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

Automatic damage assessment based on UAV-derived 3D point clouds can providefast information on the damage situation after an earthquake. However, theassessment of multiple damage grades is challenging due to the variety indamage patterns and limited transferability of existing methods to othergeographic regions or data sources. We present a novel approach toautomatically assess multi-class building damage from real-world multi-temporalpoint clouds using a machine learning model trained on virtual laser scanning(VLS) data. We (1) identify object-specific change features, (2) separatechanged and unchanged building parts, (3) train a random forest machinelearning model with VLS data based on object-specific change features, and (4)use the classifier to assess building damage in real-world point clouds fromphotogrammetry-based dense image matching (DIM). We evaluate classifierstrained on different input data with respect to their capacity to classifythree damage grades (heavy, extreme, destruction) in pre- and post-event DIMpoint clouds of a real earthquake event. Our approach is transferable withrespect to multi-source input point clouds used for training (VLS) andapplication (DIM) of the model. We further achieve geographic transferabilityof the model by training it on simulated data of geometric change whichcharacterises relevant damage grades across different geographic regions. Themodel yields high multi-target classification accuracies (overall accuracy:92.0% - 95.1%). Its performance improves only slightly when using real-worldregion-specific training data (< 3% higher overall accuracies) and when usingreal-world region-specific training data (< 2% higher overall accuracies). Weconsider our approach relevant for applications where timely information on thedamage situation is required and sufficient real-world training data is notavailable.

Classification of structural building damage grades from multi-temporal  photogrammetric point clouds using a machine learning model trained on  virtual laser scanning data