Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387059706> ?p ?o ?g. }
- W4387059706 abstract "Abstract Convolutional neural networks (CNNs) have shown results superior to most traditional image understanding approaches in many fields, incl. crop classification from satellite time series images. However, CNNs require a large number of training samples to properly train the network. The process of collecting and labeling such samples using traditional methods can be both, time-consuming and costly. To address this issue and improve classification accuracy, generating virtual training labels (VTL) from existing ones is a promising solution. To this end, this study proposes a novel method for generating VTL based on sub-dividing the training samples of each crop using self-organizing maps (SOM), and then assigning labels to a set of unlabeled pixels based on the distance to these sub-classes. We apply the new method to crop classification from Sentinel images. A three-dimensional (3D) CNN is utilized for extracting features from the fusion of optical and radar time series. The results of the evaluation show that the proposed method is effective in generating VTL, as demonstrated by the achieved overall accuracy (OA) of 95.3% and kappa coefficient (KC) of 94.5%, compared to 91.3% and 89.9% for a solution without VTL. The results suggest that the proposed method has the potential to enhance the classification accuracy of crops using VTL." @default.
- W4387059706 created "2023-09-27" @default.
- W4387059706 creator A5005595654 @default.
- W4387059706 creator A5035918055 @default.
- W4387059706 creator A5069418475 @default.
- W4387059706 creator A5072893480 @default.
- W4387059706 date "2023-09-26" @default.
- W4387059706 modified "2023-10-16" @default.
- W4387059706 title "Generating Virtual Training Labels for Crop Classification from Fused Sentinel-1 and Sentinel-2 Time Series" @default.
- W4387059706 cites W2132965769 @default.
- W4387059706 cites W2292481059 @default.
- W4387059706 cites W2500751094 @default.
- W4387059706 cites W2548791488 @default.
- W4387059706 cites W2572303978 @default.
- W4387059706 cites W2577238056 @default.
- W4387059706 cites W2604086375 @default.
- W4387059706 cites W2728388975 @default.
- W4387059706 cites W2783608381 @default.
- W4387059706 cites W2805807568 @default.
- W4387059706 cites W2894214161 @default.
- W4387059706 cites W2900829435 @default.
- W4387059706 cites W2905254777 @default.
- W4387059706 cites W2906799152 @default.
- W4387059706 cites W2915971115 @default.
- W4387059706 cites W2963131120 @default.
- W4387059706 cites W2963470893 @default.
- W4387059706 cites W2964121744 @default.
- W4387059706 cites W2978935415 @default.
- W4387059706 cites W2981830988 @default.
- W4387059706 cites W2992308087 @default.
- W4387059706 cites W3005378446 @default.
- W4387059706 cites W3015258472 @default.
- W4387059706 cites W3018158283 @default.
- W4387059706 cites W3036506870 @default.
- W4387059706 cites W3082700671 @default.
- W4387059706 cites W3088464175 @default.
- W4387059706 cites W3100996084 @default.
- W4387059706 cites W3111029974 @default.
- W4387059706 cites W3142909427 @default.
- W4387059706 cites W3160966991 @default.
- W4387059706 cites W3183470088 @default.
- W4387059706 cites W3186981108 @default.
- W4387059706 cites W3194730353 @default.
- W4387059706 cites W3202499774 @default.
- W4387059706 cites W3217764757 @default.
- W4387059706 cites W4206994619 @default.
- W4387059706 cites W4210622501 @default.
- W4387059706 cites W4210807095 @default.
- W4387059706 cites W4225542667 @default.
- W4387059706 cites W4280530869 @default.
- W4387059706 cites W4281381779 @default.
- W4387059706 cites W4285389127 @default.
- W4387059706 cites W4287074666 @default.
- W4387059706 cites W4319019665 @default.
- W4387059706 cites W4381197386 @default.
- W4387059706 cites W4385245566 @default.
- W4387059706 cites W4386065702 @default.
- W4387059706 doi "https://doi.org/10.1007/s41064-023-00256-w" @default.
- W4387059706 hasPublicationYear "2023" @default.
- W4387059706 type Work @default.
- W4387059706 citedByCount "0" @default.
- W4387059706 crossrefType "journal-article" @default.
- W4387059706 hasAuthorship W4387059706A5005595654 @default.
- W4387059706 hasAuthorship W4387059706A5035918055 @default.
- W4387059706 hasAuthorship W4387059706A5069418475 @default.
- W4387059706 hasAuthorship W4387059706A5072893480 @default.
- W4387059706 hasBestOaLocation W43870597061 @default.
- W4387059706 hasConcept C111919701 @default.
- W4387059706 hasConcept C115961682 @default.
- W4387059706 hasConcept C119857082 @default.
- W4387059706 hasConcept C124101348 @default.
- W4387059706 hasConcept C143724316 @default.
- W4387059706 hasConcept C151730666 @default.
- W4387059706 hasConcept C153180895 @default.
- W4387059706 hasConcept C154945302 @default.
- W4387059706 hasConcept C163864269 @default.
- W4387059706 hasConcept C177264268 @default.
- W4387059706 hasConcept C199360897 @default.
- W4387059706 hasConcept C41008148 @default.
- W4387059706 hasConcept C50644808 @default.
- W4387059706 hasConcept C75294576 @default.
- W4387059706 hasConcept C81363708 @default.
- W4387059706 hasConcept C86803240 @default.
- W4387059706 hasConcept C98045186 @default.
- W4387059706 hasConceptScore W4387059706C111919701 @default.
- W4387059706 hasConceptScore W4387059706C115961682 @default.
- W4387059706 hasConceptScore W4387059706C119857082 @default.
- W4387059706 hasConceptScore W4387059706C124101348 @default.
- W4387059706 hasConceptScore W4387059706C143724316 @default.
- W4387059706 hasConceptScore W4387059706C151730666 @default.
- W4387059706 hasConceptScore W4387059706C153180895 @default.
- W4387059706 hasConceptScore W4387059706C154945302 @default.
- W4387059706 hasConceptScore W4387059706C163864269 @default.
- W4387059706 hasConceptScore W4387059706C177264268 @default.
- W4387059706 hasConceptScore W4387059706C199360897 @default.
- W4387059706 hasConceptScore W4387059706C41008148 @default.
- W4387059706 hasConceptScore W4387059706C50644808 @default.
- W4387059706 hasConceptScore W4387059706C75294576 @default.
- W4387059706 hasConceptScore W4387059706C81363708 @default.
- W4387059706 hasConceptScore W4387059706C86803240 @default.