Hierarchical Disentangling Network for Building Extraction from Very High Resolution Optical Remote Sensing Imagery

Abstract

Building extraction using very high resolution (VHR) optical remote sensing imagery is an essential interpretation task that impacts human life. However, buildings in different environments exhibit various scales, complicated spatial distributions, and different imaging conditions. Additionally, with the spatial resolution of images increasing, there are diverse interior details and redundant context information present in building and background areas. Thus, the above-mentioned situations would create large intra-class variances and poor inter-class discrimination, leading to uncertain feature descriptions for building extraction, which would result in over- or under-extraction phenomena. In this article, a novel hierarchical disentangling network with an encoder–decoder architecture called HDNet is proposed to consider both the stable and uncertain feature description in a convolution neural network (CNN). Next, a hierarchical disentangling strategy is set up to individually generate strong and weak semantic zones using a newly designed feature disentangling module (FDM). Here, the strong and weak semantic zones set up the stable and uncertain description individually to determine a more stable semantic main body and uncertain semantic boundary of buildings. Next, a dual-stream semantic feature description is built to gradually integrate strong and weak semantic zones by the designed component feature fusion module (CFFM), which is able to generate a powerful semantic description for more complete and refined building extraction. Finally, extensive experiments are carried out on three published datasets (i.e., WHU satellite, WHU aerial, and INRIA), and the comparison results show that the proposed HDNet outperforms other state-of-the-art (SOTA) methods.

Multilevel Feature Aggregated Network with Instance Contrastive Learning Constraint for Building Extraction

“…To fairly evaluate the significance of our proposed method, we compared the proposed method with the most recently related building extraction methods including MC-FCN [18], RSR-Net [15], SiU-Net [14], SRI-Net [38], BOMSC-Net [50], HD-Net [51], EU-Net [52], CBR-Net [25], MA-FCN [28], MAP-Net [44], BRRNet [17], and BP-Net [25] on the above two datasets. The experimental outcomes are displayed in Table 3.…”

Multi-Layer Fault-Tolerant Protection Strategies for Hybrid Distribution Transformers Integrated Photovoltaic Systems

“…Since building mapping from remote sensing images has always been a hot research topic in the remote sensing community due to its extensive range of applications, many attempts have been widely explored, from hand-crafted feature-based traditional methods to deep learning-based automatic methods. Early work treats building extraction as a semantic segmentation task [5]- [9], [30], [31] or a instance segmentation task [10], [11], [13], [32], [33]. However, they typically output raster building segmentation masks and are not suitable for real-world applications.…”