Contextual flow
Contextual flow
复制标题
DOI：
10.1109/cvpr.2009.5206719
复制
发表时间：
2009-06
期刊：
影响因子：
--
通讯作者：
Ying Wu;Jialue Fan
中科院分区：
文献类型：
--
作者：
Ying Wu;Jialue Fan
基于局部亮度的匹配非常有限，因为局部外观的微小变化会使亮度的恒定性失效。这种限制的根源在于它的处理方式与来自空间上下文的信息无关。本文从亮度恒定性跳跃到上下文恒定性，从而从光流跳跃到上下文流。它提出了一种新方法，该方法结合上下文来约束目标跟踪的运动估计。在此方法中，给定像素的一个单独的空间上下文由其上下文域中关联要素类的后验密度表示。每个单独的上下文都为运动提供了线性上下文流约束，以便可以在超定上下文系统中估计运动。基于这种上下文流模型，本文提出了一种新的、强大的目标跟踪方法，该方法集成了显着上下文点选择、鲁棒上下文匹配和动态上下文选择的过程。大量的实验结果表明了所提出方法的有效性。
Matching based on local brightness is quite limited, because small changes on local appearance invalidate the constancy in brightness. The root of this limitation is its treatment regardless of the information from the spatial contexts. This papers leaps from brightness constancy to context constancy, and thus from optical flow to contextual flow. It presents a new approach that incorporates contexts to constrain motion estimation for target tracking. In this approach, one individual spatial context of a given pixel is represented by the posterior density of the associated feature class in its contextual domain. Each individual context gives a linear contextual flow constraint to the motion, so that the motion can be estimated in an over-determined contextual system. Based on this contextual flow model, this paper presents a new and powerful target tracking method that integrates the processes of salient contextual point selection, robust contextual matching, and dynamic context selection. Extensive experiment results show the effectiveness of the proposed approach.