Patents by Inventor Avishkar MISRA
Avishkar MISRA 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: 11663829Abstract: Described is a system for counting stacked items using image analysis. In one implementation, an image of an inventory location with stacked items is obtained and processed to determine the number of items stacked at the inventory location. In some instances, the item closest to the camera that obtains the image may be the only item viewable in the image. Using image analysis, such as depth mapping or Histogram of Oriented Gradients (HOG) algorithms, the distance of the item from the camera and the shelf of the inventory location can be determined. Using this information, and known dimension information for the item, a count of the number of items stacked at an inventory location may be determined.Type: GrantFiled: September 3, 2020Date of Patent: May 30, 2023Assignee: Amazon Technologies, Inc.Inventors: Xiaofeng Ren, Avishkar Misra, Ohil Krishnamurthy Manyam, Liefeng Bo, Sudarshan Narasimha Raghavan, Christopher Robert Towers, Gopi Prashanth Gopal, Yasser Baseer Asmi
-
Patent number: 11392850Abstract: The disclosed embodiments relate to a system that facilitates development of machine-learning techniques to perform prognostic-surveillance operations on time-series data from a monitored system, such as a power plant and associated power-distribution system. During operation, the system receives original time-series signals comprising sequences of observations obtained from sensors in the monitored system. Next, the system decomposes the original time-series signals into deterministic and stochastic components. The system then uses the deterministic and stochastic components to produce synthetic time-series signals, which are statistically indistinguishable from the original time-series signals. Finally, the system enables a developer to use the synthetic time-series signals to develop machine-learning (ML) techniques to perform prognostic-surveillance operations on subsequently received time-series signals from the monitored system.Type: GrantFiled: February 2, 2018Date of Patent: July 19, 2022Assignee: Oracle International CorporationInventors: Kenny C. Gross, Mengying Li, Alan Paul Wood, Steven T. Jeffreys, Avishkar Misra, Lawrence L. Fumagalli, Jr.
-
Patent number: 11138631Abstract: Systems, methods, and computer-readable media are disclosed for predictive user segmentation modeling and browsing interaction analysis for digital advertising. In one embodiment, an example method may include identifying a target consumer segment, generating a predictive user behavior model for the target consumer segment based at least in part on selected user data, and receiving an indication that a user is browsing a website. Example methods may include generating a first customer score for the user using the predictive user behavior model in real-time, and determining that the first customer score meets a consumer segment modification threshold for the target consumer segment.Type: GrantFiled: October 30, 2015Date of Patent: October 5, 2021Assignee: Amazon Technologies, Inc.Inventors: Evgeniy V. Perevodchikov, Paula Marie Despins, Gerard Gjonej, Avishkar Misra, Alman Ahmad Shibli
-
Patent number: 10949801Abstract: This disclosure describes an item drop location for placing items that have been picked from an inventory location within a material handling facility but have not yet been transitioned from the materials handling facility and a return location for returning items that have been transitioned from the materials handling facility. Likewise, described is a system and method for identifying an item placed at a drop location or an item placed at a return location, processing the placed item and providing confirmation to a user that placed the item and facilitating a return of the item or a removal of the item from an item identifier list associated with the user.Type: GrantFiled: April 16, 2019Date of Patent: March 16, 2021Assignee: Amazon Technologies, Inc.Inventors: Sudheer Babu Ramoji, Avishkar Misra, Yasser Baseer Asmi, Ohil Krishnamurthy Manyam, Gopi Prashanth Gopal, Long Xuan Nguyen, Sudarshan Narasimha Raghavan, Ramanathan Palaniappan, Nadya Dhalla
-
Patent number: 10882692Abstract: Described is a system and method for assisting users in properly placing and/or positioning items at inventory locations within a materials handling facility. In one example, a placement location may be distinguished for the user through use of illumination or other techniques to assist the user in quickly identifying the proper location at which to place the item. Likewise, a proper position of the item may be presented to the user to assist the user in properly positioning the item at the placement location.Type: GrantFiled: August 3, 2018Date of Patent: January 5, 2021Assignee: Amazon Technologies, Inc.Inventors: Avishkar Misra, Ohil Krishnamurthy Manyam, Ramanathan Palaniappan, Michel Leonard Goldstein, Raymond Wheekyun Lim
-
Patent number: 10789483Abstract: Described is a system for counting stacked items using image analysis. In one implementation, an image of an inventory location with stacked items is obtained and processed to determine the number of items stacked at the inventory location. In some instances, the item closest to the camera that obtains the image may be the only item viewable in the image. Using image analysis, such as depth mapping or Histogram of Oriented Gradients (HOG) algorithms, the distance of the item from the camera and the shelf of the inventory location can be determined. Using this information, and known dimension information for the item, a count of the number of items stacked at an inventory location may be determined.Type: GrantFiled: November 19, 2018Date of Patent: September 29, 2020Assignee: Amazon Technologies, Inc.Inventors: Xiaofeng Ren, Avishkar Misra, Ohil Krishnamurthy Manyam, Liefeng Bo, Sudarshan Narasimha Raghavan, Christopher Robert Towers, Gopi Prashanth Gopal, Yasser Baseer Asmi
