Height map estimation from a single aerial image plays a crucial role in localization,mapping,and 3D object detection.Deep convolutional neural networks have been used to predict height information from single-view re...Height map estimation from a single aerial image plays a crucial role in localization,mapping,and 3D object detection.Deep convolutional neural networks have been used to predict height information from single-view remote sensing images,but these methods rely on large volumes of training data and often overlook geometric features present in orthographic images.To address these issues,this study proposes a gradient-based self-supervised learning network with momentum contrastive loss to extract geometric information from non-labeled images in the pretraining stage.Additionally,novel local implicit constraint layers are used at multiple decoding stages in the proposed supervised network to refine high-resolution features in height estimation.The structural-aware loss is also applied to improve the robustness of the network to positional shift and minor structural changes along the boundary area.Experimental evaluation on the ISPRS benchmark datasets shows that the proposed method outperforms other baseline networks,with minimum MAE and RMSE of 0.116 and 0.289 for the Vaihingen dataset and 0.077 and 0.481 for the Potsdam dataset,respectively.The proposed method also shows around threefold data efficiency improvements on the Potsdam dataset and domain generalization on the Enschede datasets.These results demonstrate the effectiveness of the proposed method in height map estimation from single-view remote sensing images.展开更多
In this paper,GIS-based ordered weighted averaging(OWA)is applied to landslide susceptibility mapping(LSM)for the Urmia Lake Basin in northwest Iran.Nine landslide causal factors were used,whereby the respective param...In this paper,GIS-based ordered weighted averaging(OWA)is applied to landslide susceptibility mapping(LSM)for the Urmia Lake Basin in northwest Iran.Nine landslide causal factors were used,whereby the respective parameters were extracted from an associated spatial database.These factors were evaluated,and then the respective factor weight and class weight were assigned to each of the associated factors using analytic hierarchy process(AHP).A landslide suscept-ibility map was produced based on OWA multicriteria decision analysis.In order to validate the result,the outcome of the OWA method was qualitatively evaluated based on an existing inventory of known landslides.Correspondingly,an uncertainty analysis was carried out using the Dempster-Shafer theory.Based on the results,very strong support was determined for the high susceptibility category of the landslide susceptibility map,while strong support was received for the areas with moderate susceptibility.In this paper,we discuss in which respect these results are useful for an improved understanding of the effectiveness of OWA in LSM,and how the landslide prediction map can be used for spatial planning tasks and for the mitigation of future hazards in the study area.展开更多
基金supported by National Natural Science Foundation of China[grant number 42001329,42001283]Guangdong Basic and Applied Basic Research Foundation[grant number 2023A1515011718]+1 种基金China Postdoctoral Science Foundation[grant number 2021M701268]Foundation of Anhui Province Key Laboratory of Physical Geographic Environment,P.R.China[grant number 2022PGE012].
文摘Height map estimation from a single aerial image plays a crucial role in localization,mapping,and 3D object detection.Deep convolutional neural networks have been used to predict height information from single-view remote sensing images,but these methods rely on large volumes of training data and often overlook geometric features present in orthographic images.To address these issues,this study proposes a gradient-based self-supervised learning network with momentum contrastive loss to extract geometric information from non-labeled images in the pretraining stage.Additionally,novel local implicit constraint layers are used at multiple decoding stages in the proposed supervised network to refine high-resolution features in height estimation.The structural-aware loss is also applied to improve the robustness of the network to positional shift and minor structural changes along the boundary area.Experimental evaluation on the ISPRS benchmark datasets shows that the proposed method outperforms other baseline networks,with minimum MAE and RMSE of 0.116 and 0.289 for the Vaihingen dataset and 0.077 and 0.481 for the Potsdam dataset,respectively.The proposed method also shows around threefold data efficiency improvements on the Potsdam dataset and domain generalization on the Enschede datasets.These results demonstrate the effectiveness of the proposed method in height map estimation from single-view remote sensing images.
文摘In this paper,GIS-based ordered weighted averaging(OWA)is applied to landslide susceptibility mapping(LSM)for the Urmia Lake Basin in northwest Iran.Nine landslide causal factors were used,whereby the respective parameters were extracted from an associated spatial database.These factors were evaluated,and then the respective factor weight and class weight were assigned to each of the associated factors using analytic hierarchy process(AHP).A landslide suscept-ibility map was produced based on OWA multicriteria decision analysis.In order to validate the result,the outcome of the OWA method was qualitatively evaluated based on an existing inventory of known landslides.Correspondingly,an uncertainty analysis was carried out using the Dempster-Shafer theory.Based on the results,very strong support was determined for the high susceptibility category of the landslide susceptibility map,while strong support was received for the areas with moderate susceptibility.In this paper,we discuss in which respect these results are useful for an improved understanding of the effectiveness of OWA in LSM,and how the landslide prediction map can be used for spatial planning tasks and for the mitigation of future hazards in the study area.