Matches in SemOpenAlex for { <https://semopenalex.org/work/W3128555787> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3128555787 endingPage "472" @default.
- W3128555787 startingPage "472" @default.
- W3128555787 abstract "Airborne laser scanning (ALS) point cloud has been widely used in the fields of ground powerline surveying, forest monitoring, urban modeling, and so on because of the great convenience it brings to people’s daily life. However, the sparsity and uneven distribution of point clouds increases the difficulty of setting uniform parameters for semantic classification. The PointNet++ network is an end-to-end learning network for irregular point data and highly robust to small perturbations of input points along with corruption. It eliminates the need to calculate costly handcrafted features and provides a new paradigm for 3D understanding. However, each local region in the output is abstracted by its centroid and local feature that encodes the centroid’s neighborhood. The feature learned on the centroid point may not contain relevant information of itself for random sampling, especially in large-scale neighborhood balls. Moreover, the centroid point’s global-level information in each sample layer is also not marked. Therefore, this study proposed a modified PointNet++ network architecture which concentrates the point-level and global features on the centroid point towards the local features to facilitate classification. The proposed approach also utilizes a modified Focal Loss function to solve the extremely uneven category distribution on ALS point clouds. An elevation- and distance-based interpolation method is also proposed for the objects in ALS point clouds which exhibit discrepancies in elevation distributions. The experiments on the Vaihingen dataset of the International Society for Photogrammetry and Remote Sensing and the GML(B) 3D dataset demonstrate that the proposed method which provides additional contextual information to support classification achieves high accuracy with simple discriminative models and new state-of-the-art performance in power line categories." @default.
- W3128555787 created "2021-02-15" @default.
- W3128555787 creator A5037838106 @default.
- W3128555787 creator A5059227623 @default.
- W3128555787 creator A5067061325 @default.
- W3128555787 creator A5090395787 @default.
- W3128555787 creator A5090859671 @default.
- W3128555787 date "2021-01-29" @default.
- W3128555787 modified "2023-10-18" @default.
- W3128555787 title "PointNet++ Network Architecture with Individual Point Level and Global Features on Centroid for ALS Point Cloud Classification" @default.
- W3128555787 cites W1973644502 @default.
- W3128555787 cites W1977271893 @default.
- W3128555787 cites W1986522259 @default.
- W3128555787 cites W1994699846 @default.
- W3128555787 cites W2003731033 @default.
- W3128555787 cites W2034933046 @default.
- W3128555787 cites W2043045881 @default.
- W3128555787 cites W2086103748 @default.
- W3128555787 cites W2095359281 @default.
- W3128555787 cites W2099606917 @default.
- W3128555787 cites W2295511148 @default.
- W3128555787 cites W2567098398 @default.
- W3128555787 cites W2588275992 @default.
- W3128555787 cites W2752456892 @default.
- W3128555787 cites W2775216572 @default.
- W3128555787 cites W2884561390 @default.
- W3128555787 cites W2889155579 @default.
- W3128555787 cites W2898057260 @default.
- W3128555787 cites W2946815544 @default.
- W3128555787 cites W2979750740 @default.
- W3128555787 cites W3008274274 @default.
- W3128555787 cites W3009401626 @default.
- W3128555787 cites W3016245793 @default.
- W3128555787 cites W4244565819 @default.
- W3128555787 doi "https://doi.org/10.3390/rs13030472" @default.
- W3128555787 hasPublicationYear "2021" @default.
- W3128555787 type Work @default.
- W3128555787 sameAs 3128555787 @default.
- W3128555787 citedByCount "24" @default.
- W3128555787 countsByYear W31285557872021 @default.
- W3128555787 countsByYear W31285557872022 @default.
- W3128555787 countsByYear W31285557872023 @default.
- W3128555787 crossrefType "journal-article" @default.
- W3128555787 hasAuthorship W3128555787A5037838106 @default.
- W3128555787 hasAuthorship W3128555787A5059227623 @default.
- W3128555787 hasAuthorship W3128555787A5067061325 @default.
- W3128555787 hasAuthorship W3128555787A5090395787 @default.
- W3128555787 hasAuthorship W3128555787A5090859671 @default.
- W3128555787 hasBestOaLocation W31285557871 @default.
- W3128555787 hasConcept C124101348 @default.
- W3128555787 hasConcept C131979681 @default.
- W3128555787 hasConcept C138885662 @default.
- W3128555787 hasConcept C146599234 @default.
- W3128555787 hasConcept C153180895 @default.
- W3128555787 hasConcept C154945302 @default.
- W3128555787 hasConcept C2524010 @default.
- W3128555787 hasConcept C2776401178 @default.
- W3128555787 hasConcept C28719098 @default.
- W3128555787 hasConcept C33923547 @default.
- W3128555787 hasConcept C37054046 @default.
- W3128555787 hasConcept C41008148 @default.
- W3128555787 hasConcept C41895202 @default.
- W3128555787 hasConceptScore W3128555787C124101348 @default.
- W3128555787 hasConceptScore W3128555787C131979681 @default.
- W3128555787 hasConceptScore W3128555787C138885662 @default.
- W3128555787 hasConceptScore W3128555787C146599234 @default.
- W3128555787 hasConceptScore W3128555787C153180895 @default.
- W3128555787 hasConceptScore W3128555787C154945302 @default.
- W3128555787 hasConceptScore W3128555787C2524010 @default.
- W3128555787 hasConceptScore W3128555787C2776401178 @default.
- W3128555787 hasConceptScore W3128555787C28719098 @default.
- W3128555787 hasConceptScore W3128555787C33923547 @default.
- W3128555787 hasConceptScore W3128555787C37054046 @default.
- W3128555787 hasConceptScore W3128555787C41008148 @default.
- W3128555787 hasConceptScore W3128555787C41895202 @default.
- W3128555787 hasIssue "3" @default.
- W3128555787 hasLocation W31285557871 @default.
- W3128555787 hasOpenAccess W3128555787 @default.
- W3128555787 hasPrimaryLocation W31285557871 @default.
- W3128555787 hasRelatedWork W2002351209 @default.
- W3128555787 hasRelatedWork W2007009951 @default.
- W3128555787 hasRelatedWork W2082644203 @default.
- W3128555787 hasRelatedWork W2350539780 @default.
- W3128555787 hasRelatedWork W2381926679 @default.
- W3128555787 hasRelatedWork W2611300636 @default.
- W3128555787 hasRelatedWork W3122652148 @default.
- W3128555787 hasRelatedWork W3165040664 @default.
- W3128555787 hasRelatedWork W39961996 @default.
- W3128555787 hasRelatedWork W4282934273 @default.
- W3128555787 hasVolume "13" @default.
- W3128555787 isParatext "false" @default.
- W3128555787 isRetracted "false" @default.
- W3128555787 magId "3128555787" @default.
- W3128555787 workType "article" @default.