-
Patent number: 10671856Abstract: Described is a system for counting stacked items using image analysis. In one implementation, an image of an inventory location with stacked items is obtained and processed to determine the number of items stacked at the inventory location. In some instances, the item closest to the camera that obtains the image may be the only item viewable in the image. Using image analysis, such as depth mapping or Histogram of Oriented Gradients (HOG) algorithms, the distance of the item from the camera and the shelf of the inventory location can be determined. Using this information, and known dimension information for the item, a count of the number of items stacked at an inventory location may be determined.Type: GrantFiled: December 19, 2014Date of Patent: June 2, 2020Assignee: Amazon Technologies, Inc.Inventors: Xiaofeng Ren, Ohil Krishnamurthy Manyam, Avishkar Misra, Liefeng Bo, Sudarshan Narasimha Raghavan, Christopher Robert Towers, Gopi Prashanth Gopal, Yasser Baseer Asmi
-
Publication number: 20190243799Abstract: The disclosed embodiments relate to a system that facilitates development of machine-learning techniques to perform prognostic-surveillance operations on time-series data from a monitored system, such as a power plant and associated power-distribution system. During operation, the system receives original time-series signals comprising sequences of observations obtained from sensors in the monitored system. Next, the system decomposes the original time-series signals into deterministic and stochastic components. The system then uses the deterministic and stochastic components to produce synthetic time-series signals, which are statistically indistinguishable from the original time-series signals. Finally, the system enables a developer to use the synthetic time-series signals to develop machine-learning (ML) techniques to perform prognostic-surveillance operations on subsequently received time-series signals from the monitored system.Type: ApplicationFiled: February 2, 2018Publication date: August 8, 2019Applicant: Oracle International CorporationInventors: Kenny C. Gross, Mengying Li, Alan Paul Wood, Steven T. Jeffreys, Avishkar Misra, Lawrence L. Fumagalli, JR.
-
Patent number: 10290040Abstract: The dimensionality of user data can be reduced in order to allow cross-category data to be used to determine recommendations, advertising, or other supplemental content within a specific category. A first reduction in dimensionality results from rolling up category nodes to higher-level nodes. User data for the higher-level nodes can be used to train a neural network, with a user signature being generated using node values from a hidden layer of the trained model. The user signature can then be used to train a category specific model in order to obtain category-specific recommendations, determine category-specific advertising, or select other supplemental content based at least in part upon cross-category data.Type: GrantFiled: September 16, 2015Date of Patent: May 14, 2019Assignee: Amazon Technologies, Inc.Inventors: Avishkar Misra, Jody David Biggs
-
Patent number: 10268984Abstract: This disclosure describes an item drop location for placing items that have been picked from an inventory location within a material handling facility but have not yet been transitioned from the materials handling facility and a return location for returning items that have been transitioned from the materials handling facility. Likewise, described is a system and method for identifying an item placed at a drop location or an item placed at a return location, processing the placed item and providing confirmation to a user that placed the item and facilitating a return of the item or a removal of the item from an item identifier list associated with the user.Type: GrantFiled: September 29, 2014Date of Patent: April 23, 2019Assignee: Amazon Technologies, Inc.Inventors: Sudheer Babu Ramoji, Avishkar Misra, Yasser Baseer Asmi, Ohil Krishnamurthy Manyam, Gopi Prashanth Gopal, Long Xuan Nguyen, Sudarshan Narasimha Raghavan, Ramanathan Palaniappan, Nadya Dhalla
-
Patent number: 10169677Abstract: Described is a system for counting stacked items using image analysis. In one implementation, an image of an inventory location with stacked items is obtained and processed to determine the number of items stacked at the inventory location. In some instances, the item closest to the camera that obtains the image may be the only item viewable in the image. Using image analysis, such as depth mapping or Histogram of Oriented Gradients (HOG) algorithms, the distance of the item from the camera and the shelf of the inventory location can be determined. Using this information, and known dimension information for the item, a count of the number of items stacked at an inventory location may be determined.Type: GrantFiled: December 19, 2014Date of Patent: January 1, 2019Assignee: Amazon Technologies, Inc.Inventors: Xiaofeng Ren, Liefeng Bo, Ohil Krishnamurthy Manyam, Avishkar Misra, Sudarshan Narasimha Raghavan, Christopher Robert Towers, Gopi Prashanth Gopal, Yasser Baseer Asmi
-
Patent number: 10169660Abstract: Described is a system for counting stacked items using image analysis. In one implementation, an image of an inventory location with stacked items is obtained and processed to determine the number of items stacked at the inventory location. In some instances, the item closest to the camera that obtains the image may be the only item viewable in the image. Using image analysis, such as depth mapping or Histogram of Oriented Gradients (HOG) algorithms, the distance of the item from the camera and the shelf of the inventory location can be determined. Using this information, and known dimension information for the item, a count of the number of items stacked at an inventory location may be determined.Type: GrantFiled: December 19, 2014Date of Patent: January 1, 2019Assignee: Amazon Technologies, Inc.Inventors: Xiaofeng Ren, Avishkar Misra, Ohil Krishnamurthy Manyam, Liefeng Bo, Sudarshan Narasimha Raghavan, Christopher Robert Towers, Gopi Prashanth Gopal, Yasser Baseer Asmi
