Breaking the resolution barrier: A low-to-high network for large-scale high-resolution land-cover mapping using low-resolution labels

• Published in: ISPRS journal of photogrammetry and remote sensing Vol. 192; pp. 244 - 267
• Main Authors: Li, Zhuohong, Zhang, Hongyan, Lu, Fangxiao, Xue, Ruoyao, Yang, Guangyi, Zhang, Liangpei
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.10.2022
• Subjects: Land-cover mapping; Low-to-high task; Multi-resolution; Semantic segmentation; Multi-resolution; Semantic segmentation; Low-to-high task; Land-cover mapping
• ISSN: 0924-2716; 1872-8235
• DOI: 10.1016/j.isprsjprs.2022.08.008

Large-scale high-resolution land-cover mapping is a way to comprehend the Earth’s surface and resolve the ecological and resource challenges facing humanity. High-resolution (≤1 m) remotely sensed images can now be captured more easily, with wider coverage, as sensors and satellites develop. Nevertheless, the synchronous renewal of land-cover maps is still challenging when using the common land-cover mapping methods, due to the requirement for high-resolution land-cover labels. Abundant low-resolution (∼30 m) land-cover products are available for use as alternative label sources, but the resolution gap between these products and the growing volume of high-resolution imagery is a barrier yet to be overcome. In this paper, to break through this obstacle, we propose a low-to-high network (L2HNet) to automatically generate high-resolution land-cover maps from high-resolution images by taking only low-resolution land-cover products as the training labels, thus getting rid of the requirement for finely labeled samples during the large-scale map updating process. Firstly, to obtain the mapping results with rich details, we propose a resolution-preserving (RP) backbone that contains parallel multi-scale convolutional layers for extracting the high-resolution features from the images. Furthermore, to settle the label noise issue caused by the mismatched resolution, a confident area selection (CAS) module and a low-to-high (L2H) loss function, with weak and unsupervised strategies, are designed for obtaining reliable supervision information from the coarse labels. The experimental results obtained for six administrative states located in the Chesapeake Bay watershed of the United States show that L2HNet outperforms several of the state-of-the-art methods and the mainstream land-cover mapping methods in creating 1-m resolution land-cover maps by taking 30-m resolution land-cover products as training labels. As a further application, L2HNet was also adopted to produce the first 1-m resolution land-cover map with level II classification hierarchy for the entire state of Maryland in the United States, which covers an area of about 33,872 km2. The land-cover map of Maryland is publicly available at http://hipag.whu.edu.cn/L2HNet.html.