Patents by Inventor Peyman Milanfar

Peyman Milanfar 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: 9400405
    Abstract: A method for aligning optical layers of a multi-layer display includes displaying a dark screen image on each of a plurality of transmissive pixel arrays separated from each other by spacing regions. The transmissive pixel arrays are disposed on a display layer of the multi-layer display. The display layer is illuminated with a plurality of illumination sources of an illumination layer disposed behind the display layer. Each of the illumination sources corresponds to one of the transmissive pixel arrays to illuminate the corresponding one of the transmissive pixel arrays. An illumination pattern is cast onto a screen layer disposed in front of the display layer. The illumination pattern includes bright regions due to overlapping illumination cast from adjacent ones of the transmissive pixel arrays. The bright regions of the illumination pattern cast onto the screen layer are analyzed to identify misalignments between the display layer and the illumination layer.
    Type: Grant
    Filed: April 16, 2014
    Date of Patent: July 26, 2016
    Assignee: Google Inc.
    Inventors: Behnam Bastani, Peyman Milanfar
  • Patent number: 9253375
    Abstract: The present disclosure provides example methods operable by computing device. An example method can include receiving an image from a camera. The method can also include comparing one or more parameters of the image with one or more control parameters, where the one or more control parameters comprise information indicative of an image from a substantially unobstructed camera. Based on the comparison, the method can also include determining a score between the one or more parameters of the image and the one or more control parameters. The method can also include accumulating, by a computing device, a count of a number of times the determined score image exceeds a first threshold. Based on the count exceeding a second threshold, the method can also include determining that the camera is at least partially obstructed.
    Type: Grant
    Filed: April 2, 2013
    Date of Patent: February 2, 2016
    Assignee: Google Inc.
    Inventors: Peyman Milanfar, Marc Stewart Levoy, Samuel William Hasinoff, Changyin Zhou
  • Patent number: 9223536
    Abstract: Techniques and mechanisms for determining misalignment of one or more tileable display panels. In an embodiment, a plurality of images are processed to create a super-resolution image of the one or more tileable display panels. The super-resolution image may be processed to recognize one or more features indicating misalignment in a reference image displayed by the one or more tileable display panels. In another embodiment, the one or more features are evaluated based on fiducial data to generate a signal indicating an adjustment to be made to a first tileable display panel.
    Type: Grant
    Filed: December 3, 2013
    Date of Patent: December 29, 2015
    Assignee: Google Inc.
    Inventors: Behnam Bastani, Peyman Milanfar, Mary Lou Jepsen
  • Publication number: 20150300812
    Abstract: A method for aligning optical layers of a multi-layer display includes displaying a dark screen image on each of a plurality of transmissive pixel arrays separated from each other by spacing regions. The transmissive pixel arrays are disposed on a display layer of the multi-layer display. The display layer is illuminated with a plurality of illumination sources of an illumination layer disposed behind the display layer. Each of the illumination sources corresponds to one of the transmissive pixel arrays to illuminate the corresponding one of the transmissive pixel arrays. An illumination pattern is cast onto a screen layer disposed in front of the display layer. The illumination pattern includes bright regions due to overlapping illumination cast from adjacent ones of the transmissive pixel arrays. The bright regions of the illumination pattern cast onto the screen layer are analyzed to identify misalignments between the display layer and the illumination layer.
    Type: Application
    Filed: April 16, 2014
    Publication date: October 22, 2015
    Applicant: Google Inc.
    Inventors: Behnam Bastani, Peyman Milanfar
  • Publication number: 20140105515
    Abstract: A method for image restoration and reconstruction registers each frame of an observed image sequence to suppress geometric deformation through B-spline based non-rigid registration, producing a registered sequence, then performs a temporal regression process on the registered sequence to produce a near-diffraction-limited image, and performs a single-image blind deconvolution of thenear-diffraction-limited image to deblur it, generating a final output image.
    Type: Application
    Filed: December 16, 2013
    Publication date: April 17, 2014
    Inventors: Xiang Zhu, Peyman Milanfar
  • Patent number: 8559671
    Abstract: The present invention provides a method of learning-free detection and localization of actions that includes providing a query video action of interest and providing a target video, obtaining at least one query space-time localized steering kernel (3-D LSK) from the query video action of interest and obtaining at least one target 3-D LSK from the target video, determining at least one query feature from the query 3-D LSK and determining at least one target patch feature from the target 3-D LSK, and outputting a resemblance map, where the resemblance map provides a likelihood of a similarity between each the query feature and each target patch feature to output learning-free detection and localization of actions, where the steps of the method are performed by using an appropriately programmed computer.
