Patents by Inventor Mushfiqur Rouf

Mushfiqur Rouf 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: 20210303877
    Abstract: Examples disclosed herein may involve a computing system that is configured to (i) obtain previously-derived perception data for a collection of sensor data including a sequence of frames observed by a vehicle within one or more scenes, where the previously-derived perception data includes a respective set of object-level information for each of a plurality of objects detected within the sequence of frames, (ii) derive supplemental object-level information for at least one object detected within the sequence of frames that adds to the previously-derived object-level information for the at least one object, (iii) augment the previously-derived perception data to include the supplemental object-level information for the at least one object, and (iv) store the augmented perception data in an arrangement that encodes a hierarchical relationship between the plurality of objects, the sequence of frames, and the one or more scenes.
    Type: Application
    Filed: August 3, 2020
    Publication date: September 30, 2021
    Inventors: Ashesh Jain, Yunjian Jiang, Mushfiqur Rouf, Henru Wang, Lei Zhang
  • Patent number: 10733463
    Abstract: Examples disclosed herein may involve a computing system that is configured to (i) obtain previously-derived perception data for a collection of sensor data including a sequence of frames observed by a vehicle within one or more scenes, where the previously-derived perception data includes a respective set of object-level information for each of a plurality of objects detected within the sequence of frames, (ii) derive supplemental object-level information for at least one object detected within the sequence of frames that adds to the previously-derived object-level information for the at least one object, (iii) augment the previously-derived perception data to include the supplemental object-level information for the at least one object, and (iv) store the augmented perception data in an arrangement that encodes a hierarchical relationship between the plurality of objects, the sequence of frames, and the one or more scenes.
    Type: Grant
    Filed: March 31, 2020
    Date of Patent: August 4, 2020
    Assignee: Lyft, Inc.
    Inventors: Ashesh Jain, Yunjian Jiang, Mushfiqur Rouf, Henru Wang, Lei Zhang
  • Patent number: 10705193
    Abstract: Methods, systems, and devices are provided for calibrating a light ranging system and using the system to track environmental objects. In embodiments, the approach involves installing light ranging devices, such as lidar devices, on the vehicle exterior. The light ranging system may be calibrated using a calibration device to scan the vehicle exterior and construct a three-dimensional model of the vehicle exterior comprising the positions of the installed light ranging devices on the vehicle exterior. The calibrated light ranging system may use the model in conjunction with ranging data collected by the installed light ranging devices to track objects in the environment. In this way, the light ranging system may detect a proximity of environmental objects and help a driver of the vehicle avoid potential collisions. The light ranging system may further measure the vehicle exterior and thereby detect changes to the vehicle exterior.
    Type: Grant
    Filed: December 7, 2018
    Date of Patent: July 7, 2020
    Assignee: Ouster, Inc.
    Inventors: Angus Pacala, Dmitri Garbuzov, Daniel Lu, Wil Selby, Mushfiqur Rouf, Henru Wang, Kairen Wong
  • Publication number: 20190179029
    Abstract: Methods, systems, and devices are provided for calibrating a light ranging system and using the system to track environmental objects. In embodiments, the approach involves installing light ranging devices, such as lidar devices, on the vehicle exterior. The light ranging system may be calibrated using a calibration device to scan the vehicle exterior and construct a three-dimensional model of the vehicle exterior comprising the positions of the installed light ranging devices on the vehicle exterior. The calibrated light ranging system may use the model in conjunction with ranging data collected by the installed light ranging devices to track objects in the environment. In this way, the light ranging system may detect a proximity of environmental objects and help a driver of the vehicle avoid potential collisions. The light ranging system may further measure the vehicle exterior and thereby detect changes to the vehicle exterior.
    Type: Application
    Filed: December 7, 2018
    Publication date: June 13, 2019
    Inventors: Angus Pacala, Dmitri Garbuzov, Daniel Lu, Wil Selby, Mushfiqur Rouf, Henru Wang, Kairen Wong
  • Patent number: 9905196
    Abstract: A computer implemented method of determining a latent image from an observed image is disclosed. The method comprises implementing a plurality of image processing operations within a single optimization framework, wherein the single optimization framework comprises solving a linear minimization expression. The method further comprises mapping the linear minimization expression onto at least one non-linear solver. Further, the method comprises using the non-linear solver, iteratively solving the linear minimization expression in order to extract the latent image from the observed image, wherein the linear minimization expression comprises: a data term, and a regularization term, and wherein the regularization term comprises a plurality of non-linear image priors.
    Type: Grant
    Filed: September 26, 2016
    Date of Patent: February 27, 2018
    Assignee: NVIDIA CORPORATION
    Inventors: Dawid Stanislaw Pajak, Felix Heide, Nagilla Dikpal Reddy, Mushfiqur Rouf, Jan Kautz, Kari Pulli, Orazio Gallo
  • Patent number: 9558712
    Abstract: A computer implemented method of determining a latent image from an observed image is disclosed. The method comprises implementing a plurality of image processing operations within a single optimization framework, wherein the single optimization framework comprises solving a linear minimization expression. The method further comprises mapping the linear minimization expression onto at least one non-linear solver. Further, the method comprises using the non-linear solver, iteratively solving the linear minimization expression in order to extract the latent image from the observed image, wherein the linear minimization expression comprises: a data term, and a regularization term, and wherein the regularization term comprises a plurality of non-linear image priors.
