Efficient and accurate road extraction from remote sensing imagery is important for applications related to navigation and Geographic Information System updating. Existing data-driven methods based on semantic segmentation recognize roads from images pixel by pixel, which generally uses only local spatial information and causes issues of discontinuous extraction and jagged boundary recognition. To address these problems, we propose a cascaded attention-enhanced architecture to extract boundary-refined roads from remote sensing images. Our proposed architecture uses spatial attention residual blocks on multi-scale features to capture long-distance relations and introduce channel attention layers to optimize the multi-scale features fusion. Furthermore, a lightweight encoder-decoder network is connected to adaptively optimize the boundaries of the extracted roads. Our experiments showed that the proposed method outperformed existing methods and achieved state-of-the-art results on the Massachusetts dataset. In addition, our method achieved competitive results on more recent benchmark datasets, e.g., the DeepGlobe and the Huawei Cloud road extraction challenge.

Most of the existing approaches to the extraction of buildings from high-resolution orthoimages consider the problem as semantic segmentation, which extracts a pixel-wise mask for buildings and trains end-to-end with manually labeled building maps. However, as buildings are highly structured, such a strategy suffers several problems, such as blurred boundaries and the adhesion to close objects. To alleviate the above problems, we proposed a new strategy that also considers the contours of the buildings. Both the contours and structures of the buildings are jointly learned in the same network. The contours are learnable because the boundary of the mask labels of buildings implicitly represents the contours of buildings. We utilized the building contour information embedded in the labels to optimize the representation of building boundaries, then combined the contour information with multi-scale semantic features to enhance the robustness to image spatial resolution. The experimental results showed that the proposed method achieved 91.64%, 81.34%, and 74.51% intersection over union (IoU) on the WHU, Aerial, and Massachusetts building datasets, and outperformed the state-of-the-art (SOTA) methods. It significantly improved the accuracy of building boundaries, especially for the edges of adjacent buildings. The code is made publicly available.

Buildings are fundamental elements of human environments, and detecting changes in them is crucial for land cover studies, urban expansion monitoring, and the detection of illegal construction activities. Existing methods primarily focus on pixel-level differences in bi-temporal remote sensing imagery. However, pseudo-changes, such as variations in non-building areas caused by differences in illumination, seasonal changes, and other factors, pose significant challenges for reliable building change detection. To address these issues, we propose a novel object-level contrastive-learning-based multi-branch network (OCL-Net) for detecting building changes by integrating bi-temporal remote sensing images. First, we design a multi-head decoder to separately extract more distinguishable building change features and auxiliary semantic features from bi-temporal images, effectively leveraging building-specific priors. Second, an object-level contrastive learning loss is designed and jointly optimized with a pixel-level similarity loss to ensure the global consistency of buildings. Finally, an attention-based discriminative feature generation and fusion block is designed to enhance the representation of multi-scale change features. We validate the effectiveness of the proposed method through comparative experiments on the publicly available WHU-CD and S2Looking datasets. Our approach achieves IoU values of 88.54% and 51.94%, respectively, surpassing state-of-the-art methods for building change detection.

Landslides are among the most common and destructive geological hazards and pose a significant threat to the long-term stability of infrastructure systems. In particular, long-distance power transmission corridors often traverse mountainous and forested regions, where landslides can endanger tower foundations and transmission line safety. Such landslides predominantly occur in sloped forested areas, where dense vegetation causes severe occlusion that blurs landslide boundaries and creates strong visual similarity with surrounding land covers. Consequently, accurate and efficient landslide identification from remote sensing imagery remains a significant challenge. To address these challenges, we propose a structural constrained contrastive learning network (SC-Net) for reliable landslide extraction from remote sensing images. First, a multi-structural feature extraction module is designed to capture landslide-specific geometric characteristics. These features are further enhanced by fusing multi-scale semantic representations extracted from a pretrained backbone network through an attention-based adaptive feature fusion module. Additionally, a mask-constrained object-level contrastive learning strategy is introduced to enforce global structural consistency at the landslide object-level, thereby improving the discriminability between landslide and non-landslide regions. Extensive experiments conducted on the publicly available CAS landslide dataset demonstrate the effectiveness of the proposed method. The proposed SC-Net achieves IoU scores of 89.89% and 79.76% on the CAS-UAV and CAS-SAT datasets, respectively, outperforming the best-performing baseline by 2.09% and 0.46%. The proposed method provides an effective solution for large-scale landslide monitoring and demonstrates potential for applications in power transmission corridor inspection and infrastructure safety assessment.