Automatic annotation of sport video content

  • Authors:

  • Marco Bertini;Alberto Del Bimbo;Walter Nunziati

  • Affiliations:

  • Dipartimento di Sistemi e Informatica, Universitá degli Studi di Firenze;Dipartimento di Sistemi e Informatica, Universitá degli Studi di Firenze;Dipartimento di Sistemi e Informatica, Universitá degli Studi di Firenze

  • Venue:
  • CIARP'05 Proceedings of the 10th Iberoamerican Congress conference on Progress in Pattern Recognition, Image Analysis and Applications
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Automatic semantic annotation of video streams allows to extract significant clips for archiving and retrieval of video content. In this paper, we present a system that performs automatic annotation of soccer videos, detecting principal highlights, and recognizing identity of players. Highlight detection is carried out by means of finite state machines that encode domain knowledge, while player identification is based on face detection, and on the analysis of contextual information such as jersey’s numbers and superimposed text captions. Results obtained on actual soccer videos shows overall highlight detection rates of about 90%. Lower, but still promising, accuracy is achieved on the very difficult player identification task.