Patent · US Active

Unsupervised video segmentation

US10402986B2 · kind B2 · utility

35Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 20, 2017
Grant dateSep 3, 2019
Priority date
Expiry dateMar 7, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/20084
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

In one embodiment, a method includes a computing system accessing a first training data comprising a first image and a second image and an associated optical flow estimation. The system may input (1) the first image into a first machine-learning model configured to generate a first output and (2) the optical flow estimation into a second machine-learning model configured to generate a second output. The first output of the first machine-learning model is associated with first image segments of a predetermined number, and the second output of the second machine-learning model is associated with transformations of the predetermined number. The first output, the transformations, and the first image are configured to generate an estimated image. The system trains the first machine-learning model and the second machine-learning model based on at least a comparison of the estimated image and the second image.

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