Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387445395> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4387445395 abstract "UAVs are widely used in marine environment monitoring and ecological protection, and accurate segmentation of UAV images is the basis for achieving these applications. However, the marine images taken by UAVs often have the problems of large intra-class scale changes and high inter-class similarity, resulting in a sharp decline in the performance of traditional semantic segmentation methods in this segmentation task. In order to alleviate this dilemma, we construct a new semantic segmentation network (EMFNet) combining transformer and multi-scale feature fusion to achieve accurate segmentation of UAV ocean images. For larger intra-class variations, we introduce transformer blocks made up of external attention (EA) to capture potential correlations between data samples. For the high similarity between different semantic categories, we specially construct feature fusion branches to learn diverse feature information. Inspired by camouflage object detection, in the fusion branch, we design a mixed convolutional attention (MCA) module to increase the receptive field and a dual attention fusion module (DAFM) to realize cross-level learnin. At the same time, we apply the auxiliary segmentation head to the fused features to refine the segmentation results layer by layer and discard all auxiliary segmentation headers in the inference stage to maintain real-time inference. Experimental results show that our designed EMFNet achieves 77.13% MIoU on the public dataset Cityscapes and 61.41% MIoU on our UAV-OUC-SEG dataset, respectively, and maintains a real-time inference speed of 61.6FPS." @default.
- W4387445395 created "2023-10-10" @default.
- W4387445395 creator A5003769106 @default.
- W4387445395 creator A5014379518 @default.
- W4387445395 creator A5014578719 @default.
- W4387445395 creator A5017601344 @default.
- W4387445395 creator A5025007289 @default.
- W4387445395 creator A5046374166 @default.
- W4387445395 date "2023-07-27" @default.
- W4387445395 modified "2023-10-11" @default.
- W4387445395 title "An Image Segmentation Method Based on Transformer and Multi-Scale Feature Fusion for UAV Marine Environment Monitoring" @default.
- W4387445395 cites W1903029394 @default.
- W4387445395 cites W2150587757 @default.
- W4387445395 cites W2169384781 @default.
- W4387445395 cites W2560023338 @default.
- W4387445395 cites W2963419596 @default.
- W4387445395 cites W2963881378 @default.
- W4387445395 cites W2963890956 @default.
- W4387445395 cites W2964217532 @default.
- W4387445395 cites W3034684132 @default.
- W4387445395 cites W3125430184 @default.
- W4387445395 cites W3168112135 @default.
- W4387445395 cites W3170841864 @default.
- W4387445395 cites W3179949961 @default.
- W4387445395 cites W3190335749 @default.
- W4387445395 cites W3196904463 @default.
- W4387445395 cites W4213147678 @default.
- W4387445395 cites W4214893857 @default.
- W4387445395 cites W4285601297 @default.
- W4387445395 cites W4302275239 @default.
- W4387445395 cites W4312232166 @default.
- W4387445395 cites W4312258849 @default.
- W4387445395 cites W4312815172 @default.
- W4387445395 doi "https://doi.org/10.1109/icivc58118.2023.10270243" @default.
- W4387445395 hasPublicationYear "2023" @default.
- W4387445395 type Work @default.
- W4387445395 citedByCount "0" @default.
- W4387445395 crossrefType "proceedings-article" @default.
- W4387445395 hasAuthorship W4387445395A5003769106 @default.
- W4387445395 hasAuthorship W4387445395A5014379518 @default.
- W4387445395 hasAuthorship W4387445395A5014578719 @default.
- W4387445395 hasAuthorship W4387445395A5017601344 @default.
- W4387445395 hasAuthorship W4387445395A5025007289 @default.
- W4387445395 hasAuthorship W4387445395A5046374166 @default.
- W4387445395 hasConcept C119599485 @default.
- W4387445395 hasConcept C124504099 @default.
- W4387445395 hasConcept C127413603 @default.
- W4387445395 hasConcept C153180895 @default.
- W4387445395 hasConcept C154945302 @default.
- W4387445395 hasConcept C165801399 @default.
- W4387445395 hasConcept C2776214188 @default.
- W4387445395 hasConcept C31972630 @default.
- W4387445395 hasConcept C41008148 @default.
- W4387445395 hasConcept C52622490 @default.
- W4387445395 hasConcept C66322947 @default.
- W4387445395 hasConcept C89600930 @default.
- W4387445395 hasConceptScore W4387445395C119599485 @default.
- W4387445395 hasConceptScore W4387445395C124504099 @default.
- W4387445395 hasConceptScore W4387445395C127413603 @default.
- W4387445395 hasConceptScore W4387445395C153180895 @default.
- W4387445395 hasConceptScore W4387445395C154945302 @default.
- W4387445395 hasConceptScore W4387445395C165801399 @default.
- W4387445395 hasConceptScore W4387445395C2776214188 @default.
- W4387445395 hasConceptScore W4387445395C31972630 @default.
- W4387445395 hasConceptScore W4387445395C41008148 @default.
- W4387445395 hasConceptScore W4387445395C52622490 @default.
- W4387445395 hasConceptScore W4387445395C66322947 @default.
- W4387445395 hasConceptScore W4387445395C89600930 @default.
- W4387445395 hasLocation W43874453951 @default.
- W4387445395 hasOpenAccess W4387445395 @default.
- W4387445395 hasPrimaryLocation W43874453951 @default.
- W4387445395 hasRelatedWork W1522196789 @default.
- W4387445395 hasRelatedWork W2045526782 @default.
- W4387445395 hasRelatedWork W2055243143 @default.
- W4387445395 hasRelatedWork W2357796999 @default.
- W4387445395 hasRelatedWork W3094491777 @default.
- W4387445395 hasRelatedWork W3214715529 @default.
- W4387445395 hasRelatedWork W4206178588 @default.
- W4387445395 hasRelatedWork W4287635093 @default.
- W4387445395 hasRelatedWork W4321636575 @default.
- W4387445395 hasRelatedWork W4379231730 @default.
- W4387445395 isParatext "false" @default.
- W4387445395 isRetracted "false" @default.
- W4387445395 workType "article" @default.