    Type: Grant
    Filed: December 16, 2009
    Date of Patent: October 15, 2013
    Assignee: The Regents of the University of California
    Inventors: Peyman Milanfar, Hae Jong Seo
  • Publication number: 20110311129
    Abstract: The present invention provides a method of learning-free detection and localization of actions that includes providing a query video action of interest and providing a target video, obtaining at least one query space-time localized steering kernel (3-D LSK) from the query video action of interest and obtaining at least one target 3-D LSK from the target video, determining at least one query feature from the query 3-D LSK and determining at least one target patch feature from the target 3-D LSK, and outputting a resemblance map, where the resemblance map provides a likelihood of a similarity between each the query feature and each target patch feature to output learning-free detection and localization of actions, where the steps of the method are performed by using an appropriately programmed computer.
    Type: Application
    Filed: December 16, 2009
    Publication date: December 22, 2011
    Inventors: Peyman Milanfar, Hae Jong Seo
  • Patent number: 7940282
    Abstract: A method of creating a super-resolved color image from multiple lower-resolution color images is provided by combining a data fidelity penalty term, a spatial luminance penalty term, a spatial chrominance penalty term, and an inter-color dependencies penalty term to create an overall cost function. The data fidelity penalty term is an L1 norm penalty term to enforce similarities between raw data and a high-resolution image estimate, the spatial luminance penalty term is to encourage sharp edges in a luminance component to the high-resolution image, the spatial chrominance penalty term is to encourage smoothness in a chrominance component of the high-resolution image, and the inter-color dependencies penalty term is to encourage homogeneity of an edge location and orientation in different color bands. A steepest descent optimization is applied to the overall cost function for minimization by applying a derivative to each color band while the other color bands constant.
    Type: Grant
    Filed: August 17, 2006
    Date of Patent: May 10, 2011
    Assignee: The Regents of the University of California, Santa Cruz
    Inventors: Peyman Milanfar, Sina Farsiu, Michael Elad
  • Patent number: 7889950
    Abstract: A method of image processing using kernel regression is provided. An image gradient is estimated from original data that is analyzed for local structures by computing a scaling parameter, a rotation parameter and an elongation parameter using singular value decomposition on local gradients of the estimated gradients locally to provide steering matrices. A steering kernel regression having steering matrices is applied to the original data to provide a reconstructed image and new image gradients. The new gradients are analyzed using singular value decomposition to provide new steering matrices. The steering kernel regression with the new steering matrices is applied to the noisy data to provide a new reconstructed image and further new gradients. The last two steps are repeated up to ten iterations to denoise the original noisy data and improve the local image structure.
    Type: Grant
    Filed: August 30, 2006
    Date of Patent: February 15, 2011
    Assignee: The Regents of the University of California, Santa Cruz
    Inventors: Peyman Milanfar, Hiroyuki Takeda, Sina Farslu
  • Patent number: 7627841
    Abstract: The temperature distribution associated with a design of an integrated circuit is calculated by convoluting a surface power usage represented by a power matrix with a heat spreading function. The heat spreading function may be calculated from a simulation of a point source on the integrated circuit using a finite element analysis model of the integrated circuit or other techniques. To account for spatial variations on the chip, the heat spreading function may be made dependent on position using a position scaling function. Steady-state or transient temperature distributions may be computed by using a steady-state or transient heat spreading function. A single heat spreading function may be convolved with various alternative power maps to efficiently calculate temperature distributions for different designs. In an inverse problem, one can calculate the power map from an empirically measured temperature distribution and a heat spreading function using various de-convolution techniques.
    Type: Grant
    Filed: April 12, 2007
    Date of Patent: December 1, 2009
    Assignee: The Regents of the University of California, Santa Cruz
    Inventors: Ali Shakouri, Travis Kemper, Yan Zhang, Peyman Milanfar, Virginia Martin Hériz, Xi Wang
  • Patent number: 7477802
    Abstract: A computer method of creating a super-resolved grayscale image from lower-resolution images using an L1 norm data fidelity penalty term to enforce similarities between low and a high-resolution image estimates is provided. A spatial penalty term encourages sharp edges in the high-resolution image, the data fidelity penalty term is applied to space invariant point spread function, translational, affine, projective and dense motion models including fusing the lower-resolution images, to estimate a blurred higher-resolution image and then a deblurred image. The data fidelity penalty term uses the L1 norm in a likelihood fidelity term for motion estimation errors. The spatial penalty term uses bilateral-TV regularization with an image having horizontal and vertical pixel-shift terms, and a scalar weight between 0 and 1. The penalty terms create an overall cost function having steepest descent optimization applied for minimization. Direct image operator effects replace matrices for speed and efficiency.
