Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317627112> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4317627112 endingPage "21" @default.
- W4317627112 startingPage "1" @default.
- W4317627112 abstract "Convolutional Neural Networks (CNN) for ship classification in multi-spectral images (RGB, IR, etc.) is proposed in this paper. Recent developments in deep learning have significantly advanced the field of ship recognition. However, since maritime light intensity is frequently disturbed, multispectral imaging is considered a more robust substitute for RGB imaging. The proposed architectures were fine-tuned after being trained from scratch on the publicly available dataset VAIS (RGB-IR pairs). Unfortunately, the classification results plateaued at 59.74% accuracy, which is unsatisfactory for most real-life applications. Such an accuracy wall was due to the small number of training images. In order to overcome the scarcity of IR ship images, we proposed a novel image data augmentation strategy that translates RGB images to IR. A Pix2Pix model and a Generative Adversarial Network (GAN) network were modified to carry out the generation process as an RGB to IR translator. The KAIST general-purpose RGB-IR image pairs dataset was used to train our RGB-to-IR image translator, whereas the VAIS dataset was held aside for validation purposes. Our proposed network improved the accuracy of the native network by 8% (from 59.74% to 67.74%), which is fairly satisfactory in the field of ship recognition." @default.
- W4317627112 created "2023-01-21" @default.
- W4317627112 creator A5011805452 @default.
- W4317627112 creator A5022469183 @default.
- W4317627112 creator A5046374544 @default.
- W4317627112 creator A5051027108 @default.
- W4317627112 creator A5067645970 @default.
- W4317627112 creator A5072944170 @default.
- W4317627112 date "2023-01-19" @default.
- W4317627112 modified "2023-10-14" @default.
- W4317627112 title "A Novel Multispectral Maritime Target classification based on ThermalGAN (RGB-to-Thermal Image Translation)" @default.
- W4317627112 cites W1963882359 @default.
- W4317627112 cites W2064076387 @default.
- W4317627112 cites W2083366168 @default.
- W4317627112 cites W2117539524 @default.
- W4317627112 cites W2127934090 @default.
- W4317627112 cites W2251201217 @default.
- W4317627112 cites W2618113336 @default.
- W4317627112 cites W2727318261 @default.
- W4317627112 cites W2786644902 @default.
- W4317627112 cites W2802042319 @default.
- W4317627112 cites W2805605816 @default.
- W4317627112 cites W2890928948 @default.
- W4317627112 cites W2947500653 @default.
- W4317627112 cites W2963073614 @default.
- W4317627112 cites W2971542795 @default.
- W4317627112 cites W2972491066 @default.
- W4317627112 cites W3107538688 @default.
- W4317627112 cites W3110514869 @default.
- W4317627112 cites W3119919588 @default.
- W4317627112 cites W3155892032 @default.
- W4317627112 cites W3184767295 @default.
- W4317627112 cites W3193997983 @default.
- W4317627112 cites W3205667657 @default.
- W4317627112 cites W4283586027 @default.
- W4317627112 doi "https://doi.org/10.1080/0952813x.2023.2165723" @default.
- W4317627112 hasPublicationYear "2023" @default.
- W4317627112 type Work @default.
- W4317627112 citedByCount "1" @default.
- W4317627112 countsByYear W43176271122023 @default.
- W4317627112 crossrefType "journal-article" @default.
- W4317627112 hasAuthorship W4317627112A5011805452 @default.
- W4317627112 hasAuthorship W4317627112A5022469183 @default.
- W4317627112 hasAuthorship W4317627112A5046374544 @default.
- W4317627112 hasAuthorship W4317627112A5051027108 @default.
- W4317627112 hasAuthorship W4317627112A5067645970 @default.
- W4317627112 hasAuthorship W4317627112A5072944170 @default.
- W4317627112 hasBestOaLocation W43176271122 @default.
- W4317627112 hasConcept C108583219 @default.
- W4317627112 hasConcept C115961682 @default.
- W4317627112 hasConcept C153180895 @default.
- W4317627112 hasConcept C154945302 @default.
- W4317627112 hasConcept C173163844 @default.
- W4317627112 hasConcept C202444582 @default.
- W4317627112 hasConcept C2779757391 @default.
- W4317627112 hasConcept C31972630 @default.
- W4317627112 hasConcept C33923547 @default.
- W4317627112 hasConcept C41008148 @default.
- W4317627112 hasConcept C81363708 @default.
- W4317627112 hasConcept C82990744 @default.
- W4317627112 hasConcept C9652623 @default.
- W4317627112 hasConceptScore W4317627112C108583219 @default.
- W4317627112 hasConceptScore W4317627112C115961682 @default.
- W4317627112 hasConceptScore W4317627112C153180895 @default.
- W4317627112 hasConceptScore W4317627112C154945302 @default.
- W4317627112 hasConceptScore W4317627112C173163844 @default.
- W4317627112 hasConceptScore W4317627112C202444582 @default.
- W4317627112 hasConceptScore W4317627112C2779757391 @default.
- W4317627112 hasConceptScore W4317627112C31972630 @default.
- W4317627112 hasConceptScore W4317627112C33923547 @default.
- W4317627112 hasConceptScore W4317627112C41008148 @default.
- W4317627112 hasConceptScore W4317627112C81363708 @default.
- W4317627112 hasConceptScore W4317627112C82990744 @default.
- W4317627112 hasConceptScore W4317627112C9652623 @default.
- W4317627112 hasLocation W43176271121 @default.
- W4317627112 hasLocation W43176271122 @default.
- W4317627112 hasOpenAccess W4317627112 @default.
- W4317627112 hasPrimaryLocation W43176271121 @default.
- W4317627112 hasRelatedWork W2283162247 @default.
- W4317627112 hasRelatedWork W2731899572 @default.
- W4317627112 hasRelatedWork W2774550181 @default.
- W4317627112 hasRelatedWork W2999805992 @default.
- W4317627112 hasRelatedWork W3116150086 @default.
- W4317627112 hasRelatedWork W3133861977 @default.
- W4317627112 hasRelatedWork W4200173597 @default.
- W4317627112 hasRelatedWork W4212983513 @default.
- W4317627112 hasRelatedWork W4312417841 @default.
- W4317627112 hasRelatedWork W4321369474 @default.
- W4317627112 isParatext "false" @default.
- W4317627112 isRetracted "false" @default.
- W4317627112 workType "article" @default.