Stochastic Uncertainty Models for the Luminance Consistency Assumption

	Stochastic Uncertainty Models for the Luminance Consistency Assumption
	Corpetti, Thomas 1; Memin, Etienne 2
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2012-02-01
卷号	21 期号:2 页码:481-493
文章类型	Article
摘要	In this paper, a stochastic formulation of the brightness consistency used in many computer vision problems involving dynamic scenes (for instance, motion estimation or point tracking) is proposed. Usually, this model, which assumes that the luminance of a point is constant along its trajectory, is expressed in a differential form through the total derivative of the luminance function. This differential equation linearly links the point velocity to the spatial and temporal gradients of the luminance function. However, when dealing with images, the available information only holds at discrete time and on a discrete grid. In this paper, we formalize the image luminance as a continuous function transported by a flow known only up to some uncertainties related to such a discretization process. Relying on stochastic calculus, we define a formulation of the luminance function preservation in which these uncertainties are taken into account. From such a framework, it can be shown that the usual deterministic optical flow constraint equation corresponds to our stochastic evolution under some strong constraints. These constraints can be relaxed by imposing a weaker temporal assumption on the luminance function and also in introducing anisotropic intensity-based uncertainties. We also show that these uncertainties can be computed at each point of the image grid from the image data and hence provide meaningful information on the reliability of the motion estimates. To demonstrate the benefit of such a stochastic formulation of the brightness consistency assumption, we have considered a local least-squares motion estimator relying on this new constraint. This new motion estimator significantly improves the quality of the results.
关键词	Image Motion Analysis Image Quality Image Sampling Stochastic Processes
WOS标题词	Science & Technology ; Technology
关键词[WOS]	OPTIC FLOW COMPUTATION ; MOTION COMPUTATION ; DENSE ESTIMATION ; TRACKING ; CONSTRAINT ; FRAMEWORK
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000300559700005
引用统计	被引频次：15[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/8000
专题	脑图谱与类脑智能实验室_脑网络组研究
作者单位	1.Chinese Acad Sci, Inst Automat, Sino French Lab Comp Sci Automat & Appl Math LIAM, Beijing 100190, Peoples R China 2.Natl Inst Res Comp Sci & Control INRIA, Fluminance Grp, F-35042 Rennes, France
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Corpetti, Thomas,Memin, Etienne. Stochastic Uncertainty Models for the Luminance Consistency Assumption[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2012,21(2):481-493.
APA	Corpetti, Thomas,&Memin, Etienne.(2012).Stochastic Uncertainty Models for the Luminance Consistency Assumption.IEEE TRANSACTIONS ON IMAGE PROCESSING,21(2),481-493.
MLA	Corpetti, Thomas,et al."Stochastic Uncertainty Models for the Luminance Consistency Assumption".IEEE TRANSACTIONS ON IMAGE PROCESSING 21.2(2012):481-493.