Patents by Inventor Pascal Fua

Pascal Fua 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 AND APPARATUS FOR MULTIPLE OBJECT TRACKING WITH K-SHORTEST PATHS
    Publication number: 20130177200
    Abstract: Trajectories of objects are estimated by determining the optimal solution(s) of a tracking model on the basis of an occupancy probability distribution. The occupancy probability distribution is the probability of presence of objects over a set of discrete points in the spatio-temporal space at a number of time steps. The tracking model is defined by the set of discrete points, a virtual source location and a virtual sink location, wherein objects in the tracking model are creatable in the virtual source location and are removable in the virtual sink location.
    Type: Application
    Filed: January 11, 2012
    Publication date: July 11, 2013
    Inventors: Françoi FLEURET, Jérôme Berclaz, Engin Türetken, Pascal Fua
  • Method and system for estimating the accuracy of inference algorithms using the self-consistency methodology
    Patent number: 6834120
    Abstract: The present invention provides a method for measuring the self-consistency of inference algorithms. The present invention provides a method for measuring the accuracy of an inference algorithm that does not require comparison to ground truth. Rather, the present invention pertains to a method for measuring the accuracy of an inference algorithm by comparing the outputs of the inference algorithm against each other. Essentially, the present invention looks at how well the algorithm applied to many of the different observations gives the same answer. In particular, the present invention provides a method that is not time and labor intensive and is cost effective.
    Type: Grant
    Filed: November 15, 2000
    Date of Patent: December 21, 2004
    Assignee: SRI International
    Inventors: Yvan G. LeClerc, Quang-Tuan Luong, Pascal Fua
  • Method and system for estimating the accuracy of inference algorithms using the self-consistency methodology
    Patent number: RE42999
    Abstract: The present invention provides a method for measuring the self-consistency of inference algorithms. The present invention provides a method for measuring the accuracy of an inference algorithm that does not require comparison to ground truth. Rather, the present invention pertains to a method for measuring the accuracy of an inference algorithm by comparing the outputs of the inference algorithm against each other. Essentially, the present invention looks at how well the algorithm applied to many of the different observations gives the same answer. In particular, the present invention provides a method that is not time and labor intensive and is cost effective.
    Type: Grant
    Filed: December 21, 2006
    Date of Patent: December 6, 2011
    Assignee: Transpacific Kodex, LLC
    Inventors: Yvan G. LeClerc, Margaret Frances Davies, legal representative, Quang-Tuan Luong, Pascal Fua