Patent · US Active

Learning image processing tasks from scene reconstructions

US8971612B2 · kind B2 · utility

25Cited by
173References
19Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 15, 2011
Grant dateMar 3, 2015
Priority date
Expiry dateJun 25, 2033

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/20081
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Learning image processing tasks from scene reconstructions is described where the tasks may include but are not limited to: image de-noising, image in-painting, optical flow detection, interest point detection. In various embodiments training data is generated from a 2 or higher dimensional reconstruction of a scene and from empirical images of the same scene. In an example a machine learning system learns at least one parameter of a function for performing the image processing task by using the training data. In an example, the machine learning system comprises a random decision forest. In an example, the scene reconstruction is obtained by moving an image capture apparatus in an environment where the image capture apparatus has an associated dense reconstruction and camera tracking system.

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