Real-time feature-aware video abstraction
Real-time feature-aware video abstraction
复制标题
DOI：
10.1007/s00371-008-0254-8
复制
发表时间：
2008-07
期刊：
影响因子：
--
通讯作者：
Hanli Zhao;Xiaogang Jin;Jianbing Shen;Xiaoyang Mao;Jieqing Feng
中科院分区：
文献类型：
--
作者：
Hanli Zhao;Xiaogang Jin;Jianbing Shen;Xiaoyang Mao;Jieqing Feng
本文提出了一种新的特征感知渲染系统，该系统可以自动提取视频和图像，以提高图像在视觉通信任务中的有效性。我们整合双边网格来简化低对比度区域，这比双边滤波器的可分离近似更快，并使用特征流引导的各向异性边缘检测滤波器来增强高对比度区域。与各向同性高斯差分滤波相比，本文检测到的边缘更平滑，更连贯，更有风格。所提出的算法是高度并行的，允许在现代gpu上实现实时性能。我们的方法的实施是直截了当的。最后给出了几个实验实例来证明我们方法的有效性。
This paper presents a novel feature-aware rendering system that automatically abstracts videos and images with the goal of improving the effectiveness of imagery for visual communication tasks. We integrate the bilateral grid to simplify regions of low contrast, which is faster than the separable approximation to the bilateral filter, and use a feature flow-guided anisotropic edge detection filter to enhance regions of high contrast. The edges detected in this paper are smoother, more coherent and stylistic than those of the isotropic difference-of-Gaussian filter. The presented algorithms are highly parallel, allowing a real-time performance on modern GPUs. The implementation of our approach is straightforward. Several experimental examples are given at the end of the paper to demonstrate the effectiveness of our approach.