Patents by Inventor Eliran Dror

Eliran Dror 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).

  • Publication number: 20230325296
    Abstract: The presently disclosed subject matter aims to a system and method for generating one or more aggregation rules configured to be utilized by a log collector. The system and method involve an aggregation rules generator directed to allow a log collector to handle the aggregation of gathered log information, even for event logs with previously unobserved behavior patterns.
    Type: Application
    Filed: January 11, 2023
    Publication date: October 12, 2023
    Inventors: Eliran DROR, Odelia CERF
  • Patent number: 10610130
    Abstract: A system, method, and computer readable medium for measuring limb range of motion. The method includes initializing a scanning area. A classifier trained to recognize limbs is loaded into memory. A frame representing a 3D point cloud having at least one limb of a person in motion is captured. A box fitting algorithm is performed on the captured at least one limb to enable the classifier to identify the at least one limb. One or more boxes generated from the box fitting algorithm are sliced into a plurality of 2D point clouds to measure and record the circumference of each 2D point cloud to obtain limb range of motion parameters. The limb range of motion parameters are a maximum and a minimum size of the at least one limb as a function of soft tissue expansion and contraction of the limb while under pressure, force, and/or motion.
    Type: Grant
    Filed: June 29, 2018
    Date of Patent: April 7, 2020
    Assignee: Intel Corporation
    Inventors: Maximillian Domeika, Eliran Dror, Ned Smith
  • Publication number: 20190038181
    Abstract: A system, method, and computer readable medium for measuring limb range of motion. The method includes initializing a scanning area. A classifier trained to recognize limbs is loaded into memory. A frame representing a 3D point cloud having at least one limb of a person in motion is captured. A box fitting algorithm is performed on the captured at least one limb to enable the classifier to identify the at least one limb. One or more boxes generated from the box fitting algorithm are sliced into a plurality of 2D point clouds to measure and record the circumference of each 2D point cloud to obtain limb range of motion parameters. The limb range of motion parameters are a maximum and a minimum size of the at least one limb as a function of soft tissue expansion and contraction of the limb while under pressure, force, and/or motion.
    Type: Application
    Filed: June 29, 2018
    Publication date: February 7, 2019
    Applicant: Intel Corporation
    Inventors: Maximillian Domeika, Eliran Dror, Ned Smith