-
System and method providing automatic alignment of aerial/satellite imagery to known ground features
Patent number: 10089712Abstract: Systems, methods, and other embodiments are disclosed for correcting errors in the geo-spatial locations of acquired image data. In one embodiment, acquired aerial or satellite image data is segmented to generate extracted boundary data. The extracted boundary data represents boundaries of features of a portion of the Earth's surface, but at incorrect geo-spatial coordinates. The extracted boundary data is matched to expected boundary data derived from ground truth data. The expected boundary data represents boundaries of the features at correct geo-spatial coordinates. Adjustment parameters are generated that represent a geo-spatial misalignment between the extracted boundary data and the expected boundary data. Metadata in a header of the acquired image data is modified to include the adjustment parameters. The adjustment parameters may be applied to the acquired image data to generate corrected image data at correct geo-spatial coordinates.Type: GrantFiled: September 30, 2016Date of Patent: October 2, 2018Assignee: ORACLE INTERNATIONAL CORPORATIONInventors: Avishkar Misra, Zazhil Ha Herena Ulloa, Juan Carlos Reyes Martinez, Siva Ravada -
Patent number: 10068139Abstract: Described is a system for counting stacked items using image analysis. In one implementation, an image of an inventory location with stacked items is obtained and processed to determine the number of items stacked at the inventory location. In some instances, the item closest to the camera that obtains the image may be the only item viewable in the image. Using image analysis, such as depth mapping or Histogram of Oriented Gradients (HOG) algorithms, the distance of the item from the camera and the shelf of the inventory location can be determined. Using this information, and known dimension information for the item, a count of the number of items stacked at an inventory location may be determined.Type: GrantFiled: December 19, 2014Date of Patent: September 4, 2018Assignee: Amazon Technologies, Inc.Inventors: Xiaofeng Ren, Avishkar Misra, Ohil Krishnamurthy Manyam, Liefeng Bo, Sudarshan Narasimha Raghavan, Christopher Robert Towers, Gopi Prashanth Gopal, Yasser Baseer Asmi
-
Patent number: 10040628Abstract: Described is a system and method for assisting users in properly placing and/or positioning items at inventory locations within a materials handling facility. In one example, a placement location may be distinguished for the user through use of illumination or other techniques to assist the user in quickly identifying the proper location at which to place the item. Likewise, a proper position of the item may be presented to the user to assist the user in properly positioning the item at the placement location.Type: GrantFiled: March 25, 2014Date of Patent: August 7, 2018Assignee: Amazon Technologies, Inc.Inventors: Avishkar Misra, Ohil Krishnamurthy Manyam, Ramanathan Palaniappan, Michel Leonard Goldstein, Raymond Lim
-
Patent number: 9996818Abstract: Described is a system for counting stacked items using image analysis. In one implementation, an image of an inventory location with stacked items is obtained and processed to determine the number of items stacked at the inventory location. In some instances, the item closest to the camera that obtains the image may be the only item viewable in the image. Using image analysis, such as depth mapping or Histogram of Oriented Gradients (HOG) algorithms, the distance of the item from the camera and the shelf of the inventory location can be determined. Using this information, and known dimension information for the item, a count of the number of items stacked at an inventory location may be determined.Type: GrantFiled: April 21, 2016Date of Patent: June 12, 2018Assignee: Amazon Technologies, Inc.Inventors: Xiaofeng Ren, Ohil Krishnamurthy Manyam, Avishkar Misra, Liefeng Bo, Sudarshan Narasimha Raghavan, Christopher Robert Towers, Gopi Prashanth Gopal, Yasser Baseer Asmi
-
SYSTEM AND METHOD PROVIDING AUTOMATIC ALIGNMENT OF AERIAL/SATELLITE IMAGERY TO KNOWN GROUND FEATURES
Publication number: 20180096451Abstract: Systems, methods, and other embodiments are disclosed for correcting errors in the geo-spatial locations of acquired image data. In one embodiment, acquired aerial or satellite image data is segmented to generate extracted boundary data. The extracted boundary data represents boundaries of features of a portion of the Earth's surface, but at incorrect geo-spatial coordinates. The extracted boundary data is matched to expected boundary data derived from ground truth data. The expected boundary data represents boundaries of the features at correct geo-spatial coordinates. Adjustment parameters are generated that represent a geo-spatial misalignment between the extracted boundary data and the expected boundary data. Metadata in a header of the acquired image data is modified to include the adjustment parameters. The adjustment parameters may be applied to the acquired image data to generate corrected image data at correct geo-spatial coordinates.Type: ApplicationFiled: September 30, 2016Publication date: April 5, 2018Inventors: Avishkar MISRA, Zazhil Ha HERENA ULLOA, Juan Carlos REYES MARTINEZ, Siva RAVADA