Patents by Inventor Manohar SRIKANTH

Manohar SRIKANTH 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: 10574905
    Abstract: Systems and methods in accordance with embodiments of this invention perform depth regularization and semiautomatic interactive matting using images. In an embodiment of the invention, the image processing pipeline application directs a processor to receive (i) an image (ii) an initial depth map corresponding to the depths of pixels within the image, regularize the initial depth map into a dense depth map using depth values of known pixels to compute depth values of unknown pixels, determine an object of interest to be extracted from the image, generate an initial trimap using the dense depth map and the object of interest to be extracted from the image, and apply color image matting to unknown regions of the initial trimap to generate a matte for image matting.
    Type: Grant
    Filed: October 1, 2018
    Date of Patent: February 25, 2020
    Assignee: FotoNation Limited
    Inventors: Manohar Srikanth, Ravi Ramamoorthi, Kartik Venkataraman, Priyam Chatterjee
  • Patent number: 10540806
    Abstract: Systems and methods for automatically correcting apparent distortions in close range photographs that are captured using an imaging system capable of capturing images and depth maps are disclosed. In many embodiments, faces are automatically detected and segmented from images using a depth-assisted alpha matting. The detected faces can then be re-rendered from a more distant viewpoint and composited with the background to create a new image in which apparent perspective distortion is reduced.
    Type: Grant
    Filed: February 19, 2018
    Date of Patent: January 21, 2020
    Assignee: FotoNation Limited
    Inventors: Samuel Yang, Manohar Srikanth, Dan Lelescu, Kartik Venkataraman
  • Publication number: 20190037150
    Abstract: Systems and methods in accordance with embodiments of this invention perform depth regularization and semiautomatic interactive matting using images. In an embodiment of the invention, the image processing pipeline application directs a processor to receive (i) an image (ii) an initial depth map corresponding to the depths of pixels within the image, regularize the initial depth map into a dense depth map using depth values of known pixels to compute depth values of unknown pixels, determine an object of interest to be extracted from the image, generate an initial trimap using the dense depth map and the object of interest to be extracted from the image, and apply color image matting to unknown regions of the initial trimap to generate a matte for image matting.
    Type: Application
    Filed: October 1, 2018
    Publication date: January 31, 2019
    Inventors: Manohar SRIKANTH, Ravi RAMAMOORTHI, Kartik VENKATARAMAN, Priyam CHATTERJEE
  • Patent number: 10089740
    Abstract: Systems and methods in accordance with embodiments of this invention perform depth regularization and semiautomatic interactive matting using images. In an embodiment of the invention, the image processing pipeline application directs a processor to receive (i) an image (ii) an initial depth map corresponding to the depths of pixels within the image, regularize the initial depth map into a dense depth map using depth values of known pixels to compute depth values of unknown pixels, determine an object of interest to be extracted from the image, generate an initial trimap using the dense depth map and the object of interest to be extracted from the image, and apply color image matting to unknown regions of the initial trimap to generate a matte for image matting.
    Type: Grant
    Filed: March 9, 2015
    Date of Patent: October 2, 2018
    Assignee: FotoNation Limited
    Inventors: Manohar Srikanth, Ravi Ramamoorthi, Kartik Venkataraman, Priyam Chatterjee
  • Publication number: 20180240265
    Abstract: Systems and methods for automatically correcting apparent distortions in close range photographs that are captured using an imaging system capable of capturing images and depth maps are disclosed. In many embodiments, faces are automatically detected and segmented from images using a depth-assisted alpha matting. The detected faces can then be re-rendered from a more distant viewpoint and composited with the background to create a new image in which apparent perspective distortion is reduced.
    Type: Application
    Filed: February 19, 2018
    Publication date: August 23, 2018
    Applicant: FotoNation Cayman Limited
    Inventors: Samuel Yang, Manohar Srikanth, Dan Lelescu, Kartik Venkataraman
  • Patent number: 9898856
    Abstract: Systems and methods for automatically correcting apparent distortions in close range photographs that are captured using an imaging system capable of capturing images and depth maps are disclosed. In many embodiments, faces are automatically detected and segmented from images using a depth-assisted alpha matting. The detected faces can then be re-rendered from a more distant viewpoint and composited with the background to create a new image in which apparent perspective distortion is reduced.
