Patents by Inventor Fred Portigal

Fred Portigal 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: 7505608
    Abstract: Apparatus and methods for target detection in hyperspectral images are disclosed. In one embodiment, a method of detecting a target in a hyperspectral image includes spectrally unmixing the hyperspectral image into segments, each segment having at least one of similar spectral composition, similar textural composition, and similar variation, and spectrally unmixing at least one of the segments. The method further includes creating a clutter rejection filter for at least one segment, filtering at least one segment, and calculating target abundances in at least one segment. In alternate embodiments, channel reduction can be performed on the hyperspectral image and also on at least one segment. In further embodiments, data associated with the location of possible targets in the segments may be compiled. In yet another embodiment, this data may be compressed by cross referencing data from all segments and eliminating redundancies.
    Type: Grant
    Filed: April 15, 2005
    Date of Patent: March 17, 2009
    Assignee: The Boeing Company
    Inventors: Fred Portigal, Dennis Yelton
  • Patent number: 7450761
    Abstract: A system for the conversion, analysis and display of geographic imaging data is provided which allows for the efficient location of various targets based on user selectable search criteria. The system provides a means to convert large image database information to a more compact and efficient structure employing the use of a shape library and an associated shape index.
    Type: Grant
    Filed: November 2, 2004
    Date of Patent: November 11, 2008
    Assignee: The Boeing Company
    Inventors: Fred Portigal, Rastislav Telgarsky
  • Publication number: 20060233421
    Abstract: Apparatus and methods for target detection in hyperspectral images are disclosed. In one embodiment, a method of detecting a target in a hyperspectral image includes spectrally unmixing the hyperspectral image into segments, each segment having at least one of similar spectral composition, similar textural composition, and similar variation, and spectrally unmixing at least one of the segments. The method further includes creating a clutter rejection filter for at least one segment, filtering at least one segment, and calculating target abundances in at least one segment. In alternate embodiments, channel reduction can be performed on the hyperspectral image and also on at least one segment. In further embodiments, data associated with the location of possible targets in the segments may be compiled. In yet another embodiment, this data may be compressed by cross referencing data from all segments and eliminating redundancies.
    Type: Application
    Filed: April 15, 2005
    Publication date: October 19, 2006
    Applicant: The Boeing Company
    Inventors: Fred Portigal, Dennis Yelton
  • Publication number: 20060093223
    Abstract: A system for the conversion, analysis and display of geographic imaging data is provided which allows for the efficient location of various targets based on user selectable search criteria. The system provides a means to convert large image database information to a more compact and efficient structure employing the use of a shape library and an associated shape index.
    Type: Application
    Filed: November 2, 2004
    Publication date: May 4, 2006
    Applicant: The Boeing Company
    Inventors: Fred Portigal, Rastislav Telgarsky