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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Three-dimensional data have become increasingly present in earth observationover the last decades. However, many 3D surveys are still underexploited due tothe lack of accessible and explainable automatic classification methods, forexample, new topo-bathymetric lidar data. In this work, we introduceexplainable machine learning for 3D data classification using MultipleAttributes, Scales, and Clouds under 3DMASC, a new workflow. This workflowintroduces multi-cloud classification through dual-cloud features, encryptinglocal spectral and geometrical ratios and differences. 3DMASC uses classicalmulti-scale descriptors adapted to all types of 3D point clouds and new onesbased on their spatial variations. In this paper, we present the performancesof 3DMASC for multi-class classification of topo-bathymetric lidar data incoastal and fluvial environments. We show how multivariate and embedded featureselection allows the building of optimized predictor sets of reducedcomplexity, and we identify features particularly relevant for coastal andriverine scene descriptions. Our results show the importance of dual-cloudfeatures, lidar return-based attributes averaged over specific scales, and ofstatistics of dimensionality-based and spectral features. Additionally, theyindicate that small to medium spherical neighbourhood diameters (<7 m) aresufficient to build effective classifiers, namely when combined withdistance-to-ground or distance-to-water-surface features. Without usingoptional RGB information, and with a maximum of 37 descriptors, we obtainclassification accuracies between 91 % for complex multi-class tasks and 98 %for lower-level processing using models trained on less than 2000 samples perclass. Comparisons with classical point cloud classification methods show that3DMASC features have a significantly improved descriptive power. Ourcontributions are made available through a plugin in the CloudCompare software,allowing non-specialist users to create classifiers for any type of 3D datacharacterized by 1 or 2 point clouds (airborne or terrestrial lidar, structurefrom motion), and two labelled topo-bathymetric lidar datasets, available onhttps://opentopography.org/.

3DMASC: Accessible, explainable 3D point clouds classification. Application to Bi-spectral Topo-bathymetric lidar data