Immersion into Visual Media: New Applications of Image Understanding

  • Authors:
  • Takeo Kanade

  • Affiliations:
  • -

  • Venue:
  • IEEE Expert: Intelligent Systems and Their Applications
  • Year:
  • 1996

Quantified Score

Hi-index 0.00

Visualization

Abstract

Using images to interface machines and humans offers an exciting new application domain for image understanding. This article describes two such applications: digital libraries that bring visual data to the user, and virtualized reality that brings users to the visual data.Image understanding has traditionally been applied to recognition problems, such as those that arise in military, factory, and autonomous vehicle applications. Recently, IU technologies are finding a place in the use of images to interface people and machines. Such applications entail greater interaction between the user and the visual data--individuals can immerse themselves in the pool of visual information, systematically navigate through the data, and extract the necessary material or experience the desired sensation. We've developed two such applications: a digital library that brings visual data to the user, and virtualized reality that brings users to the visual data. The digital library calls on IU techniques such as scene segmentation and content analysis, and joins together natural language analysis and IU. Virtualized reality uses precise, dense, and video-rate stereo reconstruction techniques.