Volume 10 Issue 2 - April 2018

  • 1. Multi-view videos plus depth assessment using novel saliency detection method

    Authors : M Sowjanya, B Ramu

    Pages : 202-209

    DOI : http://dx.doi.org/10.21172/1.102.33

    Keywords : AVC,CSM, Saliency,MVD

    Abstract :

    Multi-view videos plus depth (MVD) is a popular 3D video representation where pixel depth information is exploited to generate additional views to provide 3D experience. Quality assessment of MVD data is of paramount importance since the latest research results show that existing 2D quality metrics are not suitable for MVD. This paper focuses on depth quality assessment and presents a novel algorithm to estimate the distortion in depth videos induced by compression. A novel saliency detection model is introduced by utilizing low level features obtained from Stationary Wavelet Transform domain.Firstly, wavelet transform is employed to create the multi-scale feature maps which can represent different features from edge to texture. Then, we propose a computational model for the saliency map from these features. This model is aimed to modulate local contrast at a location with its global saliency computed based on likelihood of the features and also considered local centre-surround differences and global contrast in the final saliency map. Experimental evaluation depicts the promising results from the proposed model by outperforming the relevant state of the art saliency detection models.

    Citing this Journal Article :

    M Sowjanya, B Ramu, "Multi-view videos plus depth assessment using novel saliency detection method", https://www.ijltet.org/journal_details.php?id=930&j_id=4493, Volume 10 Issue 2 - April 2018, 202-209, #ijltetorg