Semantic feature extraction based on video abstraction and temporal modeling

Research output: Contribution to journalConference articlepeer-review

1 Citation (Scopus)


This paper presents a novel scheme of object-based video indexing and retrieval based on video abstraction and semantic event modeling. The proposed algorithm consists of three major steps; Video Object (VO) extraction, object-based video abstraction and statistical modeling of semantic features. Semantic feature modeling scheme is based on temporal variation of low-level features in object area between adjacent frames of video sequence. Each semantic feature is represented by a Hidden Markov Model (HMM) which characterizes the temporal nature of VO with various combinations of object features. The experimental results demonstrate the effective performance of the proposed approach.

Original languageEnglish
Pages (from-to)392-400
Number of pages9
JournalLecture Notes in Computer Science
Issue numberI
Publication statusPublished - 2005
Externally publishedYes
EventSecond Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2005 - Estoril, Portugal
Duration: 2005 Jun 72005 Jun 9

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)


Dive into the research topics of 'Semantic feature extraction based on video abstraction and temporal modeling'. Together they form a unique fingerprint.

Cite this