Home  |  Centre for Mathematical Sciences  |  LTH  |  LU

Wearable Visual Information Systems

A camera picture has traditionally been considered as a visual recording of a specific isolated moment in place and time and as a permanent link to that moment and its associated memories. However, the advent of digital technologies for capturing, storing and transmitting pictures has dramatically extended our perception of the role of photography. Indeed already the ubiquity and vastness of most people's personal photo collection has begun to stimulate the development of mostly manual tools for managing and searching large image repositories. In fact, the ease with which pictures are captured and stored today opens up many new possibilities for exploiting captured visual information for the purposes of content analysis, guiding, information access and memory enhancement. All these tasks require advanced tools of image analysis and computer vision in order to extract useful information (semi-)automatically from images. It is the purpose of this project to advance these tools and show their usefulness in a set of compelling demonstrators based on personal wearable image capturing devices.

Specific problems that we adress are for example:

  • Automatic tagging of images taken by hand held devices
  • Localization and way finding
  • Locating everyday objects
  • Visual diaries from continuously wearable cameras

Funded by the Swedish Foundation for Strategic Research .
Period: 2009-2013.
Partners: CVAP, KTH