HRRNet: Hierarchical Refinement Residual Network for Semantic Segmentation of Remote Sensing Images

Semantic segmentation of high-resolution remote sensing images plays an important role in many practical applications, including precision agriculture and natural disaster assessment. With the emergence of a large number of studies on convolutional neural networks, the performance of the semantic segmentation model of remote sensing images has been dramatically promoted. However, many deep convolutional network models do not fully refine the segmentation result maps, and, in addition, the contextual dependencies of the semantic feature map have not been adequately exploited. This article proposes a hierarchical refinement residual network (HRRNet) to address these issues. The HRRNet mainly consists of ResNet50 as the backbone, attention blocks, and decoders. The attention block consists of a channel attention module (CAM) and a pooling residual attention module (PRAM) and residual structures. Specifically, the feature map output by the four blocks of Resnet50 is passed through the attention block to fully explore the contextual dependencies of the position and channel of the semantic feature map, and, then, the feature maps of each branch are fused step by step to realize the refinement of the feature maps, thereby improving the segmentation performance of the proposed HRRNet. Experiments show that the proposed HRRNet improves segmentation result maps compared with various state-of-the-art networks on Vaihingen and Potsdam datasets.

Automated summary

Semantic segmentation of high-resolution remote sensing images is crucial in practical applications such as precision agriculture and natural disaster assessment. This article proposes a hierarchical refinement residual network (HRRNet) that utilizes attention blocks and decoders to improve the segmentation results by exploiting contextual dependencies. Experimental results show that HRRNet achieves superior segmentation results compared to state-of-the-art networks on Vaihingen and Potsdam datasets.