FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4322005630> ?p ?o ?g. }

• W4322005630 abstract "Three-dimensional data have become increasingly present in earth observation over the last decades and, more recently, with the development of accessible 3D sensing technologies. However, many 3D surveys are still underexploited due to the lack of accessible and explainable automatic classification methods. In this work, we introduce explainable machine learning for 3D data classification using Multiple Attributes, Scales, and Clouds under 3DMASC, a new workflow. It handles multiple clouds at once, including or not spectral and multiple returns attributes. Through 3DMASC, we use classical 3D data multi-scale descriptors and new ones based on the spatial variations of geometrical, spectral and height-based features of the local point cloud. We also introduce dual-cloud features, encrypting local spectral and geometrical ratios and differences, which improve the interpretation of multi-cloud surveys. 3DMASC thus offers new possibilities for point cloud classification, namely for the interpretation of bi-spectral lidar data. Here, we experiment on topo-bathymetric lidar data, which are acquired using two lasers at infrared and green wavelengths, and feature two irregular point clouds characterized by different samplings of vegetated and flooded areas, that 3DMASC can harvest. By exploring the contributions of 88 features and 30 scales &#8211; including two types of neighborhoods &#8211; we identify a core set of features and scales particularly relevant for coastal and riverine scenes description, and give indications on how to build an optimal predictor vector to train 3D data classifiers. Our findings highlight the predominance of lidar return-based attributes over classical features based on dimensionality or eigenvalues, and the significant contribution of spectral information to the detection of more than a dozen of land and sea covers &#8211; artificial/vegetated/rocky/bare ground, rocky/sandy seabed, intermediate/high vegetation, buildings, vehicles, power lines. The experimental results show that 3DMASC competes with state-of-the-art methods in terms of classification performances while demanding lower complexity and thus remaining accessible to non-specialist users. Relying on a random forest algorithm, it generalizes and applies quickly to large datasets, and offers the possibility to filter out misclassified points depending on their prediction confidence. Classification accuracies between 91% for complex scene classifications and 98% for lower-level processing are observed, with average prediction confidences above 90% and models relying on less than 2000 samples per class and at most 30 descriptors &#8211; including both features and scales. Though dual-cloud features systematically outperform their single cloud equivalents, 3DMASC also performs on single cloud lidar data, or structure from motion point clouds. Our contributions are made available through a self-contained plugin in CloudCompare allowing non-specialist users to create a classifier and apply it, and an opensource labelled dataset of topo-bathymetric data." @default.
• W4322005630 created "2023-02-26" @default.
• W4322005630 creator A5006788065 @default.
• W4322005630 creator A5007277684 @default.
• W4322005630 creator A5024171000 @default.
• W4322005630 creator A5046531394 @default.
• W4322005630 creator A5047538306 @default.
• W4322005630 creator A5073496956 @default.
• W4322005630 creator A5082226026 @default.
• W4322005630 creator A5086914091 @default.
• W4322005630 date "2023-05-15" @default.
• W4322005630 modified "2023-10-14" @default.
• W4322005630 title "3DMASC: accessible, explainable 3D point clouds classification. Application to bi-spectral topo-bathymetric LiDAR data." @default.
• W4322005630 doi "https://doi.org/10.5194/egusphere-egu23-7115" @default.
• W4322005630 hasPublicationYear "2023" @default.
• W4322005630 type Work @default.
• W4322005630 citedByCount "0" @default.
• W4322005630 crossrefType "posted-content" @default.
• W4322005630 hasAuthorship W4322005630A5006788065 @default.
• W4322005630 hasAuthorship W4322005630A5007277684 @default.
• W4322005630 hasAuthorship W4322005630A5024171000 @default.
• W4322005630 hasAuthorship W4322005630A5046531394 @default.
• W4322005630 hasAuthorship W4322005630A5047538306 @default.
• W4322005630 hasAuthorship W4322005630A5073496956 @default.
• W4322005630 hasAuthorship W4322005630A5082226026 @default.
• W4322005630 hasAuthorship W4322005630A5086914091 @default.
• W4322005630 hasBestOaLocation W43220056302 @default.
• W4322005630 hasConcept C111030470 @default.
• W4322005630 hasConcept C111919701 @default.
• W4322005630 hasConcept C124101348 @default.
• W4322005630 hasConcept C131979681 @default.
• W4322005630 hasConcept C153180895 @default.
• W4322005630 hasConcept C154945302 @default.
• W4322005630 hasConcept C174943157 @default.
• W4322005630 hasConcept C177212765 @default.
• W4322005630 hasConcept C205649164 @default.
• W4322005630 hasConcept C41008148 @default.
• W4322005630 hasConcept C51399673 @default.
• W4322005630 hasConcept C58640448 @default.
• W4322005630 hasConcept C62649853 @default.
• W4322005630 hasConcept C77088390 @default.
• W4322005630 hasConcept C79974875 @default.
• W4322005630 hasConceptScore W4322005630C111030470 @default.
• W4322005630 hasConceptScore W4322005630C111919701 @default.
• W4322005630 hasConceptScore W4322005630C124101348 @default.
• W4322005630 hasConceptScore W4322005630C131979681 @default.
• W4322005630 hasConceptScore W4322005630C153180895 @default.
• W4322005630 hasConceptScore W4322005630C154945302 @default.
• W4322005630 hasConceptScore W4322005630C174943157 @default.
• W4322005630 hasConceptScore W4322005630C177212765 @default.
• W4322005630 hasConceptScore W4322005630C205649164 @default.
• W4322005630 hasConceptScore W4322005630C41008148 @default.
• W4322005630 hasConceptScore W4322005630C51399673 @default.
• W4322005630 hasConceptScore W4322005630C58640448 @default.
• W4322005630 hasConceptScore W4322005630C62649853 @default.
• W4322005630 hasConceptScore W4322005630C77088390 @default.
• W4322005630 hasConceptScore W4322005630C79974875 @default.
• W4322005630 hasLocation W43220056301 @default.
• W4322005630 hasLocation W43220056302 @default.
• W4322005630 hasLocation W43220056303 @default.
• W4322005630 hasLocation W43220056304 @default.
• W4322005630 hasOpenAccess W4322005630 @default.
• W4322005630 hasPrimaryLocation W43220056301 @default.
• W4322005630 hasRelatedWork W1992543912 @default.
• W4322005630 hasRelatedWork W2184765375 @default.
• W4322005630 hasRelatedWork W2739701376 @default.
• W4322005630 hasRelatedWork W2793357704 @default.
• W4322005630 hasRelatedWork W2901265155 @default.
• W4322005630 hasRelatedWork W4293094720 @default.
• W4322005630 hasRelatedWork W4319317934 @default.
• W4322005630 hasRelatedWork W4319837668 @default.
• W4322005630 hasRelatedWork W4386617716 @default.
• W4322005630 hasRelatedWork W773765100 @default.
• W4322005630 isParatext "false" @default.
• W4322005630 isRetracted "false" @default.
• W4322005630 workType "article" @default.