Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897453039> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2897453039 abstract "Recently, the new Geographic object-based image analysis (GEOBIA) was proposed as an alternative classification approach to pixel based ones. In GEOBIA, image segments can be depicted with various attributes such as spectral, texture, shape, deep features and context, and hence final classification can produce better land cover/use map. The presence of such a large number of features poses significant challenges to standard machine learning methods and has rendered many existing classification techniques impractical. In this work, we are interested to feature selection techniques, which are employed to reduce the dimensionality of the data while keeping the most of its expressive power. Inspired by recent works in remote sensing using Convolutional Neural Networks (CNNs), especially for hyperspectral band selection, a feature selection approach based on One-Dimensional Convolutional Neural Networks (1-D CNN) is proposed in this study. All object-based features are used to train the 1-D CNN to obtain well trained model. After testing different feature combinations, we use the well trained model to obtain their test classification accuracies, and finally we select the subset of features with the highest precision. In our experiments, we evaluate our feature selection approach on 30-cm resolution colour infrared (CIR) aerial orthoimagery. A multi-resolution segmentation is performed to segment the images into regions, which are characterized later using various spectral, textural and spatial attributes to form the final object-based feature dataset. The obtained experimental results show that the proposed method can achieve satisfactory results when compared with traditional feature selection approaches." @default.
- W2897453039 created "2018-10-26" @default.
- W2897453039 creator A5052949635 @default.
- W2897453039 creator A5059371063 @default.
- W2897453039 creator A5070761189 @default.
- W2897453039 creator A5076771786 @default.
- W2897453039 date "2018-10-09" @default.
- W2897453039 modified "2023-09-27" @default.
- W2897453039 title "One-dimensional convolution neural networks for object-based feature selection" @default.
- W2897453039 cites W1521436688 @default.
- W2897453039 cites W1950365613 @default.
- W2897453039 cites W1984792953 @default.
- W2897453039 cites W1991856651 @default.
- W2897453039 cites W2019180375 @default.
- W2897453039 cites W2061240006 @default.
- W2897453039 cites W2074112114 @default.
- W2897453039 cites W2115044652 @default.
- W2897453039 cites W2143426320 @default.
- W2897453039 cites W2167101736 @default.
- W2897453039 cites W2412588858 @default.
- W2897453039 cites W2600746131 @default.
- W2897453039 cites W2769143033 @default.
- W2897453039 cites W4297957988 @default.
- W2897453039 doi "https://doi.org/10.1117/12.2325640" @default.
- W2897453039 hasPublicationYear "2018" @default.
- W2897453039 type Work @default.
- W2897453039 sameAs 2897453039 @default.
- W2897453039 citedByCount "0" @default.
- W2897453039 crossrefType "proceedings-article" @default.
- W2897453039 hasAuthorship W2897453039A5052949635 @default.
- W2897453039 hasAuthorship W2897453039A5059371063 @default.
- W2897453039 hasAuthorship W2897453039A5070761189 @default.
- W2897453039 hasAuthorship W2897453039A5076771786 @default.
- W2897453039 hasConcept C111030470 @default.
- W2897453039 hasConcept C115961682 @default.
- W2897453039 hasConcept C124504099 @default.
- W2897453039 hasConcept C138885662 @default.
- W2897453039 hasConcept C148483581 @default.
- W2897453039 hasConcept C153180895 @default.
- W2897453039 hasConcept C154945302 @default.
- W2897453039 hasConcept C159078339 @default.
- W2897453039 hasConcept C160633673 @default.
- W2897453039 hasConcept C166957645 @default.
- W2897453039 hasConcept C205649164 @default.
- W2897453039 hasConcept C2776401178 @default.
- W2897453039 hasConcept C2779343474 @default.
- W2897453039 hasConcept C41008148 @default.
- W2897453039 hasConcept C41895202 @default.
- W2897453039 hasConcept C52622490 @default.
- W2897453039 hasConcept C75294576 @default.
- W2897453039 hasConcept C81363708 @default.
- W2897453039 hasConcept C89600930 @default.
- W2897453039 hasConceptScore W2897453039C111030470 @default.
- W2897453039 hasConceptScore W2897453039C115961682 @default.
- W2897453039 hasConceptScore W2897453039C124504099 @default.
- W2897453039 hasConceptScore W2897453039C138885662 @default.
- W2897453039 hasConceptScore W2897453039C148483581 @default.
- W2897453039 hasConceptScore W2897453039C153180895 @default.
- W2897453039 hasConceptScore W2897453039C154945302 @default.
- W2897453039 hasConceptScore W2897453039C159078339 @default.
- W2897453039 hasConceptScore W2897453039C160633673 @default.
- W2897453039 hasConceptScore W2897453039C166957645 @default.
- W2897453039 hasConceptScore W2897453039C205649164 @default.
- W2897453039 hasConceptScore W2897453039C2776401178 @default.
- W2897453039 hasConceptScore W2897453039C2779343474 @default.
- W2897453039 hasConceptScore W2897453039C41008148 @default.
- W2897453039 hasConceptScore W2897453039C41895202 @default.
- W2897453039 hasConceptScore W2897453039C52622490 @default.
- W2897453039 hasConceptScore W2897453039C75294576 @default.
- W2897453039 hasConceptScore W2897453039C81363708 @default.
- W2897453039 hasConceptScore W2897453039C89600930 @default.
- W2897453039 hasLocation W28974530391 @default.
- W2897453039 hasOpenAccess W2897453039 @default.
- W2897453039 hasPrimaryLocation W28974530391 @default.
- W2897453039 hasRelatedWork W2500751094 @default.
- W2897453039 hasRelatedWork W2737996023 @default.
- W2897453039 hasRelatedWork W2767651786 @default.
- W2897453039 hasRelatedWork W2774181585 @default.
- W2897453039 hasRelatedWork W2774265021 @default.
- W2897453039 hasRelatedWork W2807839383 @default.
- W2897453039 hasRelatedWork W2943345824 @default.
- W2897453039 hasRelatedWork W2955667634 @default.
- W2897453039 hasRelatedWork W3095523211 @default.
- W2897453039 hasRelatedWork W4214895820 @default.
- W2897453039 isParatext "false" @default.
- W2897453039 isRetracted "false" @default.
- W2897453039 magId "2897453039" @default.
- W2897453039 workType "article" @default.