Shot Boundary Detection in MPEG Videos using Local and Global Indicators
- Main information
-
Shot boundary detection (SBD) plays important roles in many video applications. In this paper, we describe a novel method on SBD operating directly in compressed domain. Firstly, several local indicators are extracted from MPEG macroblocks, and AdaBoost is employed for feature selection and fusion. The selected features are then used in classifying candidate cuts into five sub-spaces via pre-filtering and rule-based decision making. Following that, global indicators of frame similarity between boundary frames of cut candidates are examined using phase correlation of DC-images. Gradual transitions like fade, dissolve and combined shot cuts are also identified. Experimental results on the test data from TRECVID’07 have demonstrated the effectiveness and robustness of our proposed methodology. No referenced Knowhow defined WP5: Detection, Extraction and Annotation of Knowledge. School of Informatics University of Bradford Jianmin Jiang, Jinchang Ren 2009-04-16 11:03 Request for more detail
- Access and Use Rights
-
For LIVE project internal research purposes only. For LIVE project internal development purposes only.
- Protection Status
-
Copyright School of Informatics, University of Bradford. Patent Protection not sought. Licensing Protection not sought. Utility Model Protection not sought. To appear in IEEE Trans. CSVT Closed, attachment is not public
This item is not available for public download. For further information click on Request for more details above