Patents by Inventor Nitin SINGHAL
Nitin SINGHAL 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: 10534965Abstract: Techniques for analyzing stored video upon a request are described. For example, a method of receiving a first application programming interface (API) request to analyze a stored video, the API request to include a location of the stored video and at least one analysis action to perform on the stored video; accessing the location of the stored video to retrieve the stored video; segmenting the accessed video into chunks; processing each chunk with a chunk processor to perform the at least one analysis action, each chunk processor to utilize at least one machine learning model in performing the at least one analysis action; joining the results of the processing of each chunk to generate a final result; storing the final result; and providing the final result to a requestor in response to a second API request is described.Type: GrantFiled: March 20, 2018Date of Patent: January 14, 2020Assignee: Amazon Technologies, Inc.Inventors: Nitin Singhal, Vivek Bhadauria, Ranju Das, Gaurav D. Ghare, Roman Goldenberg, Stephen Gould, Kuang Han, Jonathan Andrew Hedley, Gowtham Jeyabalan, Vasant Manohar, Andrea Olgiati, Stefano Stefani, Joseph Patrick Tighe, Praveen Kumar Udayakumar, Renjun Zheng
-
Patent number: 10489654Abstract: A system processes a video stream to identify an activity performed by a subject. The system examines the video segment for the presence or absence of an object that is correlated with the activity. If the object is found, and if the object is positively correlated with the detected activity, a confidence level associated with detecting the activity is increase. If the object is found, and if it is negatively correlated with the activity, the confidence level is decreased. In other examples, absence of an object may be positively or negatively correlated with the activity. In one embodiment, the system may detect a number of alternative activities, and may use the presence or absence of various objects to determine the most likely activity being performed. In another embodiment, the system may use the presence of various objects to narrow the set of activities that are searched for.Type: GrantFiled: August 4, 2017Date of Patent: November 26, 2019Assignee: Amazon Technologies, Inc.Inventors: Andrea Olgiati, Nitin Singhal
-
Patent number: 10478151Abstract: A method for automatically monitoring fetal head descent in a birth canal is presented. The method includes segmenting each image in one or more images into a plurality of neighborhood components, determining a cost function corresponding to each neighborhood component in the plurality of neighborhood components in each of the one or more images, identifying at least two structures of interest in each image in the one or more images based on the cost function, wherein the at least two structures of interest include a pubic ramus and a fetal head, measuring an angle of progression based on the at least two structures of interest, and determining the fetal head descent in the birth canal based on the angle of progression.Type: GrantFiled: August 12, 2014Date of Patent: November 19, 2019Assignee: GENERAL ELECTRIC COMPANYInventors: Nitin Singhal, Kajoli Banerjee Krishnan, Christian Fritz Perrey, Klaus Pintoffl, Walter Duda, Jr., Francesca Patruno
-
Publication number: 20190343487Abstract: A system (e.g., an ultrasound imaging system) is provided. The system includes an ultrasound probe configured to acquire three-dimensional (3D) ultrasound data of a volumetric region of interest (ROI). The system further includes a display, a memory configured to store programmed instructions, and a controller circuit. The controller circuit includes one or more processors. The controller circuit is configured to execute the programmed instructions stored in the memory. When executing the programmed instructions, the controller circuit performs a plurality of operations. The operations includes collecting the 3D ultrasound data from an ultrasound probe and identifying a select set of the 3D ultrasound data corresponding to an object of interest within the volumetric ROI. The operations further include segmenting the object of interest from the select set of the 3D ultrasound data, generating a visualization plane of the object of interest, and displaying the visualization plane on the display.Type: ApplicationFiled: July 26, 2019Publication date: November 14, 2019Inventors: Christian Fritz PERREY, Suvadip MUKHERJEE, Nitin SINGHAL, Rakesh MULLICK
-
Patent number: 10398411Abstract: Embodiments for aligning a volume to a standard alignment are provided. One example method of aligning a volume constructed from captured image data to a standard orientation includes determining an orientation and a scale of the volume based on a comparison of a volume model representing the volume to captured image data of the volume over time and adjusting the volume according to the determined orientation and scale.Type: GrantFiled: February 19, 2016Date of Patent: September 3, 2019Assignee: General Electric CompanyInventors: Christian Fritz Perrey, Daniel John Buckton, Nitin Singhal, Kajoli Banerjee Krishnan
-
