融合对象性和视觉显著度的单目图像2D转3D  

Single-view image 2D-to-3D conversion based on objectness and visual saliency

作　　者：袁红星[1] 吴少群[1] 朱仁祥[1] 安鹏[1] 

机构地区：[1]宁波工程学院电子与信息工程学院,宁波315016

出　　处：《中国图象图形学报》2013年第11期1478-1485,共8页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61071173);浙江省自然科学基金项目(LY12F01001;Y1100253);宁波市自然科学基金项目(2012A610043)

摘　　要：受对象性测度和视觉显著度的启发,提出一种适用于单目图像2D转3D的对象窗深度中心环绕分布假设,给出融合对象性测度和视觉显著度的单目图像深度估计算法。首先计算图像的视觉显著度并将其映射成深度;其次在图像上随机采样若干个窗,并计算这些窗的对象性测度;再次,定义一个能量函数用于度量深度和对象性测度对彼此的影响程度,并通过迭代优化的方法改进深度和对象性测度的估计结果;最后,根据深度信息进行3D视频合成。实验结果表明,融入对象性测度信息后,显著改进了基于视觉显著度2D转3D的深度估计质量,保证了估计深度在对象边界处的不连续过渡和其他区域的平滑过渡。Inspired by objectness measurement and visual saliency, we propose an object window center-surround depth distribution hypothesis for single-view image 2D-to-3D conversion. Based on this model, a depth estimation method fusing objectness and visual saliency is presented. First, visual saliency detection is performed and it is mapped to the depth. Second, some windows are sampled randomly for objectness measuring. Third, an energy function is used to model relations between depth and objectness, and then it is minimized by an iterative method to improve depth estimation results. Finally, 3D video is rendered based on depth. Experimental results show that our method improves depth discontinuity at objects boundary and continuity at other regions greatly.

关 键 词：对象性测度 视觉显著度 2D转3D 3D视频 

分 类 号：TN911.73[电子电信—通信与信息系统]