Authors:
Hana Gharbi
;
Sahbi Bahroun
and
Ezzeddine Zagrouba
Affiliation:
Institut Supérieur d'Informatique (ISI) and Université Tunis Elmanar, Tunisia
Keyword(s):
Video Summarization, Key Frame Extraction, Interest Point, PCA, HAC.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Computer Vision, Visualization and Computer Graphics
;
Entertainment Imaging Applications
;
Image and Video Analysis
;
Image Formation and Preprocessing
;
Image Generation Pipeline: Algorithms and Techniques
;
Motion, Tracking and Stereo Vision
;
Shape Representation and Matching
;
Tracking and Visual Navigation
Abstract:
Video summarization is a principal task in video analysis and indexing algorithms. In this paper we will present a new algorithm for video key frame extraction. This process is one of the basic procedures for video retrieval and summary. Our new approach is based on interest points description and repeatability measurement. Before key frame extraction, the video should be segmented into shots. Then, for each shot, we detect interest points in all images. After that, we calculate repeatability matrix for each shot. Finally, we apply PCA and HAC to extract key frames.