This paper presents a new model of human attention that allows salient areas to be extracted from video frames. As automatic understanding of video semantic content is still far from being achieved, attention model tends to mimic the focus of the human visual system. Most existing approaches extract the saliency of images in order to be used in multiple applications but they are not compared to human perception. The model described here is achieved by the fusion of a static model inspired by the human system and a model of moving object detection. The static model is divided into two steps: a "retinal" filtering followed by a "cortical" decomposition. The moving object detection is carried out by a compensation of camera motion. Then we compare the attention model output for different videos with human judgment. A psychophysical experiment is proposed to compare the model with visual human perception and to validate it. The experimental results indicate that the model achieves about 88% of precision. This shows the usefulness of the scheme and its potential in future applications.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Spatio-temporal attention model for video content analysis


    Beteiligte:
    Guironnet, M. (Autor:in) / Guyader, N. (Autor:in) / Pellerin, D. (Autor:in) / Ladret, P. (Autor:in)


    Erscheinungsdatum :

    01.01.2005


    Format / Umfang :

    285168 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Spatio-temporal Attention Model for Video Content Analysis

    Guironnet, M. / Guyader, N. / Pellerin, D. et al. | British Library Conference Proceedings | 2005


    A Video Content Retrieval Method Based on Spatio-temporal Change Information

    Wei, W. / Shu, H.-p. / Liu, F.-y. | British Library Online Contents | 2007


    Track Prediction Based on Spatio-Temporal Attention

    Wang, Peng / Zhang, Junyi / Zhang, Lu et al. | Springer Verlag | 2022


    Real-time Attention-Augmented Spatio-Temporal Networks for Video-based Driver Activity Recognition

    Saleh, Khaled / Mihaita, Adriana-Simona / Yu, Kun et al. | IEEE | 2022


    A spatio-temporal model of the selective human visual attention

    Le Meur, O. / Thoreau, D. / Le Callet, P. et al. | IEEE | 2005