Patents by Inventor Sandeep Kanumuri

Sandeep Kanumuri 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: 9967418
    Abstract: The present disclosure provides devices and techniques for processing a media capture stream captured by a camera device using a chain device media foundation transform (DMFT). The techniques include configuring multiple DMFTs such that an original manufacturer (OEM) may have flexibility in independently selecting various functionalities from different sources (e.g., OS, OEM, IHV, ISV, or VARs) in order to maximize hardware capabilities while minimizing the drawbacks of creating a single DMFT. To that end, the implementation of the present disclosure includes a devices and techniques of chainable DMFTs such that a device transform manager may select a set of functionalities (e.g., face recognition, color effects, etc.) from multiple vendors to customize the camera's capabilities according to the OEM specification.
    Type: Grant
    Filed: October 31, 2016
    Date of Patent: May 8, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Sandeep Kanumuri, Naveen Thumpudi, Sathyanarayanan Karivaradaswamy, Rui Zhao
  • Publication number: 20180124270
    Abstract: The present disclosure provides devices and techniques for processing a media capture stream captured by a camera device using a chain device media foundation transform (DMFT). The techniques include configuring multiple DMFTs such that an original manufacturer (OEM) may have flexibility in independently selecting various functionalities from different sources (e.g., OS, OEM, IHV, ISV, or VARs) in order to maximize hardware capabilities while minimizing the drawbacks of creating a single DMFT. To that end, the implementation of the present disclosure includes a devices and techniques of chainable DMFTs such that a device transform manager may select a set of functionalities (e.g., face recognition, color effects, etc.) from multiple vendors to customize the camera's capabilities according to the OEM specification.
    Type: Application
    Filed: October 31, 2016
    Publication date: May 3, 2018
    Inventors: Sandeep KANUMURI, Naveen THUMPUDI, Sathyanarayanan KARIVARADASWAMY, Rui ZHAO
  • Publication number: 20180097986
    Abstract: Methods and devices for enabling controls of an imaging device may include receiving a data stream with a request for at least one control of an imaging device, wherein the at least one control is related to Universal Serial Bus (USB) video. The methods and devices may include identifying a defined functionality of the at least one control and transmitting the data stream to the imaging device to specify the operation of the imaging device based on the defined functionality of the at least one control. The methods and devices may also include generating metadata information from received video frame packets from an imaging device. The methods and devices may include identifying metadata information in the header of a video packet when the header size exceeds the standard header size. The methods and devices may include generating a metadata buffer with the identified metadata information.
    Type: Application
    Filed: March 10, 2017
    Publication date: April 5, 2018
    Inventors: Sandeep KANUMURI, Naveen THUMPUDI, Sang CHOE, Sathyanarayanan KARIVARADASWAMY, Joel CORLEY
  • Patent number: 9892188
    Abstract: Innovations for category-prefixed data batching (“CPDB”) of entropy-coded data or other payload data for coded media data, as well as innovations for corresponding recovery of the entropy-coded data (or other payload data) formatted with CPDB. The CPDB can be used in conjunction with coding/decoding for video content, image content, audio content or another type of content. For example, after receiving coded media data in multiple categories from encoding units, a formatting tool formats payload data with CPDB, generating a batch prefix for a batch of the CPDB-formatted payload data. The batch prefix includes a category identifier and a data quantity indicator. The formatting tool outputs the CPDB-formatted payload data to a bitstream. At the decoder side, a formatting tool receives the CPDB-formatted payload data in a bitstream, recovers the payload data from the CPDB-formatted payload data, and outputs the payload data (e.g., to decoding units).
    Type: Grant
    Filed: November 8, 2012
    Date of Patent: February 13, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Gary J. Sullivan, Leon Bottou, Sandeep Kanumuri, Yongjun Wu
  • Patent number: 9876837
    Abstract: A processor that processes encoded media is configured so as to apply constraints to the encoded bitstream. Such constraints are not those required by a specification of a standard with which the encoded media is compliant; instead such constraints reflect portions of the standard that are insufficiently constrained and are applied by the processor to ensure that the processor does not experience performance degradation or errors. The constraints can be applied, for example, as a preprocessing step before reading, writing or decoding the bitstream, or while the bitstream is being decoded, or while the bitstream is being received from a transmission.
