Probabilistic tracking in joint feature-spatial spaces
Probabilistic tracking in joint feature-spatial spaces
复制标题
DOI：
10.1109/cvpr.2003.1211432
复制
发表时间：
2003-06
期刊：
影响因子：
--
通讯作者：
A. Elgammal;R. Duraiswami;L. Davis
中科院分区：
文献类型：
--
作者：
A. Elgammal;R. Duraiswami;L. Davis
在本文中，我们提出了一种基于区域外观的概率跟踪框架。我们利用表示对象的区域的特征-空间分布作为概率约束来跟踪该区域随时间的变化。在给定联合特征-空间分布的非参数表示的情况下，通过在变换空间上最大化基于相似性的目标函数来实现跟踪。这种表示对与区域结构耦合的区域特征分布施加了概率约束，这产生了对小的局部变形和部分遮挡具有鲁棒性的外观跟踪器。我们给出了联合特征空间分布的一般形式，并将其应用于不同类型图像特征的跟踪，包括行强度、颜色和图像梯度。
In this paper, we present a probabilistic framework for tracking regions based on their appearance. We exploit the feature-spatial distribution of a region representing an object as a probabilistic constraint to track that region over time. The tracking is achieved by maximizing a similarity-based objective function over transformation space given a nonparametric representation of the joint feature-spatial distribution. Such a representation imposes a probabilistic constraint on the region feature distribution coupled with the region structure, which yields an appearance tracker that is robust to small local deformations and partial occlusion. We present the approach for the general form of joint feature-spatial distributions and apply it to tracking with different types of image features including row intensity, color and image gradient.