Patents by Inventor Girish Srinivasa Murthy

Girish Srinivasa Murthy 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: 11430136
    Abstract: Methods, apparatus, systems and articles of manufacture to improve efficiency of object tracking in video frames are disclosed. An example apparatus includes a clusterer to cluster a map of a video frame into blobs; a comparator to determine an intersection over union value between the blobs and bounding boxes in a second video frame; and an interface to initiate object detection by a neural network on the first video frame when the intersection over union does not satisfy a threshold.
    Type: Grant
    Filed: December 19, 2019
    Date of Patent: August 30, 2022
    Assignee: Intel Corporation
    Inventors: Srenivas Varadarajan, Girish Srinivasa Murthy, Anand Bodas, Omesh Tickoo, Vallabhajosyula Somayazulu
  • Publication number: 20200134837
    Abstract: Methods, apparatus, systems and articles of manufacture to improve efficiency of object tracking in video frames are disclosed. An example apparatus includes a clusterer to cluster a map of a video frame into blobs; a comparator to determine an intersection over union value between the blobs and bounding boxes in a second video frame; and an interface to initiate object detection by a neural network on the first video frame when the intersection over union does not satisfy a threshold.
    Type: Application
    Filed: December 19, 2019
    Publication date: April 30, 2020
    Inventors: Srenivas Varadarajan, Girish Srinivasa Murthy, Anand Bodas, Omesh Tickoo, Vallabhajosyula Somayazulu
  • Patent number: 8780973
    Abstract: A method for encoding a picture in a video sequence is provided that includes determining the current encoded size of the picture after coding a plurality of macroblocks in the picture, determining that encoding remaining macroblocks in the picture may cause the encoded size of the picture to exceed a maximum encoded picture size, computing a quantization scale responsive to the determining, wherein the quantization scale is computed such that the estimated encoded size of the remaining macroblocks if the remaining macroblocks are quantized with the quantization scale does not exceed the difference between the maximum encoded picture size and the current encoded picture size, and quantizing at least one of the remaining macroblocks with the new quantization scale.
    Type: Grant
    Filed: August 10, 2011
    Date of Patent: July 15, 2014
    Assignee: Texas Instruments Incorporated
    Inventors: Naveen Srinivasamurthy, Girish Srinivasa Murthy, Satish Kumar, Soyeb Nagori
  • Publication number: 20120039386
    Abstract: A method for encoding a picture in a video sequence is provided that includes determining the current encoded size of the picture after coding a plurality of macroblocks in the picture, determining that encoding remaining macroblocks in the picture may cause the encoded size of the picture to exceed a maximum encoded picture size, computing a quantization scale responsive to the determining, wherein the quantization scale is computed such that the estimated encoded size of the remaining macroblocks if the remaining macroblocks are quantized with the quantization scale does not exceed the difference between the maximum encoded picture size and the current encoded picture size, and quantizing at least one of the remaining macroblocks with the new quantization scale.
    Type: Application
    Filed: August 10, 2011
    Publication date: February 16, 2012
    Inventors: Naveen Srinivasamurthy, Girish Srinivasa Murthy, Satish Kumar, Soyeb Nagori