Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285283611> ?p ?o ?g. }
- W4285283611 endingPage "4872" @default.
- W4285283611 startingPage "4861" @default.
- W4285283611 abstract "In aquaculture, using high-resolution SAR images to precisely segment offshore farms is helpful for reasonable layout planning and statistics of breeding density. However, conventional segmentation methods tend to have low accuracy and slow inference speed. Therefore, we propose a novel, precise and fast segmentation scheme for offshore farms in high-resolution SAR images based on model fusion and half-precision parallel inference. Specifically, we propose several new high-performance improved UNet++ and reasonably fuse the test results. At the same time, a simulated annealing strategy and a morphological closing operation are introduced to improve the segmentation accuracy. In addition, we find that resizing the images to 256×256 pixels is better than 512×512 pixels for this task, which not only has higher segmentation accuracy but can increase the inference speed by nearly 13%. Furthermore, a novel half-precision parallel inference strategy is proposed, which can fully utilize the GPU and increases the inference speed by 72.6%. Compared with some state-of-the-art methods, the proposed scheme that merges two improved UNet++ achieves superior accuracy with a frequency weighted intersection over union (FWIoU) of 0.9876 and a single image inference time of 0.0218 seconds on the high-resolution SAR offshore farm dataset." @default.
- W4285283611 created "2022-07-14" @default.
- W4285283611 creator A5000427996 @default.
- W4285283611 creator A5009866828 @default.
- W4285283611 creator A5021687717 @default.
- W4285283611 creator A5048012502 @default.
- W4285283611 creator A5075979415 @default.
- W4285283611 creator A5090632210 @default.
- W4285283611 date "2022-01-01" @default.
- W4285283611 modified "2023-10-18" @default.
- W4285283611 title "Precise and Fast Segmentation of Offshore Farms in High-Resolution SAR Images Based on Model Fusion and Half-Precision Parallel Inference" @default.
- W4285283611 cites W1623363662 @default.
- W4285283611 cites W1980287119 @default.
- W4285283611 cites W1990304459 @default.
- W4285283611 cites W2071521005 @default.
- W4285283611 cites W2097117768 @default.
- W4285283611 cites W2105259808 @default.
- W4285283611 cites W2110158442 @default.
- W4285283611 cites W2111727749 @default.
- W4285283611 cites W2146123543 @default.
- W4285283611 cites W2169552481 @default.
- W4285283611 cites W2183341477 @default.
- W4285283611 cites W2194775991 @default.
- W4285283611 cites W2312984074 @default.
- W4285283611 cites W2343614411 @default.
- W4285283611 cites W2395611524 @default.
- W4285283611 cites W2485120789 @default.
- W4285283611 cites W2529506056 @default.
- W4285283611 cites W2531409750 @default.
- W4285283611 cites W2560023338 @default.
- W4285283611 cites W2560385169 @default.
- W4285283611 cites W2565639579 @default.
- W4285283611 cites W2617083732 @default.
- W4285283611 cites W2618530766 @default.
- W4285283611 cites W2753385162 @default.
- W4285283611 cites W2791829678 @default.
- W4285283611 cites W2804860796 @default.
- W4285283611 cites W2806070179 @default.
- W4285283611 cites W2890713182 @default.
- W4285283611 cites W2895222021 @default.
- W4285283611 cites W2898947732 @default.
- W4285283611 cites W2942366787 @default.
- W4285283611 cites W2962914239 @default.
- W4285283611 cites W2963420686 @default.
- W4285283611 cites W2964350391 @default.
- W4285283611 cites W2969675848 @default.
- W4285283611 cites W2983707810 @default.
- W4285283611 cites W2984253982 @default.
- W4285283611 cites W2996290406 @default.
- W4285283611 cites W2996544626 @default.
- W4285283611 cites W2998340221 @default.
- W4285283611 cites W3004996704 @default.
- W4285283611 cites W3034429256 @default.
- W4285283611 cites W3049670509 @default.
- W4285283611 cites W3106753828 @default.
- W4285283611 cites W3114780996 @default.
- W4285283611 cites W3159208409 @default.
- W4285283611 cites W3200421546 @default.
- W4285283611 cites W3201366805 @default.
- W4285283611 cites W3207056758 @default.
- W4285283611 cites W3213513932 @default.
- W4285283611 cites W4205090338 @default.
- W4285283611 cites W4210920397 @default.
- W4285283611 cites W4214819464 @default.
- W4285283611 cites W4375939887 @default.
- W4285283611 cites W66352275 @default.
- W4285283611 doi "https://doi.org/10.1109/jstars.2022.3181355" @default.
- W4285283611 hasPublicationYear "2022" @default.
- W4285283611 type Work @default.
- W4285283611 citedByCount "3" @default.
- W4285283611 countsByYear W42852836112023 @default.
- W4285283611 crossrefType "journal-article" @default.
- W4285283611 hasAuthorship W4285283611A5000427996 @default.
- W4285283611 hasAuthorship W4285283611A5009866828 @default.
- W4285283611 hasAuthorship W4285283611A5021687717 @default.
- W4285283611 hasAuthorship W4285283611A5048012502 @default.
- W4285283611 hasAuthorship W4285283611A5075979415 @default.
- W4285283611 hasAuthorship W4285283611A5090632210 @default.
- W4285283611 hasBestOaLocation W42852836111 @default.
- W4285283611 hasConcept C124504099 @default.
- W4285283611 hasConcept C153180895 @default.
- W4285283611 hasConcept C154945302 @default.
- W4285283611 hasConcept C160633673 @default.
- W4285283611 hasConcept C2776214188 @default.
- W4285283611 hasConcept C31972630 @default.
- W4285283611 hasConcept C41008148 @default.
- W4285283611 hasConcept C87360688 @default.
- W4285283611 hasConcept C89600930 @default.
- W4285283611 hasConceptScore W4285283611C124504099 @default.
- W4285283611 hasConceptScore W4285283611C153180895 @default.
- W4285283611 hasConceptScore W4285283611C154945302 @default.
- W4285283611 hasConceptScore W4285283611C160633673 @default.
- W4285283611 hasConceptScore W4285283611C2776214188 @default.
- W4285283611 hasConceptScore W4285283611C31972630 @default.
- W4285283611 hasConceptScore W4285283611C41008148 @default.
- W4285283611 hasConceptScore W4285283611C87360688 @default.
- W4285283611 hasConceptScore W4285283611C89600930 @default.
- W4285283611 hasLocation W42852836111 @default.