Publication number: 20190156124Abstract: Techniques for analyzing stored video upon a request are described. For example, a method of receiving a first application programming interface (API) request to analyze a stored video, the API request to include a location of the stored video and at least one analysis action to perform on the stored video; accessing the location of the stored video to retrieve the stored video; segmenting the accessed video into chunks; processing each chunk with a chunk processor to perform the at least one analysis action, each chunk processor to utilize at least one machine learning model in performing the at least one analysis action; joining the results of the processing of each chunk to generate a final result; storing the final result; and providing the final result to a requestor in response to a second API request is described.Type: ApplicationFiled: March 20, 2018Publication date: May 23, 2019Inventors: Nitin SINGHAL, Vivek BHADAURIA, Ranju DAS, Gaurav D. GHARE, Roman GOLDENBERG, Stephen GOULD, Kuang HAN, Jonathan Andrew HEDLEY, Gowtham JEYABALAN, Vasant MANOHAR, Andrea OLGIATI, Stefano STEFANI, Joseph Patrick TIGHE, Praveen Kumar Udayakumar, Renjun ZHANG
-
Publication number: 20180240551Abstract: Systems and methods are provided relating to hierarchical machine learning models to identify an anatomical structure of interest and perform diagnostic procedures for a medical diagnostic imaging system. The systems and methods organize a plurality of models into a hierarchical structure based on anatomical structures. The plurality of models are defined by a machine learning algorithm for diagnostic procedures of one or more of the anatomical structures. The systems and methods receive a medical image, identifying an anatomical structure of interest within the medical image, select at least a first model from the plurality of models based on the anatomical structure of interest, and perform a first diagnostic procedure of the anatomical structure of interest based on the first model.Type: ApplicationFiled: February 20, 2018Publication date: August 23, 2018Inventors: Christian Fritz Perrey, Nitin Singhal
-
Publication number: 20180042577Abstract: A system (e.g., an ultrasound imaging system) is provided. The system includes an ultrasound probe configured to acquire three dimensional (3D) ultrasound data of a volumetric region of interest (ROI). The system further includes a display, a memory configured to store programmed instructions, and a controller circuit. The controller circuit includes one or more processors. The controller circuit is configured to execute the programmed instructions stored in the memory. When executing the programmed instructions, the controller circuit performs a plurality of operations. The operations includes collecting the 3D ultrasound data from an ultrasound probe and identifying a select set of the 3D ultrasound data corresponding to an object of interest within the volumetric ROI. The operations further include segmenting the object of interest from the select set of the 3D ultrasound data, generating a visualization plane of the object of interest, and displaying the visualization plane on the display.Type: ApplicationFiled: September 7, 2016Publication date: February 15, 2018Inventors: Christian Fritz PERREY, Suvadip MUKHERJEE, Nitin SINGHAL, Rakesh MULLICK
-
Publication number: 20170238904Abstract: Embodiments for aligning a volume to a standard alignment are provided. One example method of aligning a volume constructed from captured image data to a standard orientation includes determining an orientation and a scale of the volume based on a comparison of a volume model representing the volume to captured image data of the volume over time and adjusting the volume according to the determined orientation and scale.Type: ApplicationFiled: February 19, 2016Publication date: August 24, 2017Inventors: Christian Fritz Perrey, Daniel John Buckton, Nitin Singhal, Kajoli Banerjee Krishnan
-
Publication number: 20160045152Abstract: A method for automatically monitoring fetal head descent in a birth canal is presented. The method includes segmenting each image in one or more images into a plurality of neighborhood components, determining a cost function corresponding to each neighborhood component in the plurality of neighborhood components in each of the one or more images, identifying at least two structures of interest in each image in the one or more images based on the cost function, wherein the at least two structures of interest include a pubic ramus and a fetal head, measuring an angle of progression based on the at least two structures of interest, and determining the fetal head descent in the birth canal based on the angle of progression.Type: ApplicationFiled: August 12, 2014Publication date: February 18, 2016Inventors: Nitin Singhal, Kajoli Banerjee Krishnan, Christian Fritz Perrey, Klaus Pintoffl, Walter Duda, JR., Francesca Patruno
-
Publication number: 20150149246Abstract: A computing device receives a first user input requesting an estimated revenue for a projected time period. The computing device receives a second user input. The computing device determines an expected revenue for the projected time period from new maintenance contracts and renewed maintenance contracts and an expected revenue for the projected time period from warranty upgrades on units based on at least the current number of installed units as of the base time period, the expected number of unit installations for the projected time period, the attrition rate and the warranty option upgrade rate. The computing device determines a total expected revenue for the projected time period based on at least the computing device determining the expected revenue for the projected time period from new maintenance contracts and renewed maintenance contracts and the expected revenue for the projected time period from warranty upgrades on installed units.Type: ApplicationFiled: November 25, 2013Publication date: May 28, 2015Applicant: International Business Machines CorporationInventors: Edward Cannon, Sue Lynn Chong, John J. Dillon, Dawn M. Fritz, Kurt W. Mueller, Nitin Singhal
-
