论文信息 - Résumé de vidéo à partir d'un modèle d'attention visuelle

Résumé de vidéo à partir d'un modèle d'attention visuelle

This paper presents a method of video summarization based on a visual attention model. This model gives saliency maps which highlight area of frames containing more information and which attract human gaze. These saliency maps are used to detect changes on frames during the video which make it possible to select keyframes. A comparison between the summary and a reference summary shows the efficiency of our method.

Denis Pellerin | Mickael Guironnet | Sophie Marat

[1] Raimondo Schettini,et al. Video summarization using a neurodynamical model of visual attention , 2004, IEEE 6th Workshop on Multimedia Signal Processing, 2004..

[2] Stephen W. Smoliar,et al. An integrated system for content-based video retrieval and browsing , 1997, Pattern Recognit..

[3] Mickael Guironnet. Méthodes de résumé de vidéo à partir d'informations bas niveau, du mouvement de caméra ou de l'attention visuelle , 2006 .

[4] Ying Li,et al. An Overview of Video Abstraction Techniques , 2001 .

[5] Christof Koch,et al. A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[6] Jeanny Hérault,et al. NATURAL SCENE PERCEPTION: VISUAL ATTRACTORS AND IMAGES PROCESSING , 2002 .

[7] Laurent Itti,et al. Realistic avatar eye and head animation using a neurobiological model of visual attention , 2004, SPIE Optics + Photonics.

[8] Lie Lu,et al. A generic framework of user attention model and its application in video summarization , 2005, IEEE Trans. Multim..

[9] Nathalie Guyader,et al. STATIC AND DYNAMIC FEATURE − BASED VISUAL ATTENTION MODEL : COMPARAISON WITH HUMAN JUDGMENT ( TueAmOR 1 ) Author ( s ) : , 2005 .

[10] Nathalie Guyader,et al. Static and dynamic feature-based visual attention model: Comparison to human judgment , 2005, 2005 13th European Signal Processing Conference.