Learning patterns of activity using real-time tracking
Learning patterns of activity using real-time tracking
复制标题
DOI：
10.1109/34.868677
复制
发表时间：
2000-08-01
影响因子：
23.6
通讯作者：
Grimson, WEL
中科院分区：
文献类型：
--
作者：
Stauffer, C;Grimson, WEL
我们的目标是开发一个视觉监控系统，被动地观察一个网站中的移动对象，并从这些观察中学习活动模式。对于扩展站点，系统将需要多个摄像机。因此，系统的关键要素是运动跟踪、摄像机协调、活动分类和事件检测。在本文中，我们专注于运动跟踪，并展示如何使用观察到的运动来学习网站中的活动模式。运动分割是基于自适应背景减除方法，该方法将每个像素建模为高斯混合，并使用在线近似来更新模型。然后评估高斯分布，以确定哪些最有可能来自背景过程。这就产生了一个稳定。实时户外跟踪器，可靠地处理照明变化、杂乱中的重复运动和长期场景变化。虽然跟踪系统不知道它跟踪的任何对象的身份，但身份对于整个跟踪序列保持相同。我们的系统通过积累序列中表示的联合同现来利用这些信息。这些联合同现统计，然后使用创建一个分层二叉树分类的表示。此方法可用于对序列以及站点中活动的各个实例进行分类。
Our goal is to develop a visual monitoring system that passively observes moving objects in a site and learns patterns of activity from those observations. For extended sites, the system will require multiple cameras. Thus, key elements of the system are motion tracking, camera coordination, activity classification, and event detection. In this paper, we focus on motion tracking and show how one can use observed motion to learn patterns of activity in a site. Motion segmentation is based on an adaptive background subtraction method that models each pixel as a mixture of Gaussians and uses an on-line approximation to update the model. The Gaussian distributions are then evaluated to determine which are most likely to result from a background process. This yields a stable. real-time outdoor tracker that reliably deals with lighting changes, repetitive motions from clutter, and long-term scene changes. While a tracking system is unaware of the identity of any object it tracks, the identity remains the same for the entire tracking sequence. Our system leverages this information by accumulating joint co-occurrences of the representations within a sequence. These joint cooccurrence statistics are then used to create a hierarchical binary-tree classification of the representations. This method is useful for classifying sequences, as well as individual instances of activities in a site.