Li Qiming, Chen Chengcheng
College of Information Engineering, Shanghai Maritime University, Shanghai 201306, China.
Math Biosci Eng. 2023 Jan;20(1):1058-1082. doi: 10.3934/mbe.2023049. Epub 2022 Oct 24.
Limited by GPU memory, high-resolution image segmentation is a highly challenging task. To improve the accuracy of high-resolution segmentation, High-Resolution Refine Net (HRRNet) is proposed. The network is divided into a rough segmentation module and a refinement module. The former improves DeepLabV3+ by adding the shallow features of 1/2 original image size and the corresponding skip connection to obtain better rough segmentation results, the output of which is used as the input of the latter. In the refinement module, first, the global context information of the input image is obtained by a global process. Second, the high-resolution image is divided into patches, and each patch is processed separately to obtain local details in a local process. In both processes, multiple refine units (RU) are cascaded for refinement processing, and two cascaded residual convolutional units (RCU) are added to the different output paths of RU to improve the mIoU and the convergence speed of the network. Finally, according to the context information of the global process, the refined patches are pieced to obtain the refined segmentation result of the whole high-resolution image. In addition, the regional non-maximum suppression is introduced to improve the Sobel edge detection, and the Pascal VOC 2012 dataset is enhanced, which improves the segmentation accuracy and robust performance of the network. Compared with the state-of-the-art semantic segmentation models, the experimental results show that our model achieves the best performance in high-resolution image segmentation.
受GPU内存限制，高分辨率图像分割是一项极具挑战性的任务。为提高高分辨率分割的准确性，提出了高分辨率细化网络（HRRNet）。该网络分为粗略分割模块和细化模块。前者通过添加原始图像大小1/2的浅层特征及相应的跳跃连接来改进DeepLabV3+，以获得更好的粗略分割结果，其输出用作后者的输入。在细化模块中，首先通过全局处理获取输入图像的全局上下文信息。其次，将高分辨率图像划分为多个图像块，每个图像块分别进行处理以在局部处理中获取局部细节。在这两个处理过程中，多个细化单元（RU）级联进行细化处理，并且在RU的不同输出路径中添加两个级联的残差卷积单元（RCU）以提高网络的平均交并比（mIoU）和收敛速度。最后，根据全局处理的上下文信息，将细化后的图像块拼接起来以获得整个高分辨率图像的细化分割结果。此外，引入区域非极大值抑制来改进Sobel边缘检测，并增强了Pascal VOC 2012数据集，这提高了网络的分割精度和鲁棒性能。与当前最先进的语义分割模型相比，实验结果表明我们的模型在高分辨率图像分割中取得了最佳性能。