    Type: Grant
    Filed: November 16, 2006
    Date of Patent: January 13, 2009
    Assignee: The Regents of the University of California, Santa Cruz
    Inventors: Peyman Milanfar, Sina Farsiu, Michael Elad, Michael D. Robinson
  • Patent number: 7412107
    Abstract: An integrated method for both super-resolution and multi-frame demosaicing includes an image fusion followed by simultaneous deblurring and interpolation. For the case of color super-resolution, the first step involves application of recursive image fusion separately on the three different color layers. The second step is based on minimizing a maximum a posteriori (MAP) cost function. In one embodiment, the MAP cost function is composed of several terms: a data fidelity penalty term that penalizes dissimilarity between the raw data and the super-resolved estimate, a luminance penalty term that favors sharp edges in the luminance component of the image, a chrominance penalty term that favors low spatial frequency changes in the chrominance component of the image, and an orientation penalty term that favors similar edge orientations across the color channels. The method is also applicable to color super-resolution (without demosaicing), where the low-quality input images are already demosaiced.
    Type: Grant
    Filed: December 12, 2005
    Date of Patent: August 12, 2008
    Assignee: The Regents of the University of California, Santa Cruz
    Inventors: Peyman Milanfar, Sina Farsiu, Michael Elad
  • Patent number: 7379612
    Abstract: A method is provided of solving the dynamic super-resolution (SR) problem of reconstructing a high-quality set of monochromatic or color superresolved images from low-quality monochromatic, color, or mosaiced frames. The invention includes a joint method for simultaneous SR, deblurring, and demosaicing, this way taking into account practical color measurements encountered in video sequences. For the case of translational motion and common space-invariant blur, the proposed invention is based on a very fast and memory efficient approximation of the Kalman filter (KF). Experimental results on both simulated and real data are supplied, demonstrating the invention algorithms, and their strength.
    Type: Grant
    Filed: October 19, 2006
    Date of Patent: May 27, 2008
    Assignee: The Regents of the University of California, Santa Cruz
    Inventors: Peyman Milanfar, Sina Farsiu, Michael Elad
  • Publication number: 20080026493
    Abstract: The temperature distribution associated with a design of an integrated circuit is calculated by convoluting a surface power usage represented by a power matrix with a heat spreading function. The heat spreading function may be calculated from a simulation of a point source on the integrated circuit using a finite element analysis model of the integrated circuit or other techniques. To account for spatial variations on the chip, the heat spreading function may be made dependent on position using a position scaling function. Steady-state or transient temperature distributions may be computed by using a steady-state or transient heat spreading function. A single heat spreading function may be convolved with various alternative power maps to efficiently calculate temperature distributions for different designs. In an inverse problem, one can calculate the power map from an empirically measured temperature distribution and a heat spreading function using various de-convolution techniques.
    Type: Application
    Filed: April 12, 2007
    Publication date: January 31, 2008
    Inventors: Ali Shakouri, Travis Kemper, Yan Zhang, Peyman Milanfar, Virginia Martin Heriz, Xi Wang
  • Publication number: 20070217713
    Abstract: A computer method of creating a super-resolved grayscale image from lower-resolution images using an L1 norm data fidelity penalty term to enforce similarities between low and a high-resolution image estimates is provided. A spatial penalty term encourages sharp edges in the high-resolution image, the data fidelity penalty term is applied to space invariant point spread function, translational, affine, projective and dense motion models including fusing the lower-resolution images, to estimate a blurred higher-resolution image and then a deblurred image. The data fidelity penalty term uses the L1 norm in a likelihood fidelity term for motion estimation errors. The spatial penalty term uses bilateral-TV regularization with an image having horizontal and vertical pixel-shift terms, and a scalar weight between 0 and 1. The penalty terms create an overall cost function having steepest descent optimization applied for minimization. Direct image operator effects replace matrices for speed and efficiency.
