文献类型：会议论文

英文题名：Non-linear dynamic texture analysis and synthesis using constrained Gaussian process latent variable model

作者：Zhou, Guanling[1];Dong, Nanping[1];Wang, Yuping[1]

第一作者：Zhou, Guanling

通讯作者：Zhou, GL[1]

机构：[1]Beijing Union Univ, Coll Automat, Beijing 100101, Peoples R China

第一机构：北京联合大学城市轨道交通与物流学院

通讯机构：[1]corresponding author), Beijing Union Univ, Coll Automat, Beijing 100101, Peoples R China.|[1141751]北京联合大学城市轨道交通与物流学院;[11417]北京联合大学;

会议论文集：Pacific-Asia Conference on Circuits, Communications and Systems

会议日期：MAY 16-17, 2009

会议地点：Chengdu, PEOPLES R CHINA

语种：英文

外文关键词：computer vision; dynamic texture; machine learning; sampling method

摘要：Linear dynamic system (LDS) [1] has been proposed to model dynamic texture. However, the temporal evolution of dynamic texture is non-linear in general and is not fully captured by the linear model. In this paper, we formulate the dynamic texture learning and synthesis via nonlinear approach. Assuming that dynamic texture is sampled from a low dimensional manifold, the constrained Gaussian process latent variable model (CGPLVM) is proposed to model the dynamic texture as a set of latent states. The essence of dynamic texture is captured as the spatial relationship within the latent states. Moreover, Metropolis-Hastings sampling method is used to sample new states, which hold the spatio-temporal statistics of dynamic texture. Experimental results demonstrate that our approach can produce dynamic texture sequences with promising visual quality.