Patents by Inventor Pranav MISHRA

Pranav MISHRA 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).

  • Publication number: 20220244336
    Abstract: Methods, apparatus, systems and articles of manufacture to trigger calibration of a sensor node using machine learning are disclosed. An example apparatus includes a machine learning model trainer to train a machine learning model using first sensor data collected from a sensor node. A disturbance forecaster is to, using the machine learning model and second sensor data, forecast a temporal disturbance to a communication of the sensor node. A communications processor is to transmit a first calibration trigger in response to a determination that a start of the temporal disturbance is forecasted and a determination that a first calibration trigger has not been sent.
    Type: Application
    Filed: November 8, 2021
    Publication date: August 4, 2022
    Inventors: Yatish Mishra, Mats Agerstam, Mateo Guzman, Sindhu Pandian, Shubhangi Rajasekhar, Pranav Sanghadia, Troy Willes
  • Patent number: 10267639
    Abstract: An approach is provided for validating potential points of interest using device and user characteristics. The validation platform processes and/or facilitates a processing of location information associated with at least one device to determine one or more potential points of interest visited by the at least one device. Next, the validation platform causes, at least in part, a tagging of the one or more potential points of interest with one or more characteristics of the at least one device, one or more users of the at least one device, or a combination thereof. Then, the validation platform causes, at least on part, a validation of the one or more potential points of interest based, at least in part, on the one or more characteristics as captured by at least one other device, one or more other users of the at least one other device, or a combination thereof.
    Type: Grant
    Filed: December 3, 2013
    Date of Patent: April 23, 2019
    Assignee: Nokia Technologies Oy
    Inventor: Pranav Mishra
  • Publication number: 20190005672
    Abstract: An image acquisition unit that acquires a photographic image showing a hand on which a card of a known size is placed. A card detection unit detects a size of the card in the photographic image. A finger joint measurement unit measures a size of the joint of the finger for the ring in the photographic image. A finger size estimation unit estimates an actual size of the joint of the finger for the ring from a measured value of the size of the joint of the finger of the ring in the photographic image, based on a ratio between the known size of the card and the size of the card in the photographic image detected. A ring size determination unit determines a size of the ring based on an estimated actual size of the joint of the finger for the ring.
    Type: Application
    Filed: June 22, 2018
    Publication date: January 3, 2019
    Inventors: John McLear, Satya Mallick, Pranav Mishra
  • Patent number: 10146316
    Abstract: A method includes, in response to a detected gesture user input, wherein the gesture user input is ambiguous as to which one of a plurality of putative targets the gesture user input is directed, disambiguating the plurality of putative targets using disambiguating data to enable selection of one of the plurality of targets; and performing, in response to the gesture user input, a user input command associated with the selected target.
    Type: Grant
    Filed: November 2, 2012
    Date of Patent: December 4, 2018
    Assignee: Nokia Technologies Oy
    Inventors: Pranav Mishra, Rajeswari Kannan
  • Patent number: 10102827
    Abstract: An apparatus for generating a panoramic image(s) may include a processor and memory storing executable computer code causing the apparatus to at least perform operations including generating a panoramic image(s) based on performing registration on at least two images associated with depth map data and determining an overlap region(s) between the two images within first and second items of depth map data. The computer program code may further cause the apparatus to label the overlap region(s) within the first or second item of depth map data based on generating a virtual seam(s) connecting portions of the two images to generate a composite image. The portions correspond to image data within first and second items of depth map data. The computer program code may further cause the apparatus to blend the seam of the composite image to obtain the panoramic image. Corresponding methods and computer program products are also provided.
    Type: Grant
    Filed: April 5, 2012
    Date of Patent: October 16, 2018
    Assignee: Nokia Technologies Oy
    Inventors: Gururaj Gopal Putraya, Pranav Mishra, Krishna Annasagar Govindarao
  • Patent number: 9760764
    Abstract: An apparatus for recognizing faces with different illuminations may include a processor and memory storing executable computer program code causing the apparatus to at least perform operations including detecting and extracting face data of a first candidate face of a first image and a second candidate face of a second image. The first image is associated with a first light intensity and the second image associated with a second light intensity different from the first light intensity. The computer program code may further cause the apparatus to analyze face data to determine whether the first candidate face corresponds to an area in the first image that is substantially the same as an area of the second candidate face and evaluate data of the first and second areas to determine whether the first and second candidate faces are valid or invalid faces. Corresponding methods and computer program products are also provided.