    Type: Application
    Filed: November 16, 2006
    Publication date: September 20, 2007
    Inventors: Peyman Milanfar, Sina Farsiu, Michael Elad, Michael Robinson
  • Publication number: 20070071362
    Abstract: A method is provided of solving the dynamic super-resolution (SR) problem of reconstructing a high-quality set of monochromatic or color superresolved images from low-quality monochromatic, color, or mosaiced frames. The invention includes a joint method for simultaneous SR, deblurring, and demosaicing, this way taking into account practical color measurements encountered in video sequences. For the case of translational motion and common space-invariant blur, the proposed invention is based on a very fast and memory efficient approximation of the Kalman filter (KF). Experimental results on both simulated and real data are supplied, demonstrating the invention algorithms, and their strength.
    Type: Application
    Filed: October 19, 2006
    Publication date: March 29, 2007
    Inventors: Peyman Milanfar, Sina Farsiu, Michael Elad
  • Publication number: 20070047838
    Abstract: A method of image processing using kernel regression is provided. An image gradient is estimated from original data that is analyzed for local structures by computing a scaling parameter, a rotation parameter and an elongation parameter using singular value decomposition on local gradients of the estimated gradients locally to provide steering matrices. A steering kernel regression having steering matrices is applied to the original data to provide a reconstructed image and new image gradients. The new gradients are analyzed using singular value decomposition to provide new steering matrices. The steering kernel regression with the new steering matrices is applied to the noisy data to provide a new reconstructed image and further new gradients. The last two steps are repeated up to ten iterations to denoise the original noisy data and improve the local image structure.
    Type: Application
    Filed: August 30, 2006
    Publication date: March 1, 2007
    Inventors: Peyman Milanfar, Hiroyuki Takeda, Sina Farsiu
  • Patent number: 7173245
    Abstract: Methods and apparatus for non-contact thermal measurement which are capable of providing sub micron surface thermal characterization of samples, such as active semiconductor devices. The method obtains thermal image information by reflecting a light from a surface of a device in synchronous with the modulation of the thermal excitation and then acquiring and processing an AC-coupled thermoreflective image. The method may be utilized for making measurements using different positioning techniques, such as point measurements, surface scanning, two-dimensional imaging, and combinations thereof. A superresolution method is also described for increasing the resultant image resolution, based on multiple images with fractional pixel offsets, without the need to increase the resolution of the image detectors being utilized.
    Type: Grant
    Filed: January 4, 2002
    Date of Patent: February 6, 2007
    Assignee: The Regents of the University of California
    Inventors: Ali Shakouri, Peyman Milanfar, Kenneth Pedrotti, James Christofferson
  • Publication number: 20060291750
    Abstract: In one aspect, the present invention provides a dynamic super-resolution technique that is computationally efficient. A recursive computation takes as input a previously computed super-resolved image derived from a sequence of low-resolution input frames. Combining this super-resolved image with a later low-resolution input frame in the sequence, the technique produces a new super-resolved image. By recursive application, a sequence of super-resolved images is produced. In a preferred embodiment, the technique uses a computationally simple and effective method based on adaptive filtering for computing a high resolution image and updating this high resolution image over time to produce an enhanced sequence of images. The method may be implemented as a general super-resolution software tool capable of handing a wide variety of input image data.
    Type: Application
    Filed: December 12, 2005
    Publication date: December 28, 2006
    Inventors: Peyman Milanfar, Sina Farsiu, Michael Elad
  • Publication number: 20060290711
    Abstract: An integrated method for both super-resolution and multi-frame demosaicing includes an image fusion followed by simultaneous deblurring and interpolation. For the case of color super-resolution, the first step involves application of recursive image fusion separately on the three different color layers. The second step is based on minimizing a maximum a posteriori (MAP) cost function. In one embodiment, the MAP cost function is composed of several terms: a data fidelity penalty term that penalizes dissimilarity between the raw data and the super-resolved estimate, a luminance penalty term that favors sharp edges in the luminance component of the image, a chrominance penalty term that favors low spatial frequency changes in the chrominance component of the image, and an orientation penalty term that favors similar edge orientations across the color channels. The method is also applicable to color super-resolution (without demosaicing), where the low-quality input images are already demosaiced.
    Type: Application
    Filed: December 12, 2005
    Publication date: December 28, 2006
    Inventors: Peyman Milanfar, Sina Farsiu, Michael Elad