Patents by Inventor Kostas Stamatiou

Kostas Stamatiou 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).

  • Anomaly detection using non-target clustering
    Patent number: 10679055
    Abstract: A system and methods for radiometric anomaly detection using non-target clustering, wherein a hierarchy generator organizes the image information content into a hierarchical data representation structure, and a non-target clustering engine processes the hierarchical model to identify large homogeneous regions and significantly dissimilar smaller regions within them based on search criteria.
    Type: Grant
    Filed: November 3, 2017
    Date of Patent: June 9, 2020
    Assignee: DIGITALGLOBE, INC.
    Inventors: Georgios Ouzounis, Kostas Stamatiou
  • Muddy water detection using normalized semantic layers
    Patent number: 10515272
    Abstract: A system and methods for muddy water detection using normalized semantic layers, wherein a spectrum analyzer isolates spectrum bands within an image to produce a set of three normalized differential index images from which a composite color image is created, from which a power band is computed, from which a two-color image is produced, and then filters image components within the two-color representation based on defined criteria.
    Type: Grant
    Filed: September 1, 2017
    Date of Patent: December 24, 2019
    Assignee: DigitalGlobe, Inc.
    Inventors: Georgios Ouzounis, Kostas Stamatiou
  • Shape-based segmentation using hierarchical image representations for automatic training data generation and search space specification for machine learning algorithms
    Patent number: 10372984
    Abstract: A system and various methods for processing an image to produce a hierarchical image representation model, segment the image model using shape criteria to produce positive and negative training data sets as well as a search-space data set comprising shapes matched to a search query provided as input, and using the training data sets to train a machine learning model to improve recognition of shapes that are similar to an input query without being exact matches, to improve object recognition.
    Type: Grant
    Filed: November 2, 2017
    Date of Patent: August 6, 2019
    Assignee: DigitalGlobe, Inc.
    Inventors: Georgios Ouzounis, Kostas Stamatiou, Nikki Aldeborgh
  • ANOMALY DETECTION USING NON-TARGET CLUSTERING
    Publication number: 20180330190
    Abstract: A system and methods for radiometric anomaly detection using non-target clustering, wherein a hierarchy generator organizes the image information content into a hierarchical data representation structure, and a non-target clustering engine processes the hierarchical model to identify large homogeneous regions and significantly dissimilar smaller regions within them based on search criteria.
    Type: Application
    Filed: November 3, 2017
    Publication date: November 15, 2018
    Inventors: Georgios Ouzounis, Kostas Stamatiou
  • MUDDY WATER DETECTION USING NORMALIZED SEMANTIC LAYERS
    Publication number: 20180330488
    Abstract: A system and methods for muddy water detection using normalized semantic layers, wherein a spectrum analyzer isolates spectrum bands within an image to produce a set of three normalized differential index images from which a composite color image is created, from which a power band is computed, from which a two-color image is produced, and then filters image components within the two-color representation based on defined criteria.
    Type: Application
    Filed: September 1, 2017
    Publication date: November 15, 2018
    Inventors: Georgios Ouzounis, Kostas Stamatiou
  • SHAPE-BASED SEGMENTATION USING HIERARCHICAL IMAGE REPRESENTATIONS FOR AUTOMATIC TRAINING DATA GENERATION AND SEARCH SPACE SPECIFICATION FOR MACHINE LEARNING ALGORITHMS
    Publication number: 20180330187
    Abstract: A system and various methods for processing an image to produce a hierarchical image representation model, segment the image model using shape criteria to produce positive and negative training data sets as well as a search-space data set comprising shapes matched to a search query provided as input, and using the training data sets to train a machine learning model to improve recognition of shapes that are similar to an input query without being exact matches, to improve object recognition.
    Type: Application
    Filed: November 2, 2017
    Publication date: November 15, 2018
    Inventors: Georgios Ouzounis, Kostas Stamatiou, Nikki Aldeborgh