Online background subtraction with freely moving cameras using different motion boundaries
Online background subtraction with freely moving cameras using different motion boundaries
复制标题
DOI：
10.1016/j.imavis.2018.06.003
复制
发表时间：
2018-08
期刊：
影响因子：
--
通讯作者：
D. Sugimura;Fumihiro Teshima;T. Hamamoto
中科院分区：
文献类型：
--
作者：
D. Sugimura;Fumihiro Teshima;T. Hamamoto
我们提出了一种从自由移动摄像机捕获的连续帧视频中在线减去背景的方法。我们的方法利用了一种带有种子的交互式图像分割技术(标记为“前景”和“背景”的像素子集)。我们方法的主要创新之处在于，通过利用两个不同的运动边界来自动估计种子，这两个边界分别使用流场的大小和方向来计算。当移动对象和相机朝着相同方向移动时，流场的大小可能有助于区分前景和背景运动。相反，当运动物体和摄像机的位移量相同时，流场方向有助于区分观察到的运动。通过自适应地利用这些不同运动边界的优势，我们的方法能够估计出可靠的前景/背景种子。使用估计的种子，我们的方法即使在复杂的摄像机运动(例如，大的摇摄-倾斜-变焦，旋转)时也能执行准确的背景减去。我们使用公共数据集和其他真实图像序列进行了实验，证明了该方法的有效性。
We propose a method for online background subtraction from a successive-frame video captured using a freely moving camera. Our method exploits a technique of interactive image segmentation with seeds (the subsets of pixels marked as “foreground” and “background”). The key novelty of our method is to automatically estimate the seeds by exploiting two different motion boundaries that are respectively computed using the magnitude and direction of the flow field. The magnitude of flow field is likely to be useful in differentiating the foreground and background motions when the moving objects and the camera make a movement towards the same direction. In contrast, the direction of flow field helps in discriminating the observed motions when the amount of displacement of the moving objects and the camera is the same. By adaptively exploiting the advantages of these different motion boundaries, our method enables to estimate the reliable foreground/background seeds. With the estimated seeds, our method performs accurate background subtraction even when the complex camera movements (e.g., large pan-tilt-zoom, rotation) are made. Our experiments demonstrate the effectiveness of our method using public dataset and other real image sequences.