    Type: Grant
    Filed: April 29, 2016
    Date of Patent: January 23, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Sandeep Kanumuri, Shyam Sadhwani
  • Publication number: 20170318309
    Abstract: Innovations in signaling of reference picture list (“RPL”) modification information. For example, a video encoder evaluates a condition that depends at least in part on a variable indicating a number of total reference pictures. Depending on the results of the evaluation, the encoder signals in a bit stream a flag that indicates whether an RPL is modified according to syntax elements explicitly signaled in the bit stream. A video decoder evaluates the condition and, depending on results of the evaluation, parses from a bit stream a flag that indicates whether an RPL is modified according to syntax elements explicitly signaled in the bit stream. The condition can be evaluated as part of processing for an RPL modification structure that includes the flag, or as part of processing for a slice header. The encoder and decoder can also evaluate other conditions that affect syntax elements for list entries of the RPL modification information.
    Type: Application
    Filed: July 20, 2017
    Publication date: November 2, 2017
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Gary J. Sullivan, Sandeep Kanumuri
  • Patent number: 9762928
    Abstract: Innovations in signaling of reference picture list (“RPL”) modification information. For example, a video encoder evaluates a condition that depends at least in part on a variable indicating a number of total reference pictures. Depending on the results of the evaluation, the encoder signals in a bitstream a flag that indicates whether an RPL is modified according to syntax elements explicitly signaled in the bitstream. A video decoder evaluates the condition and, depending on results of the evaluation, parses from a bitstream a flag that indicates whether an RPL is modified according to syntax elements explicitly signaled in the bitstream. The condition can be evaluated as part of processing for an RPL modification structure that includes the flag, or as part of processing for a slice header. The encoder and decoder can also evaluate other conditions that affect syntax elements for list entries of the RPL modification information.
    Type: Grant
    Filed: March 8, 2016
    Date of Patent: September 12, 2017
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Gary J. Sullivan, Sandeep Kanumuri
  • Patent number: 9723200
    Abstract: One or more techniques and/or systems are provided for camera capture recommendation. For example, an application may operate to capture an image using a capture device (e.g., a user may use a camera of a smart phone to capture a vacation photo for sharing through a social network app). Camera parameters of the capture device and/or a preview data stream (e.g., pixel data depicting a beach “seen” by the camera in real-time) may be used to generate a camera capture recommendation (e.g., a recommendation to use a haze removal module, a high dynamic range module, a focus bracketing module, etc.). The camera capture recommendation is provided to the application. In this way, the application may selectively use, override, supplement (e.g., use an application supplied module), or modify the camera capture recommendation for application to the capture device to obtain an output image.
    Type: Grant
    Filed: October 15, 2014
    Date of Patent: August 1, 2017
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Sandeep Kanumuri, Naveen Thumpudi
  • Publication number: 20170142445
    Abstract: Disclosed herein are innovations for bitstreams having clean random access (CRA) pictures and/or other types of random access point (RAP) pictures. New type definitions and strategic constraints on types of RAP pictures can simplify mapping of units of elementary video stream data to a container format. Such innovations can help improve the ability for video coding systems to more flexibly perform adaptive video delivery, production editing, commercial insertion, and the like.
    Type: Application
    Filed: December 15, 2016
    Publication date: May 18, 2017
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Gary J. Sullivan, Sandeep Kanumuri
  • Publication number: 20170026661
    Abstract: The present invention provides low complexity planar mode coding in which a value of a bottom-right pixel in a prediction block is calculated from a value of at least one pixel in at least one of an array of horizontal boundary pixels and an array of vertical boundary pixels. Linear and bi-linear interpolations on the value of the bottom-right pixel and values of at least some of the horizontal and vertical boundary pixels to derive values of remaining pixels in the prediction block. A residual between the prediction block and an original block is signaled to a decoder.
