsupervised, i.e., performed independent of any training data that defines particular objects, allowing a behavior-recognition system to forgo a training phase and for object classification to proceed without being constrained by specific object definitions. A micro-feature extractor that does not require training data is adaptive and self-trains while performing the extraction. The extracted micro-features are represented as a micro-feature vector that may be input to a micro-classifier which groups objects into object type clusters based on the micro-feature vectors.Type: GrantFiled: August 18, 2009Date of Patent: April 25, 2017Inventors: Wesley Kenneth Cobb, Rajkiran K. Gottumukkal, Kishor Adinath Saitwal, Ming-Jung Seow, Gang Xu, Lon W. Risinger, Jeff Graham
-
Publication number: 20170046576Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.Type: ApplicationFiled: October 28, 2016Publication date: February 16, 2017Inventors: John Eric EATON, Wesley Kenneth COBB, Dennis G. URECH, David S. FRIEDLANDER, Gang XU, Ming-Jung SEOW, Lon W. RISINGER, David M. SOLUM, Tao YANG, Rajkiran K. GOTTUMUKKAL, Kishor Adinath SAITWAL
-
Patent number: 9489569Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.Type: GrantFiled: January 11, 2016Date of Patent: November 8, 2016Assignee: 9051147 CANADA INC.Inventors: John Eric Eaton, Wesley Kenneth Cobb, Dennis G. Urech, David S. Friedlander, Gang Xu, Ming-Jung Seow, Lon W. Risinger, David M. Solum, Tao Yang, Rajkiran K. Gottumukkal, Kishor Adinath Saitwal
-
Publication number: 20160125233Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.Type: ApplicationFiled: January 11, 2016Publication date: May 5, 2016Inventors: John Eric EATON, Wesley Kenneth COBB, Dennis G. URECH, David S. FRIEDLANDER, Gang XU, Ming-Jung SEOW, Lon W. RISINGER, David M. SOLUM, Tao YANG, Rajkiran K. GOTTUMUKKAL, Kishor Adinath SAITWAL