Patent · US Active

Method for object segmentation in videos tagged with semantic labels

US9740956B2 · kind B2 · utility

11Cited by
8References
8Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 29, 2016
Grant dateAug 22, 2017
Priority date
Expiry dateMar 29, 2036

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V2201/07
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The present invention provides a method for object segmentation in videos tagged with semantic labels, including: detecting each frame of a video sequence with an object bounding box detector from a given semantic category and an object contour detector, and obtaining a candidate object bounding box set and a candidate object contour set for each frame of the input video; building a joint assignment model for the candidate object bounding box set and the candidate object contour set and solving the model to obtain the initial object segment sequence; processing the initial object segment, to estimate a probability distribution of the object shapes; and optimizing the initial object segment sequence with a variant of graph cut algorithm that integrates the shape probability distribution, to obtain an optimal segment sequence.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.