Adaptive background model registration for moving cameras
Adaptive background model registration for moving cameras
复制标题
DOI：
10.1016/j.patrec.2017.03.010
复制
发表时间：
2017-09-01
影响因子：
5.1
通讯作者：
Taniguchi, Rin-ichiro
中科院分区：
文献类型：
--
作者：
Minematsu, Tsubasa;Uchiyama, Hideaki;Taniguchi, Rin-ichiro
我们提出了一种自适应地将背景模型与图像配准的框架，用于移动摄像机的背景减去。现有的方法使用固定的窗口大小来搜索背景模型，以抑制在检测前景时的误报数量。然而，这些方法会导致许多假阴性，因为它们可能使用不适当的窗口大小。合适的大小取决于目标场景的各种因素。为了抑制误检测，我们提出了自适应控制方法参数，这些参数通常是启发式确定的。更具体地，背景配准的搜索窗口大小和前景检测阈值是使用由基于单应性的相机运动估计计算的重新投影误差自动确定的。我们的方法是基于这样一个事实，即如果像素属于背景，则误差较低，如果不属于背景，则误差较高。我们定量地证实，当应用于各种公共数据集中的运动摄像机的图像时，所提出的框架提高了背景减去的精度。(C)2017爱思唯尔B.V.保留所有权利。
We propose a framework for adaptively registering background models with an image for background subtraction with moving cameras. Existing methods search for a background model using a fixed window size, to suppress the number of false positives when detecting the foreground. However, these approaches result in many false negatives because they may use inappropriate window sizes. The appropriate size depends on various factors of the target scenes. To suppress false detections, we propose adaptively controlling the method parameters, which are typically determined heuristically. More specifically, the search window size for background registration and the foreground detection threshold are automatically determined using the re-projection error computed by the homography based camera motion estimate. Our method is based on the fact that the error at a pixel is low if it belongs to background and high if it does not. We quantitatively confirmed that the proposed framework improved the background subtraction accuracy when applied to images from moving cameras in various public datasets. (C) 2017 Elsevier B.V. All rights reserved.