Robustly estimating changes in image appearance

Black MJ.; Yacoob Y.; Fleet DJ.

首页> 外文期刊>Computer vision and image understanding: CVIU >Robustly estimating changes in image appearance

【24h】

Robustly estimating changes in image appearance

机译：Robustly estimating changes in image appearance

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

We propose a generalized model of image ''appearance change" in which brightness variation over time is represented as a probabilistic mixture of different causes, We define four generative models of appearance change due to (1) object or camera motion: (2) illumination phenomena: (3) specular reflections: and (4) "iconic changes" which are specific to the objects being viewed. These iconic changes include complex occlusion events and changes in the material properties of the objects. We develop a robust statistical framework for recovering these appearance changes in image sequences. This approach generalizes previous work on optical flow to provide a richer description of image events and more reliable estimates of image motion in the presense of shadows and specular reflections. (C) 2000 Academic Press. References: 45

著录项

来源
《Computer vision and image understanding: CVIU》 |2000年第1期|8-31|共24页
作者
Black MJ.; Yacoob Y.; Fleet DJ.;
展开▼
作者单位

Xerox Corp, Palo Alto Res Ctr, 3333 Coyote Hill Rd, Palo Alto, CA 94304, USA.;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类计算机的应用;
关键词
Optical flow; Mixture models; Outliers; Probabilistic models; Illumination change; Specularities; Iconic change; Optical-flow; Phase information; Motion estimation; Representations; Computation; Integration; Tracking; Models; Fields; Layers;

Robustly estimating changes in image appearance

摘要

著录项

相关主题

期刊订阅