Self-supervised contrastive learning (SSCL) is a potential learning paradigm for learning remote sensing image (RSI)-invariant features through the label-free method. The existing SSCL of RSI is built based on constructing positive and negative sample pairs. However, due to the richness of RSI ground objects and the complexity of the RSI contextual semantics, the same RSI patches have the coexistence and imbalance of positive and negative samples, which causing the SSCL pushing negative samples far away while pushing positive samples far away, and vice versa. We call this the sample confounding issue (SCI).To solve this problem, we propose a False negAtive sampLes aware contraStive lEarning model (FALSE) for the semantic segmentation of high-resolution RSIs. Since the SSCL pretraining is unsupervised, the lack of definable criteria for false negative sample (FNS) leads to theoretical undecidability, we designed two steps to implement the FNS approximation determination: coarse determination of FNS and precise calibration of FNS. We achieve coarse determination of FNS by the FNS self-determination (FNSD) strategy and achieve calibration of FNS by the FNS confidence calibration (FNCC) loss function. Experimental results on three RSI semantic segmentation datasets demonstrated that the FALSE effectively improves the accuracy of the downstream RSI semantic segmentation task compared with the current three models, which represent three different types of SSCL models. The mean Intersection-over-Union on ISPRS Potsdam dataset is improved by 0.7% on average; on CVPR DGLC dataset is improved by 12.28% on average; and on Xiangtan dataset this is improved by 1.17% on average. This indicates that the SSCL model has the ability to self-differentiate FNS and that the FALSE effectively mitigates the SCI in self-supervised contrastive learning.

No abstract

A high-quality built environment is important for human health and well-being. Assessing the quality of the urban built environment can provide planners and managers with decision-making for urban renewal to improve resident satisfaction. Many studies evaluate the built environment from the perspective of street scenes, but it is difficult for street-view data to cover every area of the built environment and its update frequency is low, which cannot meet the requirement of built-environment assessment under rapid urban development. Earth-observation data have the advantages of wide coverage, high update frequency, and good availability. This paper proposes an intelligent evaluation method for urban built environments based on scene understanding of high-resolution remote-sensing images. It contributes not only the assessment criteria for the built environment in remote-sensing images from the perspective of visual cognition but also an image-caption dataset applicable to urban-built-environment assessment. The results show that the proposed deep-learning-driven method can provide a feasible paradigm for representing high-resolution remote-sensing image scenes and large-scale urban-built-area assessment.

Landslide hazard assessment is essential for determining the probability of landslide occurrence in a specific spatial and temporal range. The hazard assessment of potential landslides could support landslide disaster early warning and disaster prevention decisions, which have important guiding significance for urban construction and sustainable development. Due to the lack of consideration of the synergistic effect of multiple factors and geographic scene heterogeneity, the accuracy of existing landslide hazard assessment methods still needs to be improved, and the interpretability and applicability of existing models still need to be improved. In this paper, we propose a landslide hazard assessment method considering the synergistic effect of multiple factors, including natural factors and human activities, and the heterogeneity of geographic scenes. On this basis, we carry out experimental verification on rainfall–induced landslides in Dehong Prefecture, Yunnan Province, China. Firstly, rainfall–induced landslide hazards’ characteristics and impact factors are analyzed and classified. The whole study area is divided into some homogeneous sub–regions using regional dynamic constraint clustering based on the similarity of underlying environmental variables. Then, considering the spatial autocorrelation between various landslide conditioning and trigger factors, a local weighted random forest model is developed to evaluate the rainfall–induced landslide hazards comprehensively. Experimental results show that the proposed method has higher accuracy and interpretability than the existing representative methods and can provide useful references for preventing landslide hazards.