基于改进DeepLabv3+网络的图像语义分割方法

Image Semantic Segmentation Method Based on Improved DeepLabv3+ Network

针对DeepLab网络不能充分利用多尺度特征信息,忽略了高分辨率浅层特征以及直接上采样倍数过大导致的重要像素信息丢失问题,提出了一种基于改进DeepLabv3+网络的图像语义分割方法。首先,充分利用了网络产生的多尺度特征信息,并采用特征金字塔网络有效融合了高分辨率的浅层特征;然后,使用逐层上采样增强图像中像素信息的连续性;最后,将空洞空间金字塔池化模块中的标准卷积替换为深度可分离卷积,提高了网络模型的训练效率。在语义分割标准数据集PASCAL VOC2012验证集上的实验结果表明,本方法的平均交并比可达到79.97%。相比DeepLab网络,可预测出更精细的语义分割结果。

This paper proposes an image semantic segmentation method based on an improved DeepLabv3+network to address the DeepLab network’s inability to fully utilize multiscale feature information while ignoring the problem of high-resolution shallow features and the loss of important pixel information due to excessive direct upsampling multiples.First,the multiscale feature information generated by the network is fully utilized and the feature pyramid network is used to effectively fuse high-resolution shallow features.Then,layer-by-layer upsampling is used to improve the image’s pixel information continuity.Finally,in the atrous spatial pyramid pooling module,the standard convolution is replaced with depthwise separable convolution,enhancing the network model’s training efficiency.The experimental results on the semantic segmentation standard data set PASCAL VOC2012 verification set show that,the mean intersection over union of the method can reach 79.97%.It can predict more refined semantic segmentation results compared with the DeepLab network.