    Type: Grant
    Filed: November 4, 2011
    Date of Patent: September 12, 2017
    Assignee: Nokia Technologies Oy
    Inventors: Pranav Mishra, Vinod Pathangay, Krishna Govindarao
  • Patent number: 9648214
    Abstract: An apparatus including a substrate; a plurality of first image sensels supported by the substrate and arranged in rows and columns, wherein the substrate includes one or more apertures.
    Type: Grant
    Filed: April 26, 2013
    Date of Patent: May 9, 2017
    Assignee: Nokia Technologies Oy
    Inventors: Pranav Mishra, Gururaj Putraya
  • Patent number: 9582681
    Abstract: In accordance with an example embodiment of the present invention, a method is disclosed. The method includes defining a first privacy setting related to a user. Communicating the first privacy setting using a first radio communication network to a server. Storing the first privacy setting related to the user on the server. Applying the first privacy setting when analyzing an image to determine the user in the image. Determining to apply a second privacy setting related to the user. Defining the second privacy setting related to the user and communicating the second privacy setting to another device of a second user using a second radio communication network.
    Type: Grant
    Filed: April 19, 2013
    Date of Patent: February 28, 2017
    Assignee: Nokia Technologies Oy
    Inventor: Pranav Mishra
  • Patent number: 9549129
    Abstract: A method comprising reading out first lines of pixels of a sensor, when the first lines are read out in a sequence of the first lines in a first direction along the sensor also reading out different second lines of the pixels of the sensor, when the second lines are read out in a sequence of the second lines in a different second direction along the sensor and interleaving the read outs from the first lines of pixels and the different second lines of pixels.
    Type: Grant
    Filed: October 4, 2013
    Date of Patent: January 17, 2017
    Assignee: Nokia Technologies Oy
    Inventors: Ramesh Raskar, Rajeswari Kannan, Pranav Mishra
  • Patent number: 9400937
    Abstract: In an example embodiment, a method, apparatus and computer program product are provided. The method includes facilitating capture of at least one image of a scene including a foreground object by at least one rolling shutter sensor. The at least one image includes a pattern in an image region of the foreground object comprising a series of alternate dark and bright pixel regions. The at least one image is captured by setting exposure time of the sensor as equal or less than a read-out time of a set of pixel rows of a plurality of pixel rows, and by facilitating a repeating sequence of ON and OFF of flash such that flash is ON while capturing the set of pixel rows, and OFF while capturing subsequent set of pixel rows. The method includes determining a contour of the foreground object in the at least one image based on the pattern.
    Type: Grant
    Filed: November 18, 2014
    Date of Patent: July 26, 2016
    Assignee: Nokia Technologies Oy
    Inventors: Pranav Mishra, Rajeswari Kannan, Ravi Shenoy, Ramesh Raskar
  • Publication number: 20160189387
    Abstract: In exemplary implementations of this invention, a depth-sensing system includes multiple light sources, multiple cameras, a pattern generator and one or more computers. The system measures depth in a scene. The multiple light sources emit light that illuminates a pattern generator. The pattern generator refracts, reflects or selectively attenuates the light, to create a textured light pattern that is projected onto the scene. The multiple cameras capture images of the scene from different viewpoints, while the scene is illuminated by the textured light. One or more computers process the images and compute the depth of points in the scene, by a computation that involves stereoscopic triangulation.
    Type: Application
    Filed: December 24, 2014
    Publication date: June 30, 2016
    Inventors: Rajeswari Kannan, Pranav Mishra, Ashish Rao, Vivek Boominathan, Ashok Veeraraghavan, Ramesh Raskar
  • Patent number: 9355456
    Abstract: A red-eye detection and correction method includes computing a first difference image based on a difference between red pixel intensity and green pixel intensity of a set of pixels. The set of pixels are associated with a first eye region of an image. The method further includes processing the first difference image for computing at least one gradient and at least one projection associated with the at least one gradient. Furthermore, the method includes determining at least one central point based on the at least one projection; and thereafter computing the first eye color defect region based on the at least one central point and a plurality of red pixels of the set of pixels. The method also includes mapping an eye color defect location information computed from a low resolution image to be applicable on the original high resolution image, thereby avoiding recomputation.
    Type: Grant
    Filed: May 17, 2011
    Date of Patent: May 31, 2016
    Assignee: Nokia Technologies Oy
    Inventors: Basavaraja S-V, Krishna Govindarao, Veldandi Muninder, Pranav Mishra
  • Publication number: 20160147826
    Abstract: An approach is provided for updating or validating information associated with potential points of interest using crowd sourcing methods. The validation/updating platform determines at least one query from at least one device for location information associated with at least one point of interest. Next, the validation/updating platform determines at least one next location visited by the at least one device. Then, the validation/updating platform causes, at least in part, an updating of the location information associated with the at least one point of interest based, at least in part, on the at least one next location.