Patent number: 8638979Abstract: Provided are a method and apparatus for combining and composing a plurality of images into one image. An image processing unit calculates importance levels of the plurality of input images, respectively, according to selection criteria, selects at least two important images from among the plurality of input images according to the calculated importance levels, determines Regions Of Interest (ROIs) of the important images, selects the ROIs in one canvas, arranges corresponding important images at positions corresponding to the selected ROIs, and composes the arranged important images into one image.Type: GrantFiled: January 27, 2011Date of Patent: January 28, 2014Assignees: Samsung Electronics Co., Ltd, Inha-Industry Partnership InstituteInventors: Nitin Singhal, Sung-Dae Cho, In-Kyu Park, Man-Hee Lee
-
Patent number: 8543940Abstract: A method and apparatus for browsing media content and executing functions related to the media content are provided. Under the state that a collage image generated by combining a plurality of image elements corresponding respectively to a plurality of media contents is displayed, if a selection input is generated on the collage image, a preview window for a media content corresponding to a location of a point where the selection input is generated is configured to overlay the preview window on the collage image. If a function execution input is generated on the collage image, a representative function is performed using a media content corresponding to a location of a point where the function execution input is generated.Type: GrantFiled: October 25, 2010Date of Patent: September 24, 2013Assignee: Samsung Electronics Co., LtdInventors: Nitin Singhal, Sung-Dae Cho, Chung-Hoon Kim, Yoon-Choon Hwang
-
Publication number: 20110280475Abstract: An apparatus and method for out-focusing photography in a portable terminal is disclosed, including detecting a position of each pixel corresponding to a light area from an original image, generating a blurred image by blurring the original image, mapping a preset texture in correspondence with the detected positions of the pixels in the blurred image, and outputting a result image by mixing the image in which the texture is mapped and the original image, a user can perform out-focusing photography by using a portable terminal having a small lens iris.Type: ApplicationFiled: May 12, 2011Publication date: November 17, 2011Applicant: Samsung Electronics Co., Ltd.Inventors: Nitin SINGHAL, Ji-Hye Kim, Sung-Dae Cho
-
Publication number: 20110234611Abstract: A handheld device including a Central Processing Unit (CPU) for receiving an original image input into the handheld device, and converting the original image into a quadrilateral image corresponding to a display size; and a General Purpose Computing on Graphics Processing Unit (GPGPU) for setting fragments for pixels included within vertices of the quadrilateral image, and applying a predetermined algorithm for image processing to the original image.Type: ApplicationFiled: March 28, 2011Publication date: September 29, 2011Applicant: Samsung Electronics Co., Ltd.Inventors: Nitin Singhal, Sung-Dae Cho, Chung-Hoon Kim, Abhinav Arora, Yoon-Choon Hwang
-
Publication number: 20110200273Abstract: Provided are a method and apparatus for combining and composing a plurality of images into one image. An image processing unit calculates importance levels of the plurality of input images, respectively, according to selection criteria, selects at least two important images from among the plurality of input images according to the calculated importance levels, determines Regions Of Interest (ROIs) of the important images, selects the ROIs in one canvas, arranges corresponding important images at positions corresponding to the selected ROIs, and composes the arranged important images into one image.Type: ApplicationFiled: January 27, 2011Publication date: August 18, 2011Applicants: Samsung Electronics Co., Ltd., Inha-Industry Partnership InstituteInventors: Nitin SINGHAL, Sung-Dae Cho, In-Kyu Park, Man-Hee Lee
-
Publication number: 20110141257Abstract: A facial image registration apparatus and method are provided for registering a plurality of facial images to be used for face recognition. A plurality of facial images are detected and sorted from a plurality of captured images input from a camera unit at the request of a user. A face feature value is calculated for each of the facial images. The face feature value is a score that is applied according to face features of each of the facial images. Facial images selected according to the calculated face feature values are registered as target facial images to be used for face recognition. As such, various facial images may be registered at a user's single request, thus improving a face recognition rate.Type: ApplicationFiled: December 15, 2010Publication date: June 16, 2011Applicant: Samsung Electronics Co., Ltd.Inventors: Yoon-Choon Hwang, Sung-Dae Cho, Byung-Jun Son, Tae-Hwa Hong, Chung-Hoon Kim, Nitin Singhal
-
Publication number: 20110099514Abstract: A method and apparatus for browsing media content and executing functions related to the media content are provided. Under the state that a collage image generated by combining a plurality of image elements corresponding respectively to a plurality of media contents is displayed, if a selection input is generated on the collage image, a preview window for a media content corresponding to a location of a point where the selection input is generated is configured to overlay the preview window on the collage image. If a function execution input is generated on the collage image, a representative function is performed using a media content corresponding to a location of a point where the function execution input is generated.Type: ApplicationFiled: October 25, 2010Publication date: April 28, 2011Applicant: Samsung Electronics Co., Ltd.Inventors: Nitin SINGHAL, Sung-Dae Cho, Chung-Hoon Kim, Yoon-Choon Hwang