English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Precision mapping of landslide inventory is crucial for hazard mitigation.Most landslides generally co-exist with other confusing geological features,and the presence of such areas can only be inferred unambiguously at a largescale. In addition, local information is also important for the preservation ofobject boundaries. Aiming to solve this problem, this paper proposes aneffective approach to fuse both local and non-local features to surmount thecontextual problem. Built upon the U-Net architecture that is widely adopted inthe remote sensing community, we utilize two additional modules. The first oneuses dilated convolution and the corresponding atrous spatial pyramid pooling,which enlarged the receptive field without sacrificing spatial resolution orincreasing memory usage. The second uses a scale attention mechanism to guidethe up-sampling of features from the coarse level by a learned weight map. Inimplementation, the computational overhead against the original U-Net was onlya few convolutional layers. Experimental evaluations revealed that the proposedmethod outperformed state-of-the-art general-purpose semantic segmentationapproaches. Furthermore, ablation studies have shown that the two modelsafforded extensive enhancements in landslide-recognition performance.

Deep Fusion of Local and Non-Local Features for Precision Landslide Recognition