    Type: Grant
    Filed: January 20, 2015
    Date of Patent: January 31, 2017
    Assignee: NVIDIA CORPORATION
    Inventors: Dawid Stanislaw Pajak, Felix Heide, Nagilla Dikpal Reddy, Mushfiqur Rouf, Jan Kautz, Kari Pulli, Orazio Gallo
  • Publication number: 20170011710
    Abstract: A computer implemented method of determining a latent image from an observed image is disclosed. The method comprises implementing a plurality of image processing operations within a single optimization framework, wherein the single optimization framework comprises solving a linear minimization expression. The method further comprises mapping the linear minimization expression onto at least one non-linear solver. Further, the method comprises using the non-linear solver, iteratively solving the linear minimization expression in order to extract the latent image from the observed image, wherein the linear minimization expression comprises: a data term, and a regularization term, and wherein the regularization term comprises a plurality of non-linear image priors.
    Type: Application
    Filed: September 26, 2016
    Publication date: January 12, 2017
    Inventors: Dawid Stanislaw Pajak, Felix Heide, Nagilla Dikpal Reddy, Mushfiqur Rouf, Jan Kautz, Kari Pulli, Orazio Gallo
  • Patent number: 9307208
    Abstract: There is provided a computer-implemented method for solving inverse imaging problems to compensate for distortions in an image. The method comprises: minimizing a cost objective function containing a data fitting term and one or more image prior terms to each of the plurality of channels, the one or more image prior terms comprising cross-channel information for a plurality of channels derived from the image.
    Type: Grant
    Filed: March 7, 2014
    Date of Patent: April 5, 2016
    Assignee: THE UNIVERSITY OF BRITISH COLUMBIA
    Inventors: Wolfgang Heidrich, Felix Heide, Mushfiqur Rouf, Matthias Hullin
  • Publication number: 20150254810
    Abstract: There is provided a computer-implemented method for solving inverse imaging problems to compensate for distortions in an image. The method comprises: minimizing a cost objective function containing a data fitting term and one or more image prior terms to each of the plurality of channels, the one or more image prior terms comprising cross-channel information for a plurality of channels derived from the image.
    Type: Application
    Filed: March 7, 2014
    Publication date: September 10, 2015
    Applicant: The University of British Columbia
    Inventors: Wolfgang Heidrich, Felix Heide, Mushfiqur Rouf, Matthias Hullin
  • Publication number: 20150206504
    Abstract: A computer implemented method of determining a latent image from an observed image is disclosed. The method comprises implementing a plurality of image processing operations within a single optimization framework, wherein the single optimization framework comprises solving a linear minimization expression. The method further comprises mapping the linear minimization expression onto at least one non-linear solver. Further, the method comprises using the non-linear solver, iteratively solving the linear minimization expression in order to extract the latent image from the observed image, wherein the linear minimization expression comprises: a data term, and a regularization term, and wherein the regularization term comprises a plurality of non-linear image priors.
    Type: Application
    Filed: January 20, 2015
    Publication date: July 23, 2015
    Inventors: Dawid Stanislaw Pajak, Felix Heide, Nagilla Dikpal Reddy, Mushfiqur Rouf, Jan Kautz, Kari Pulli, Orazio Gallo
  • Patent number: 8861851
    Abstract: Methods and apparatus may be applied to reconstruct pixel values in saturated regions of an image. Saturated regions are identified and hues for pixels in the saturated regions are estimated based on hues in boundaries of the saturated regions. Gradients for pixel values in saturated color channels within the saturated region may be estimated based on known gradients for non-saturated color channels. Reconstructed pixel values may be derived from the estimated gradients. The methods and apparatus may be applied in conjunction with dynamic range expansion.
    Type: Grant
    Filed: May 3, 2012
    Date of Patent: October 14, 2014
    Assignee: Dolby Laboratories Licensing Corporation
    Inventors: Wolfgang Heidrich, Mushfiqur Rouf
  • Publication number: 20120288192
    Abstract: Methods and apparatus may be applied to reconstruct pixel values in saturated regions of an image. Saturated regions are identified and hues for pixels in the saturated regions are estimated based on hues in boundaries of the saturated regions. Gradients for pixel values in saturated color channels within the saturated region may be estimated based on known gradients for non-saturated color channels. Reconstructed pixel values may be derived from the estimated gradients. The methods and apparatus may be applied in conjunction with dynamic range expansion.
    Type: Application
    Filed: May 3, 2012
    Publication date: November 15, 2012
    Inventors: Wolfgang Heidrich, Mushfiqur Rouf