Patents by Inventor Joubin Nasehi Tehrani

Joubin Nasehi Tehrani 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).

  • Method to estimate real-time rotation and translation of a target with a single x-ray imager
    Patent number: 9314219
    Abstract: A method of real-time estimation of target rotation and translation for 6 degrees of freedom using a single planar 2-dimensional imager and an algorithm, such as the iterative closest point (ICP) algorithm, that includes creating pairing, using a nearest neighbor algorithm, between a set of target points of at least three fiducial markers and a set of source points of the markers using K nearest neighbors, iteratively executing estimation of a rotation parameter R and a translation parameter T of the markers using a cost function such as root mean square error, terminating the estimation of R and T if the change in a mean distance between the set of target points of the markers and the set of source points of the markers is below a threshold or at a maximum iteration number, transforming the set of target points of the markers using estimated parameters, and re-associating a new set of the target points of the markers.
    Type: Grant
    Filed: December 10, 2013
    Date of Patent: April 19, 2016
    Inventors: Paul J Keall, Joubin Nasehi Tehrani, Ricky O'Brien, Per Rugaard Poulsen
  • Method to estimate real-time rotation and translation of a target with a single x-ray imager
    Publication number: 20140241497
    Abstract: A method of real-time estimation of target rotation and translation for 6 degrees of freedom using a single planar 2-dimensional imager and an algorithm, such as the iterative closest point (ICP) algorithm, that includes creating pairing, using a nearest neighbor algorithm, between a set of target points of at least three fiducial markers and a set of source points of the markers using K nearest neighbors, iteratively executing estimation of a rotation parameter R and a translation parameter T of the markers using a cost function such as root mean square error, terminating the estimation of R and T if the change in a mean distance between the set of target points of the markers and the set of source points of the markers is below a threshold or at a maximum iteration number, transforming the set of target points of the markers using estimated parameters, and re-associating a new set of the target points of the markers.
    Type: Application
    Filed: December 10, 2013
    Publication date: August 28, 2014
    Inventors: Paul J. Keall, Joubin Nasehi Tehrani, Ricky O'Brien, Per Rugaard Poulsen