Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200463399> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4200463399 endingPage "106617" @default.
- W4200463399 startingPage "106617" @default.
- W4200463399 abstract "Convolutional neural network has brought breakthroughs on multispectral image reconstruction research. Previous work has largely focused on reconstructing MSI using the R-G-B channels from the MSI as inputs of the model. However, it’s image manipulation rather than practical use. In real application, to reconstruct multispectral image using images from RGB camera is a research that has hardly been studied. In this research, high resolution aerial RGB images are collected by drone with RGB camera and multispectral images are collected by drone with RedEdge-M multispectral Camera. Then a new two-step Generative Adversarial Network (GAN)-based reconstruction method was proposed as follows: At first, MSI and RGB images are carefully registered to make sure that pixels are one–one correspondent. Then two data sources are cropped to form dataset. After that, a novel R-MSI GAN using is proposed. It uses a ResUp&Down block to replace the ResNet block of the Generator network and it outperforms ResNet-based GAN. The experimental results show that: (1) the combination of Mean Square Error and Discriminator (MSE-D) can alleviate the problem of the high-frequency loss of generated images. (2) The root means square error (RMSE), mean relative absolute error (MRAE) and Structural Similarity (SSIM) can only reflect overall error but can’t reflect details in reconstructed images, while different bands' statistical histogram can present the total high-frequency loss of generated bands. (3) 3 indexes, which are intersection over union (IoU) based normalized difference vegetation index (NDVI)-IoU, normalized difference red edge (NDRE)-IoU and enhance vegetation index (EVI)-IoU, were defined to verify the effect of the generated MSI and they show good consistence with vegetation index map. 4 In comparisons among ResNet-based GAN, single step ResUp&Down GAN and two-step ResUp&Down GAN(T-GAN) with 3 loss functions (L1, MSE, Discriminator), the two-step ResUp&Down GAN(T-GAN) with MSE-D loss function performs best in reconstructing RGB bands. The T-GAN with L1loss-D (mean absolute error loss) performs best in reconstructing NIR and rededge bands. In summary, the proposed methods can effectively reconstruct MSI using images from RGB camera at drone based remote sensing." @default.
- W4200463399 created "2021-12-31" @default.
- W4200463399 creator A5008897278 @default.
- W4200463399 creator A5020484211 @default.
- W4200463399 creator A5036992589 @default.
- W4200463399 creator A5049798592 @default.
- W4200463399 creator A5054738516 @default.
- W4200463399 creator A5059602238 @default.
- W4200463399 creator A5060804553 @default.
- W4200463399 creator A5090803877 @default.
- W4200463399 date "2022-01-01" @default.
- W4200463399 modified "2023-10-15" @default.
- W4200463399 title "Two-step ResUp&Down generative adversarial network to reconstruct multispectral image from aerial RGB image" @default.
- W4200463399 cites W2011457345 @default.
- W4200463399 cites W2062493000 @default.
- W4200463399 cites W2088304553 @default.
- W4200463399 cites W2100109944 @default.
- W4200463399 cites W2111607654 @default.
- W4200463399 cites W2133665775 @default.
- W4200463399 cites W2148050322 @default.
- W4200463399 cites W2767657507 @default.
- W4200463399 cites W2947934595 @default.
- W4200463399 cites W2964782831 @default.
- W4200463399 cites W2995363336 @default.
- W4200463399 cites W2996290406 @default.
- W4200463399 cites W3124539583 @default.
- W4200463399 cites W3139551783 @default.
- W4200463399 doi "https://doi.org/10.1016/j.compag.2021.106617" @default.
- W4200463399 hasPublicationYear "2022" @default.
- W4200463399 type Work @default.
- W4200463399 citedByCount "3" @default.
- W4200463399 countsByYear W42004633992022 @default.
- W4200463399 countsByYear W42004633992023 @default.
- W4200463399 crossrefType "journal-article" @default.
- W4200463399 hasAuthorship W4200463399A5008897278 @default.
- W4200463399 hasAuthorship W4200463399A5020484211 @default.
- W4200463399 hasAuthorship W4200463399A5036992589 @default.
- W4200463399 hasAuthorship W4200463399A5049798592 @default.
- W4200463399 hasAuthorship W4200463399A5054738516 @default.
- W4200463399 hasAuthorship W4200463399A5059602238 @default.
- W4200463399 hasAuthorship W4200463399A5060804553 @default.
- W4200463399 hasAuthorship W4200463399A5090803877 @default.
- W4200463399 hasConcept C105795698 @default.
- W4200463399 hasConcept C139945424 @default.
- W4200463399 hasConcept C153180895 @default.
- W4200463399 hasConcept C154945302 @default.
- W4200463399 hasConcept C160633673 @default.
- W4200463399 hasConcept C173163844 @default.
- W4200463399 hasConcept C2524010 @default.
- W4200463399 hasConcept C2777210771 @default.
- W4200463399 hasConcept C31972630 @default.
- W4200463399 hasConcept C33923547 @default.
- W4200463399 hasConcept C41008148 @default.
- W4200463399 hasConcept C82990744 @default.
- W4200463399 hasConceptScore W4200463399C105795698 @default.
- W4200463399 hasConceptScore W4200463399C139945424 @default.
- W4200463399 hasConceptScore W4200463399C153180895 @default.
- W4200463399 hasConceptScore W4200463399C154945302 @default.
- W4200463399 hasConceptScore W4200463399C160633673 @default.
- W4200463399 hasConceptScore W4200463399C173163844 @default.
- W4200463399 hasConceptScore W4200463399C2524010 @default.
- W4200463399 hasConceptScore W4200463399C2777210771 @default.
- W4200463399 hasConceptScore W4200463399C31972630 @default.
- W4200463399 hasConceptScore W4200463399C33923547 @default.
- W4200463399 hasConceptScore W4200463399C41008148 @default.
- W4200463399 hasConceptScore W4200463399C82990744 @default.
- W4200463399 hasFunder F4320321001 @default.
- W4200463399 hasLocation W42004633991 @default.
- W4200463399 hasOpenAccess W4200463399 @default.
- W4200463399 hasPrimaryLocation W42004633991 @default.
- W4200463399 hasRelatedWork W2131104905 @default.
- W4200463399 hasRelatedWork W2139599928 @default.
- W4200463399 hasRelatedWork W2593793146 @default.
- W4200463399 hasRelatedWork W2739874619 @default.
- W4200463399 hasRelatedWork W2757828114 @default.
- W4200463399 hasRelatedWork W2767823485 @default.
- W4200463399 hasRelatedWork W2956043259 @default.
- W4200463399 hasRelatedWork W2980049530 @default.
- W4200463399 hasRelatedWork W3005455252 @default.
- W4200463399 hasRelatedWork W4213228110 @default.
- W4200463399 hasVolume "192" @default.
- W4200463399 isParatext "false" @default.
- W4200463399 isRetracted "false" @default.
- W4200463399 workType "article" @default.