    Type: Application
    Filed: October 3, 2016
    Publication date: January 26, 2017
    Inventors: Frank Jan BOSSEN, Sandeep KANUMURI
  • Patent number: 9532055
    Abstract: Disclosed herein are innovations for bitstreams having clean random access (CRA) pictures and/or other types of random access point (RAP) pictures. New type definitions and strategic constraints on types of RAP pictures can simplify mapping of units of elementary video stream data to a container format. Such innovations can help improve the ability for video coding systems to more flexibly perform adaptive video delivery, production editing, commercial insertion, and the like.
    Type: Grant
    Filed: December 31, 2012
    Date of Patent: December 27, 2016
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Gary J. Sullivan, Sandeep Kanumuri
  • Publication number: 20160323349
    Abstract: A processor that processes encoded media is configured so as to apply constraints to the encoded bitstream. Such constraints are not those required by a specification of a standard with which the encoded media is compliant; instead such constraints reflect portions of the standard that are insufficiently constrained and are applied by the processor to ensure that the processor does not experience performance degradation or errors. The constraints can be applied, for example, as a preprocessing step before reading, writing or decoding the bitstream, or while the bitstream is being decoded, or while the bitstream is being received from a transmission.
    Type: Application
    Filed: April 29, 2016
    Publication date: November 3, 2016
    Inventors: Sandeep Kanumuri, Shyam Sadhwani
  • Publication number: 20160323490
    Abstract: A facility for generating at least one image is described. For each of multiple registered photography scenarios, the facility determines a suitable score for the scenario based upon state of a photography device. The facility selects a scenario having a suitability score that is no lower than any other determined suitability score. The facility then captures a sequence of one or more frames in a manner specified for the selected scenario, and processes that captured sequence of frames in a manner specified for the selected scenario to obtain at least one image.
    Type: Application
    Filed: April 28, 2015
    Publication date: November 3, 2016
    Inventors: Naveen Thumpudi, Denis Demandolx, Sandeep Kanumuri, Suhib Alsisan, William Guyman, Yijie Wang
  • Publication number: 20160316206
    Abstract: Innovations in control and use of chroma quantization parameter (“QP”) values that depend on luma QP values. More generally, the innovations relate to control and use of QP values for a secondary color component that depend on QP values for a primary color component. For example, during encoding, an encoder determines a QP index from a primary component QP and secondary component QP offset. The encoder maps the QP index to a secondary component QP, which has an extended range. The encoder outputs at least part of a bitstream including the encoded content. A corresponding decoder receives at least part of a bitstream including encoded content. During decoding, the decoder determines a QP index from a primary component QP and secondary component QP offset, then maps the QP index to a secondary component QP, which has an extended range.
    Type: Application
    Filed: July 6, 2016
    Publication date: October 27, 2016
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Gary J. Sullivan, Sandeep Kanumuri
  • Patent number: 9414054
    Abstract: Innovations in control and use of chroma quantization parameter (“QP”) values that depend on luma QP values. More generally, the innovations relate to control and use of QP values for a secondary color component that depend on QP values for a primary color component. For example, during encoding, an encoder determines a QP index from a primary component QP and secondary component QP offset. The encoder maps the QP index to a secondary component QP, which has an extended range. The encoder outputs at least part of a bitstream including the encoded content. A corresponding decoder receives at least part of a bitstream including encoded content. During decoding, the decoder determines a QP index from a primary component QP and secondary component QP offset, then maps the QP index to a secondary component QP, which has an extended range.
