US Patent Application 18030391. ESTIMATING BOUNDARIES OF AN OBJECT OF INTEREST (OOI) WITHIN A THREE-DIMENSIONAL MODEL OF AN AREA simplified abstract

From WikiPatents
Jump to navigation Jump to search

ESTIMATING BOUNDARIES OF AN OBJECT OF INTEREST (OOI) WITHIN A THREE-DIMENSIONAL MODEL OF AN AREA

Organization Name

Telefonaktiebolaget LM Ericsson (publ)

Inventor(s)

Erik Carlbaum Ekholm of Johanneshov (SE)

Volodya Grancharov of SOLNA (SE)

Manish Sonal of Sollentuna (SE)

ESTIMATING BOUNDARIES OF AN OBJECT OF INTEREST (OOI) WITHIN A THREE-DIMENSIONAL MODEL OF AN AREA - A simplified explanation of the abstract

This abstract first appeared for US patent application 18030391 titled 'ESTIMATING BOUNDARIES OF AN OBJECT OF INTEREST (OOI) WITHIN A THREE-DIMENSIONAL MODEL OF AN AREA

Simplified Explanation

The patent application describes a method for estimating boundaries of an Object of Interest (OOI) using point clouds and images.

  • Obtaining a set of N points and a set of K images.
  • Identifying the location of each point within a 2D space corresponding to each image.
  • Determining a motion metric for each point using the location identifiers.
  • Using the motion metrics to form a subset of points.
  • Obtaining location identifiers for each point in the subset.
  • Estimating the center of the OOI using the location identifiers.
  • Using the estimated center to identify boundaries for the OOI.


Original Abstract Submitted

A method () for estimating boundaries of an OOI. The method includes obtaining (s) a first point cloud comprising a set of N points. The method also includes obtaining (s) a set of K images. The method also includes, for each point included in the set of N points, identifying (s), for each one of the K images, the point's location within a 2D space corresponding to the image, thereby obtaining, for each point included in the set of N points, K location identifiers. The method also includes, for each point included in the set of N points, determining (s) a motion metric for the point using the K location identifiers for the point. The method also includes using (s) the N motion metrics to form a subset of the N points. The method also includes, for each point included in the subset of points, obtaining (s) a location identifier for the point. The method also includes using (s) the location identifiers to estimate a center of the OOI and then using (s) the estimated center of the OOI to identify boundaries for the OOI.