    Type: Application
    Filed: June 25, 2014
    Publication date: May 26, 2016
    Inventor: Pranav MISHRA
  • Patent number: 9240839
    Abstract: An array of light emitters is arranged single-file along an emitting surface of a transmitting device and emits light in a z-direction normal to the emitting surface. The array of light emitters is aligned along a y-direction normal to the z-direction. A lens assembly is optically coupled to the array of light emitters. The lens assembly includes at least one cylindrical lens and at least one aspherical lens. The lens assembly emits the light in free-space along the z-direction and has a first focal length in the y-direction and a different, second focal length in an x-direction. An encoder is coupled to apply a data signal to the array of light emitters. The data signal causes the array of light emitters to illuminate in a pattern that switches at a rate corresponding to a rolling shutter of a receiving sensor array.
    Type: Grant
    Filed: January 7, 2014
    Date of Patent: January 19, 2016
    Assignee: NOKIA CORPORATION
    Inventors: Ramesh Raskar, Pranav Mishra, Rajeswari Kannan
  • Patent number: 9207843
    Abstract: An example approach is provided for presenting content in a user interface associated with social networking messages based on gaze tracking information. A content presentation platform determines a rendering of a user interface presenting one or more social networking messages. The content presentation platform further determines a selection of at least one of the one or more social networking messages based, at least in part, on gaze tracking information. The content presentation platform also causes, at least in part, a presentation of content at the user interface based, at least in part, on the selection.
    Type: Grant
    Filed: March 26, 2013
    Date of Patent: December 8, 2015
    Assignee: Nokia Technologies Oy
    Inventor: Pranav Mishra
  • Publication number: 20150319349
    Abstract: An apparatus including a substrate; a plurality of first image sensels supported by the substrate and arranged in rows and columns, wherein the substrate includes one or more apertures.
    Type: Application
    Filed: April 26, 2013
    Publication date: November 5, 2015
    Inventors: Pranav MISHRA, Gururaj PUTRAYA
  • Publication number: 20150308838
    Abstract: An approach is provided for validating potential points of interest using device and user characteristics. The validation platform processes and/or facilitates a processing of location information associated with at least one device to determine one or more potential points of interest visited by the at least one device. Next, the validation platform causes, at least in part, a tagging of the one or more potential points of interest with one or more characteristics of the at least one device, one or more users of the at least one device, or a combination thereof. Then, the validation platform causes, at least on part, a validation of the one or more potential points of interest based, at least in part, on the one or more characteristics as captured by at least one other device, one or more other users of the at least one other device, or a combination thereof.
    Type: Application
    Filed: December 3, 2013
    Publication date: October 29, 2015
    Inventor: Pranav Mishra
  • Publication number: 20150293597
    Abstract: A method including in response to a detected gesture user input, wherein the gesture user input is ambiguous as to which one of a plurality of putative targets the gesture user input is directed, disambiguating the plurality of putative targets using disambiguating data to enable selection of one of the plurality of targets; and performing, in response to the gesture user input, a user input command associated with the selected target.
    Type: Application
    Filed: November 2, 2012
    Publication date: October 15, 2015
    Inventors: Pranav Mishra, Rajeswari Kannan
  • Patent number: 9131159
    Abstract: A method and apparatus for optical field communication, wherein incident light is spread on the surface of an image sensor with a diffuser element; a conventional digital image is captured with high exposure pixel rows of the image sensor; and the light intensity on two successive low exposure pixel rows of the image sensor is recorded. The recorded light intensities of the two successive low exposure pixel rows are compared; and in response to comparing the recorded light intensities of the two successive low exposure pixel rows, a value of a bit received via optical field communication is determined.
    Type: Grant
    Filed: June 28, 2013
    Date of Patent: September 8, 2015
    Assignee: Nokia Technologies Oy
    Inventors: Ramesh Raskar, Rajeswari Kannan, Pranav Mishra
  • Patent number: 9082001
    Abstract: Method, apparatus, and computer program product are provided. The method includes detecting a face portion in a frame of a plurality of frames of a multi-media content. The method further includes tracking the face portion in at least one subsequent frame of the frame. A color-tracking of the face portion is performed on losing a track of the face portion in the at least one subsequent frame. The color-tracking is performed for re-tracking the face portion in the at least one subsequent frame.
    Type: Grant
    Filed: June 7, 2011
    Date of Patent: July 14, 2015
    Assignee: Nokia Technologies Oy
    Inventors: Veldandi Muninder, Pranav Mishra, Changyeon Jo, Krishna Govindarao