Scene Composition in Augmented Virtual Presenter System

In soccer match, presenters or commentators are needed to help the audiences understanding the match more clearly. For better visual effect, we design an Augmented Virtual Presenter System which can integrate presenter’s image into the soccer field in match video. In fact, it is a scene composition process. In this paper, we will illustrate the structure and features of this system, and propose several solutions for the key problems. For scene composition, we design an algorithm consisting of automatic matting, localization, and occlusion processing. For occlusion problem, we propose a mixture solution including interactive and semantic segmentations for different scenarios.

[1]  Christophe Chefd'Hotel,et al.  Random Walk and Front Propagation on Watershed Adjacency Graphs for Multilabel Image Segmentation , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[2]  Michael F. Cohen,et al.  Optimized Color Sampling for Robust Matting , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Dani Lischinski,et al.  A Closed-Form Solution to Natural Image Matting , 2008 .

[5]  Anton Nijholt,et al.  Introducing an Embodied Virtual Presenter Agent in a Virtual Meeting Room , 2005, Artificial Intelligence and Applications.

[6]  Xinjian Chen,et al.  Random Walk and Graph Cut for Co-Segmentation of Lung Tumor on PET-CT Images , 2015, IEEE Transactions on Image Processing.

[7]  David Salesin,et al.  A Bayesian approach to digital matting , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[8]  Ling Shao,et al.  Sub-Markov Random Walk for Image Segmentation , 2016, IEEE Transactions on Image Processing.

[9]  Xinjian Chen,et al.  Correction to “Random Walk and Graph Cut for Co-Segmentation of Lung Tumor on PET-CT Images” , 2016, IEEE Transactions on Image Processing.

[10]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Timothy W. Bickmore,et al.  DynamicDuo: Co-presenting with Virtual Agents , 2015, CHI.

[14]  Vladimir Kolmogorov,et al.  "GrabCut": interactive foreground extraction using iterated graph cuts , 2004, ACM Trans. Graph..

[15]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[16]  Norman I. Badler,et al.  Design of a Virtual Human Presenter , 2000, IEEE Computer Graphics and Applications.