A COMPUTATIONAL FRAMEWORK AND AN ALGORITHM FOR THE MEASUREMENT OF VISUAL-MOTION
A COMPUTATIONAL FRAMEWORK AND AN ALGORITHM FOR THE MEASUREMENT OF VISUAL-MOTION
复制标题
DOI：
10.1007/bf00158167
复制
发表时间：
1989-01-01
影响因子：
19.5
通讯作者：
ANANDAN, P
中科院分区：
文献类型：
--
作者：
ANANDAN, P
从数字化图像序列中鲁棒地测量视觉运动一直是计算机视觉中的一个重要但困难的问题。本文描述了一种用于从一对图像确定密集位移场的分层计算框架，以及与该框架一致的算法。我们的框架基于图像强度信息和测量运动过程的基于比例的分离。首先使用大尺度强度信息来获得图像运动的粗略估计，然后使用较小尺度的强度信息来细化图像运动。估计值采用像素位移（或速度）矢量的形式，并伴有方向相关的置信度度量。采用平滑约束将高置信度的测量结果传播到置信度较低的邻近区域。在所有级别上，计算都是像素并行的，在整个图像中是均匀的，并且基于来自像素的小邻域的信息。包括将我们的算法应用于成对的真实图像的结果。除了我们自己的匹配算法之外，我们还表明两种不同的基于梯度的分层算法与我们的框架一致。
The robust measurement of visual motion from digitized image sequences has been an important but difficult problem in computer vision. This paper describes a hierarchical computational framework for the determination of dense displacement fields from a pair of images, and an algorithm consistent with that framework. Our framework is based on a scale-based separation of the image intensity information and the process of measuring motion. The large-scale intensity information is first used to obtain rough estimates of image motion, which are then refined by using intensity information at smaller scales. The estimates are in the form of displacement (or velocity) vectors for pixels and are accompanied by a direction-dependent confidence measure. A smoothness constraint is employed to propagate measurements with high confidence to neighboring areas where the confidences are low. At all levels, the computations are pixel-parallel, uniform across the image, and based on information from a small neighborhood of a pixel. Results of applying our algorithm to pairs of real images are included. In addition to our own matching algorithm, we also show that two different hierarchical gradient-based algorithms are consistent with our framework.