项目名称: 基于关键帧匹配与双向蒙特卡罗粒子滤波器的视频运动重定向研究
项目编号: No.61201236
项目类型: 青年科学基金项目
立项/批准年度: 2013
项目学科: 电子学与信息系统
项目作者: 叶龙
作者单位: 中国传媒大学
项目金额: 24万元
中文摘要: 在新媒体与文化创意产业蓬勃发展的今天,视频动画化由于在动画制作效率以及动画表现力方面的优势受到众多研究者的关注。本项目针对视频动画化中进行视频运动重定向时存在的观测模型缺失与高维采样问题,提出了一种基于关键帧匹配与双向马尔科夫链蒙特卡罗采样的视频运动重定向方法。对于给定视频,本课题首先提取其关键帧并通过仿射变换与线性叠加对由关键帧形成的视频时空体参数进行状态初始化并形成观测模型;其次,在每个时空体内部,基于时空体内各帧状态的双向马尔科夫性,提出一种双向马尔科夫链蒙特卡罗采样粒子滤波器结构,通过充分利用参数状态与观测模型的前后帧关系估计运动重定向参数;同时,针对高维采样问题,本课题根据定向参数的相关性实现骨架参数-形态参数-物理参数的分级,并提出分等级遗传策略优化参数输出并提高算法效率。本项目的研究将产生一种高效的且具有丰富动画表现力的视频运动重定向方法, 对视频动画化的发展具有重要意义。
中文关键词: 粒子滤波器;特征提取;运动重定向;视频重建;立体视频采集
英文摘要: Nowadays with the blooming development of new media and cultural creative industries, the video animation has drawn so many researchers' attention due to animation production efficiency and animation expression. This project aim at the difficulty that lack of observation model and high-dimensional sampling in video tooning, propose a method based on key frame matching and dual-directional Markov chain Monte Carlo sampling of video motion redirection. At first, after extracting the key frame of a given video, By affine transformation and linear superposition, the subject initializes the video's space-time parameters and forms the observation model; Secondly, in each space-time, based on the bi-directional Markov property of each frame, This subject proposed a dual-directional Markov chain Monte Carlo sampling particle filter structure and takes full advantage of the relationship of the front and back frame of the parameters to estimate motion redirection parameters. At the same time, for high-dimensional sampling problem, the subject according to the directional parameters' correlation implements classification of skeleton parameters-morphological parameters-physical parameters, proposes a hierarchical genetic strategy to optimize the output parameters and improves the efficiency of the algorithm. The research of
英文关键词: Particle Filtering;Feature Extraction;Motion Retargeting;Video Reconstruction;Stereo Video Capturing