    Type: Grant
    Filed: September 29, 2014
    Date of Patent: February 20, 2018
    Assignee: FotoNation Cayman Limited
    Inventors: Samuel Yang, Manohar Srikanth, Dan Lelescu, Kartik Venkataraman
  • Publication number: 20160173869
    Abstract: An apparatus comprises a main camera configured to produce a high quality image; at least two auxiliary cameras configured to produce images of lower quality; and electronic circuitry linked to the main camera and the at least two auxiliary cameras, the electronic circuitry comprising a controller having a memory and a processor, the electronic circuitry configured to operate on data pertaining to the high quality image and pertaining to the images of lower quality to produce an enhanced high quality image as output data.
    Type: Application
    Filed: December 15, 2014
    Publication date: June 16, 2016
    Inventors: Ting-Chun Wang, Manohar Srikanth
  • Patent number: 9170580
    Abstract: A method determines trajectories of redundant actuators of a machine including a first actuator and a second actuator. The method determines a first trajectory of the first actuator tracking a reference trajectory with an error tolerance, wherein the error tolerance is a function of a constraint of the second actuator, and determines a second trajectory of the second actuator based on a difference between the reference trajectory and the first trajectory.
    Type: Grant
    Filed: October 19, 2012
    Date of Patent: October 27, 2015
    Assignee: Mitsubishi Electric Rsearch Laboratories, Inc.
    Inventors: Vijay Shilpiekandula, Matthew Brand, Manohar Srikanth, Scott A. Bortoff
  • Publication number: 20150254868
    Abstract: Systems and methods in accordance with embodiments of this invention perform depth regularization and semiautomatic interactive matting using images. In an embodiment of the invention, the image processing pipeline application directs a processor to receive (i) an image (ii) an initial depth map corresponding to the depths of pixels within the image, regularize the initial depth map into a dense depth map using depth values of known pixels to compute depth values of unknown pixels, determine an object of interest to be extracted from the image, generate an initial trimap using the dense depth map and the object of interest to be extracted from the image, and apply color image matting to unknown regions of the initial trimap to generate a matte for image matting.
    Type: Application
    Filed: March 9, 2015
    Publication date: September 10, 2015
    Inventors: Manohar Srikanth, Ravi Ramamoorthi, Kartik Venkataraman, Priyam Chatterjee
  • Publication number: 20150091900
    Abstract: Systems and methods for automatically correcting apparent distortions in close range photographs that are captured using an imaging system capable of capturing images and depth maps are disclosed. In many embodiments, faces are automatically detected and segmented from images using a depth-assisted alpha matting. The detected faces can then be re-rendered from a more distant viewpoint and composited with the background to create a new image in which apparent perspective distortion is reduced.
    Type: Application
    Filed: September 29, 2014
    Publication date: April 2, 2015
    Inventors: Samuel Yang, Manohar Srikanth, Dan Lelescu, Kartik Venkataraman
  • Publication number: 20140114463
    Abstract: A method determines trajectories of redundant actuators of a machine including a first actuator and a second actuator. The method determines a first trajectory of the first actuator tracking a reference trajectory with an error tolerance, wherein the error tolerance is a function of a constraint of the second actuator, and determines a second trajectory of the second actuator based on a difference between the reference trajectory and the first trajectory.
    Type: Application
    Filed: October 19, 2012
    Publication date: April 24, 2014
    Applicant: Mitsubishi Electric Research Laboratories, Inc.
    Inventors: Vijay Shilpiekandula, Matthew Brand, Manohar Srikanth, Scott A. Bortoff
  • Publication number: 20070146325
    Abstract: Disclosed herein are a system and method for simultaneously reporting changes in location and orientation of an object moving over a planar surface and forming part of a computer input device, interoperably with a conventional mouse where reporting only location is in question. Further the present invention provides improved ways of user interaction with computer displays of two and three dimensional data and structures.
    Type: Application
    Filed: December 27, 2006
    Publication date: June 28, 2007
    Inventors: Timothy POSTON, Manohar SRIKANTH