论文标题
使用有监督的方法无监督进行前景细分
Using a Supervised Method without supervision for foreground segmentation
论文作者
论文摘要
神经网络是静态相机获得的视频中前景细分的强大框架，在各种具有挑战性的情况下以健壮的方式从背景中分割了移动对象。首要方法是基于监督的方法，该方法需要在特定静态摄像头的数十个手动分割图像的数据库上进行最终训练阶段。在这项工作中，我们提出了一种方法，可以自动创建一个“人造”数据库，该数据库足以训练监督方法，以便它的性能比当前无监督的方法更好。与监督方法相比，它基于将弱前景细分器组合在一起，以从训练图像中提取合适的对象，并将这些对象随机插入背景图像中。测试结果显示在CDNET的测试序列上。
Neural networks are a powerful framework for foreground segmentation in video acquired by static cameras, segmenting moving objects from the background in a robust way in various challenging scenarios. The premier methods are those based on supervision requiring a final training stage on a database of tens to hundreds of manually segmented images from the specific static camera. In this work, we propose a method to automatically create an "artificial" database that is sufficient for training the supervised methods so that it performs better than current unsupervised methods. It is based on combining a weak foreground segmenter, compared to the supervised method, to extract suitable objects from the training images and randomly inserting these objects back into a background image. Test results are shown on the test sequences in CDnet.
