FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306174002> ?p ?o ?g. }

• W4306174002 endingPage "104383" @default.
• W4306174002 startingPage "104383" @default.
• W4306174002 abstract "In this paper, a fast, lightweight image fusion network, FLFuse-Net, is proposed to generate a new perspective image with identical and discriminative features from both infrared and visible images. In this network, deep convolutional features are extracted and fused synchronously through feature flow, while the edge features of the salient targets from the infrared image are compensated asynchronously. First, we design an autoencoder network structure with cross-connections for simultaneous feature extraction and fusion. In this structure, the fusion strategy is carried out through feature flow rather than by using a fixed fusion strategy, as in previous works. Second, we propose an edge compensation branch for salient information with the corresponding edge loss function to obtain the edge features of salient information from infrared images. Third, our network is designed as a lightweight network with a small number of parameters and low computational complexity, resulting in lower hardware requirements and a faster calculation speed. The experimental results confirm that the proposed FLFuse-Net outperforms the state-of-the-art fusion methods in objective and subjective assessments with very few parameters, especially on the TNO Image Fusion and NIR Scenes datasets. • In our proposed network, the information extraction and fusion are implemented simultaneously. On the one hand, it is no longer to design a fixed fusion strategy, and on the other hand, it reduces the additional computational effort caused by additional fusion strategies. • Our proposed network has been designed to be fast and lightweight. Especially, the weight sharing and information exchanging between two branches makes the network lightweight and fast. Inference speed of 512 × 512 images on RTX2080Ti takes less than 1ms. • An edge compensation branch and the corresponding edge loss function are proposed to provide more edge information for salient thermal targets from the infrared images to fused images." @default.
• W4306174002 created "2022-10-14" @default.
• W4306174002 creator A5003248833 @default.
• W4306174002 creator A5056401979 @default.
• W4306174002 creator A5078350872 @default.
• W4306174002 date "2022-12-01" @default.
• W4306174002 modified "2023-10-13" @default.
• W4306174002 title "FLFuse-Net: A fast and lightweight infrared and visible image fusion network via feature flow and edge compensation for salient information" @default.
• W4306174002 cites W1563797521 @default.
• W4306174002 cites W1965606870 @default.
• W4306174002 cites W1965739998 @default.
• W4306174002 cites W1999034606 @default.
• W4306174002 cites W1999316653 @default.
• W4306174002 cites W2040040441 @default.
• W4306174002 cites W2081195086 @default.
• W4306174002 cites W2091484864 @default.
• W4306174002 cites W2116702374 @default.
• W4306174002 cites W2131168375 @default.
• W4306174002 cites W2133665775 @default.
• W4306174002 cites W2146353910 @default.
• W4306174002 cites W2306859282 @default.
• W4306174002 cites W2474462684 @default.
• W4306174002 cites W2532801510 @default.
• W4306174002 cites W2559295071 @default.
• W4306174002 cites W2559870345 @default.
• W4306174002 cites W2589361588 @default.
• W4306174002 cites W2589745805 @default.
• W4306174002 cites W2621197300 @default.
• W4306174002 cites W2735436330 @default.
• W4306174002 cites W2751011928 @default.
• W4306174002 cites W2790212360 @default.
• W4306174002 cites W2792365373 @default.
• W4306174002 cites W2809216229 @default.
• W4306174002 cites W2912126472 @default.
• W4306174002 cites W2912147220 @default.
• W4306174002 cites W2954773727 @default.
• W4306174002 cites W2963134949 @default.
• W4306174002 cites W2963446712 @default.
• W4306174002 cites W2963787388 @default.
• W4306174002 cites W2963788325 @default.
• W4306174002 cites W2971071255 @default.
• W4306174002 cites W2991289865 @default.
• W4306174002 cites W3037628245 @default.
• W4306174002 cites W3087893884 @default.
• W4306174002 cites W3105639468 @default.
• W4306174002 cites W3138233798 @default.
• W4306174002 cites W3181367324 @default.
• W4306174002 cites W3190808861 @default.
• W4306174002 cites W3215518825 @default.
• W4306174002 cites W4206713196 @default.
• W4306174002 cites W4226178544 @default.
• W4306174002 doi "https://doi.org/10.1016/j.infrared.2022.104383" @default.
• W4306174002 hasPublicationYear "2022" @default.
• W4306174002 type Work @default.
• W4306174002 citedByCount "6" @default.
• W4306174002 countsByYear W43061740022023 @default.
• W4306174002 crossrefType "journal-article" @default.
• W4306174002 hasAuthorship W4306174002A5003248833 @default.
• W4306174002 hasAuthorship W4306174002A5056401979 @default.
• W4306174002 hasAuthorship W4306174002A5078350872 @default.
• W4306174002 hasConcept C11171543 @default.
• W4306174002 hasConcept C115961682 @default.
• W4306174002 hasConcept C120665830 @default.
• W4306174002 hasConcept C121332964 @default.
• W4306174002 hasConcept C138885662 @default.
• W4306174002 hasConcept C14166107 @default.
• W4306174002 hasConcept C153180895 @default.
• W4306174002 hasConcept C154945302 @default.
• W4306174002 hasConcept C15744967 @default.
• W4306174002 hasConcept C158355884 @default.
• W4306174002 hasConcept C158525013 @default.
• W4306174002 hasConcept C162307627 @default.
• W4306174002 hasConcept C2524010 @default.
• W4306174002 hasConcept C2776401178 @default.
• W4306174002 hasConcept C2780023022 @default.
• W4306174002 hasConcept C2780719617 @default.
• W4306174002 hasConcept C31972630 @default.
• W4306174002 hasConcept C33923547 @default.
• W4306174002 hasConcept C38349280 @default.
• W4306174002 hasConcept C41008148 @default.
• W4306174002 hasConcept C41895202 @default.
• W4306174002 hasConcept C57879066 @default.
• W4306174002 hasConcept C69744172 @default.
• W4306174002 hasConceptScore W4306174002C11171543 @default.
• W4306174002 hasConceptScore W4306174002C115961682 @default.
• W4306174002 hasConceptScore W4306174002C120665830 @default.
• W4306174002 hasConceptScore W4306174002C121332964 @default.
• W4306174002 hasConceptScore W4306174002C138885662 @default.
• W4306174002 hasConceptScore W4306174002C14166107 @default.
• W4306174002 hasConceptScore W4306174002C153180895 @default.
• W4306174002 hasConceptScore W4306174002C154945302 @default.
• W4306174002 hasConceptScore W4306174002C15744967 @default.
• W4306174002 hasConceptScore W4306174002C158355884 @default.
• W4306174002 hasConceptScore W4306174002C158525013 @default.
• W4306174002 hasConceptScore W4306174002C162307627 @default.
• W4306174002 hasConceptScore W4306174002C2524010 @default.
• W4306174002 hasConceptScore W4306174002C2776401178 @default.
• W4306174002 hasConceptScore W4306174002C2780023022 @default.

• next