    Type: Grant
    Filed: December 31, 2012
    Date of Patent: August 9, 2016
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Gary J. Sullivan, Sandeep Kanumuri
  • Patent number: 9398217
    Abstract: One or more techniques and/or systems are provided for video stabilization and/or for image frame generation. For example, a user may instruct a video application hosted on a smart phone to capture a video at a target resolution of 1080 pixels. A padded input having a padded resolution that is larger than the target resolution may be obtained from a capture device, such as a camera of the smart phone. The padded input may be provided to a video stabilization component to obtain a target image frame having the target resolution. In this way, the video stabilization component may perform cropping using padded margin pixels (e.g., additional pixels of the padded input beyond the 1080 pixels of the target resolution) so that image upscaling after cropping (e.g., to account for global warping, etc.) may be mitigated to reduce blur that may otherwise result from image upscaling.
    Type: Grant
    Filed: October 15, 2014
    Date of Patent: July 19, 2016
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Jinglin Shen, Naveen Thumpudi, Jeffrey D. Day, Yongjun Wu, Sandeep Kanumuri
  • Publication number: 20160191949
    Abstract: Innovations in signaling of reference picture list (“RPL”) modification information. For example, a video encoder evaluates a condition that depends at least in part on a variable indicating a number of total reference pictures. Depending on the results of the evaluation, the encoder signals in a bitstream a flag that indicates whether an RPL is modified according to syntax elements explicitly signaled in the bitstream. A video decoder evaluates the condition and, depending on results of the evaluation, parses from a bitstream a flag that indicates whether an RPL is modified according to syntax elements explicitly signaled in the bitstream. The condition can be evaluated as part of processing for an RPL modification structure that includes the flag, or as part of processing for a slice header. The encoder and decoder can also evaluate other conditions that affect syntax elements for list entries of the RPL modification information.
    Type: Application
    Filed: March 8, 2016
    Publication date: June 30, 2016
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Gary J. Sullivan, Sandeep Kanumuri
  • Patent number: 9330101
    Abstract: A processor that processes encoded media is configured so as to apply constraints to the encoded bitstream. Such constraints are not those required by a specification of a standard with which the encoded media is compliant; instead such constraints reflect portions of the standard that are insufficiently constrained and are applied by the processor to ensure that the processor does not experience performance degradation or errors. The constraints can be applied, for example, as a preprocessing step before reading, writing or decoding the bitstream, or while the bitstream is being decoded, or while the bitstream is being received from a transmission.
    Type: Grant
    Filed: December 18, 2013
    Date of Patent: May 3, 2016
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Sandeep Kanumuri, Shyam Sadhwani
  • Patent number: 9324184
    Abstract: Among other things, one or more techniques and/or systems are disclosed for creating a three-dimensional model of an image. Image data, comprise a series of images of a location, such as along a route, can be received. The image data can comprise a first image element location for a first image element, where the first image element location may correspond to a three-dimensional point in the image, such as a location in the image with a depth from a point of observation. The first image element can be segmented into a first façade plane using the first image element location. The first façade plane can be merged with a second façade plane, resulting in a three-dimensional model of the image. The second façade plane can comprise a second image element, where the image data comprises a second image element location for the second image element.
    Type: Grant
    Filed: December 14, 2011
    Date of Patent: April 26, 2016
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Samuel Williams, Jett Evan Jones, Peter G. Sibley, Don Kim, Sandeep Kanumuri, Jonathan Rosenberg
  • Publication number: 20160112638
    Abstract: One or more techniques and/or systems are provided for video stabilization and/or for image frame generation. For example, a user may instruct a video application hosted on a smart phone to capture a video at a target resolution of 1080 pixels. A padded input having a padded resolution that is larger than the target resolution may be obtained from a capture device, such as a camera of the smart phone. The padded input may be provided to a video stabilization component to obtain a target image frame having the target resolution. In this way, the video stabilization component may perform cropping using padded margin pixels (e.g., additional pixels of the padded input beyond the 1080 pixels of the target resolution) so that image upscaling after cropping (e.g., to account for global warping, etc.) may be mitigated to reduce blur that may otherwise result from image upscaling.
    Type: Application
    Filed: October 15, 2014
    Publication date: April 21, 2016
    Inventors: Jinglin Shen, Naveen Thumpudi, Jeffrey D. Day, Yongjun Wu, Sandeep Kanumuri