Patwardhan Kedar A, Sapiro Guillermo, Morellas Vassilios
Visualization and Computer Vision Lab, GE Global Research, One Research Circle, Niskayuna, NY 12309, USA.
IEEE Trans Pattern Anal Mach Intell. 2008 Apr;30(4):746-51. doi: 10.1109/TPAMI.2007.70843.
A framework for robust foreground detection that works under difficult conditions such as dynamic background and moderately moving camera is presented in this paper. The proposed method includes two main components: coarse scene representation as the union of pixel layers, and foreground detection in video by propagating these layers using a maximum-likelihood assignment. We first cluster into "layers" those pixels that share similar statistics. The entire scene is then modeled as the union of such non-parametric layer-models. An in-coming pixel is detected as foreground if it does not adhere to these adaptive models of the background. A principled way of computing thresholds is used to achieve robust detection performance with a pre-specified number of false alarms. Correlation between pixels in the spatial vicinity is exploited to deal with camera motion without precise registration or optical flow. The proposed technique adapts to changes in the scene, and allows to automatically convert persistent foreground objects to background and re-convert them to foreground when they become interesting. This simple framework addresses the important problem of robust foreground and unusual region detection, at about 10 frames per second on a standard laptop computer. The presentation of the proposed approach is complemented by results on challenging real data and comparisons with other standard techniques.
本文提出了一种用于鲁棒前景检测的框架，该框架可在诸如动态背景和适度移动相机等困难条件下工作。所提出的方法包括两个主要部分：作为像素层联合的粗略场景表示，以及通过使用最大似然分配传播这些层来进行视频中的前景检测。我们首先将具有相似统计量的像素聚类为“层”。然后将整个场景建模为这些非参数层模型的联合。如果一个传入像素不符合这些背景自适应模型，则将其检测为前景。使用一种计算阈值的原则方法来在预先指定的误报数量下实现鲁棒的检测性能。利用空间邻域中像素之间的相关性来处理相机运动，而无需精确配准或光流。所提出的技术能够适应场景变化，并允许自动将持久的前景对象转换为背景，当它们变得有趣时再将其重新转换为前景。这个简单的框架解决了鲁棒前景和异常区域检测的重要问题，在标准笔记本电脑上以每秒约10帧的速度运行。通过在具有挑战性的真实数据上的结果以及与其他标准技术的比较，对所提出方法进行了补充说明。
