Paris: A MPEG-7 geo-referenced personal photograph database

Pei Jeng Kuo, Terumasa Aoki, Hiroshi Yasuda

Research output: Contribution to conferencePaperpeer-review

Abstract

Geo-referenced digital photographs stamped with location information such as GPS data have become possible with the aid of GPS receiving devices and increasingly sophisticated digital cameras. In previous publications, we have proposed a MPEG-7 based annotation architecture, Dozen Dimensional Digital Content (DDDC), specially designed for facilitating the managing, browsing and retrieving of personal digital photograph collections. While our proposed DDDC annotation architecture supports spatial and temporal attributes, constructing a geo-referenced digital photograph library is still time-consuming and cumbersome. In this paper, we explain the concept and structure of our MPEG-7 based georeferenced digital photograph library prototype system, named PARIS (Personal Archiving and Retrieving Image System). In addition to utilizing the temporal information recorded directly from image devices, our approach integrates spatial coordinates to realize novel retrieving methodology with georeferenced photograph collections.

Original languageEnglish
Pages255-259
Number of pages5
Publication statusPublished - 2005
Event11th Annual Scientific Conference on Web Technology, New Media Communications and Telematics Theory Methods, Tools and Applications, EUROMEDIA 2005 - Toulouse, France
Duration: 2005 Apr 112005 Apr 13

Other

Other11th Annual Scientific Conference on Web Technology, New Media Communications and Telematics Theory Methods, Tools and Applications, EUROMEDIA 2005
CountryFrance
CityToulouse
Period05/4/1105/4/13

Keywords

  • Digital image database
  • Image retrieval
  • MPEG-7
  • Metadata
  • Ontology
  • Semantic Web
  • Semi-automatic annotation
  • Spatial-temporal

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Paris: A MPEG-7 geo-referenced personal photograph database'. Together they form a unique fingerprint.

Cite this