Stereoscopic Visual Attention Model for 3D Video
Stereoscopic Visual Attention Model for 3D Video
复制标题
DOI：
10.1007/978-3-642-11301-7_33
复制
发表时间：
2010-01
期刊：
影响因子：
--
通讯作者：
Yun Zhang;G. Jiang;Mei Yu;Ken Chen
中科院分区：
文献类型：
--
作者：
Yun Zhang;G. Jiang;Mei Yu;Ken Chen
与传统的单视点视频相比，三维视频(3DV)提供了用户交互功能和立体感，使人们对弹出区域或深度值较小的区域更感兴趣。因此，传统的单视视频视觉注意模型很难直接应用于三维视频的立体视觉注意分析。在本文中，我们提出了一种自下而上的SVA模型，以更准确地模拟具有立体视觉的人类视觉系统。该模型基于多种感知刺激，包括深度信息、亮度、颜色、方向和运动对比度。然后，提出了一种基于深度的动态融合方法来融合这些特征。在多视点视频测试序列上的实验结果表明，该模型保持了较高的鲁棒性，能够有效地模拟人眼的SVA。
Compared with traditional mono-view video, three-dimensional video (3DV) provides user interactive functionalities and stereoscopic perception, which makes people more interested in pop-out regions or the regions with small depth value. Thus, traditional visual attention model for mono-view video can hardly be directly applied to stereoscopic visual attention (SVA) analysis for 3DV. In this paper, we propose a bottom-up SVA model to simulate human visual system with stereoscopic vision more accurately. The proposed model is based on multiple perceptual stimuli including depth information, luminance, color, orientation and motion contrast. Then, a depth based dynamic fusion is proposed to integrate these features. The experimental results on multi-view video test sequences show that the proposed model maintains high robustness and is able to efficiently simulate SVA of human eyes.