基于空洞卷积的快速背景自动更换

针对背景更换过程复杂性较高导致传统方法效率低下并且精确度难以提高的问题，提出一种基于空洞卷积的快速图像背景更换方法——FABRNet。首先，采用VGG（Visual Geometry Group network）模型中前三部分网络结构对输入图片进行卷积和池化操作；其次，多组空洞卷积并联组合使得网络拥有足够大和足够细的感受野，并且加上残差网络结构来保证卷积过程中信息位置分布的准确性；最后，通过双线性插值算法将图片缩放到原图尺寸输出。在实验部分，与三种经典方法KNN（K-Nearest Neighbor）matting、Portrait matting和Deep matting进行了对比，结果表明，FABRNet能够有效地完成背景自动更换的操作，并且在速度方面有一定的优势。

Fast image background automatic replacement based on dilated convolution

Because of complexity of background replacement, the traditional method is inefficient and the accuracy is difficult to improve. To solve these problems, a fast image background replacement method based on dilated convolution, called FABRNet, was proposed. First of all, the first three parts of VGG (Visual Geometry Group network) model were used for convolution and pooling operations of input images. Secondly, the combination of multiple sets of dilated convolutions were embedded into convolution neural network to make the network have a large and fine enough receptive field; meanwhile, the residual network structure was used to ensure the accuracy of the information distribution in the convolution process. Finally, the image was scaled to the original size and output by bilinear interpolation algorithm. Compared with three classical methods such as KNN (K-Nearest Neighbors) matting, Portrait matting and Deep matting, the experimental results show that FABRNet can effectively complete the background automatic replacement, and has advantages in running speed.