Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328110740> ?p ?o ?g. }
- W4328110740 endingPage "1682" @default.
- W4328110740 startingPage "1682" @default.
- W4328110740 abstract "In traditional image processing, the Fourier transform is often used to transform an image from the spatial domain to the frequency domain, and frequency filters are designed from the perspective of the frequency domain to sharpen or blur the image. In the field of remote sensing change detection, deep learning is beginning to become a mainstream tool. However, deep learning can still refer to traditional methodological ideas. In this paper, we designed a new convolutional neural network (MFGFNet) in which multiple global filters (GFs) are used to capture more information in the frequency domain, thus sharpening the image boundaries and better preserving the edge information of the change region. In addition, in MFGFNet, we use CNNs to extract multi-scale images to enhance the effects and to better focus on information about changes in different sizes (multi-scale combination module). The multiple pairs of enhancements are fused by the difference method and then convolved and concatenated several times to obtain a better difference fusion effect (feature fusion module). In our experiments, the IOUs of our network for the LEVIR-CD, SYSU, and CDD datasets are 0.8322, 0.6780, and 0.9101, respectively, outperforming the state-of-the-art model and providing a new perspective on change detection." @default.
- W4328110740 created "2023-03-22" @default.
- W4328110740 creator A5021301663 @default.
- W4328110740 creator A5036584593 @default.
- W4328110740 creator A5039088967 @default.
- W4328110740 creator A5048915407 @default.
- W4328110740 date "2023-03-21" @default.
- W4328110740 modified "2023-10-14" @default.
- W4328110740 title "MFGFNet: A Multi-Scale Remote Sensing Change Detection Network Using the Global Filter in the Frequency Domain" @default.
- W4328110740 cites W2157026765 @default.
- W4328110740 cites W2165577558 @default.
- W4328110740 cites W2169966850 @default.
- W4328110740 cites W2577832105 @default.
- W4328110740 cites W2805152403 @default.
- W4328110740 cites W2896365540 @default.
- W4328110740 cites W2908320224 @default.
- W4328110740 cites W2908624219 @default.
- W4328110740 cites W2951991161 @default.
- W4328110740 cites W2963420686 @default.
- W4328110740 cites W2966542792 @default.
- W4328110740 cites W2984954051 @default.
- W4328110740 cites W3009942016 @default.
- W4328110740 cites W3027225766 @default.
- W4328110740 cites W3034771037 @default.
- W4328110740 cites W3036453075 @default.
- W4328110740 cites W3099503507 @default.
- W4328110740 cites W3104899156 @default.
- W4328110740 cites W3113081737 @default.
- W4328110740 cites W3131652207 @default.
- W4328110740 cites W3138516171 @default.
- W4328110740 cites W3141138843 @default.
- W4328110740 cites W3170841864 @default.
- W4328110740 cites W3184566187 @default.
- W4328110740 cites W3187748454 @default.
- W4328110740 cites W3214430396 @default.
- W4328110740 cites W4220936840 @default.
- W4328110740 cites W4288901840 @default.
- W4328110740 cites W4291670771 @default.
- W4328110740 cites W4292387496 @default.
- W4328110740 cites W4292825893 @default.
- W4328110740 cites W4312272867 @default.
- W4328110740 doi "https://doi.org/10.3390/rs15061682" @default.
- W4328110740 hasPublicationYear "2023" @default.
- W4328110740 type Work @default.
- W4328110740 citedByCount "1" @default.
- W4328110740 countsByYear W43281107402023 @default.
- W4328110740 crossrefType "journal-article" @default.
- W4328110740 hasAuthorship W4328110740A5021301663 @default.
- W4328110740 hasAuthorship W4328110740A5036584593 @default.
- W4328110740 hasAuthorship W4328110740A5039088967 @default.
- W4328110740 hasAuthorship W4328110740A5048915407 @default.
- W4328110740 hasBestOaLocation W43281107401 @default.
- W4328110740 hasConcept C102519508 @default.
- W4328110740 hasConcept C106131492 @default.
- W4328110740 hasConcept C115961682 @default.
- W4328110740 hasConcept C120665830 @default.
- W4328110740 hasConcept C121332964 @default.
- W4328110740 hasConcept C12713177 @default.
- W4328110740 hasConcept C134306372 @default.
- W4328110740 hasConcept C138885662 @default.
- W4328110740 hasConcept C153180895 @default.
- W4328110740 hasConcept C154945302 @default.
- W4328110740 hasConcept C158525013 @default.
- W4328110740 hasConcept C19118579 @default.
- W4328110740 hasConcept C192209626 @default.
- W4328110740 hasConcept C203595873 @default.
- W4328110740 hasConcept C205649164 @default.
- W4328110740 hasConcept C2776401178 @default.
- W4328110740 hasConcept C2778755073 @default.
- W4328110740 hasConcept C2781137444 @default.
- W4328110740 hasConcept C31972630 @default.
- W4328110740 hasConcept C33923547 @default.
- W4328110740 hasConcept C36503486 @default.
- W4328110740 hasConcept C41008148 @default.
- W4328110740 hasConcept C41895202 @default.
- W4328110740 hasConcept C58640448 @default.
- W4328110740 hasConcept C69744172 @default.
- W4328110740 hasConcept C81363708 @default.
- W4328110740 hasConceptScore W4328110740C102519508 @default.
- W4328110740 hasConceptScore W4328110740C106131492 @default.
- W4328110740 hasConceptScore W4328110740C115961682 @default.
- W4328110740 hasConceptScore W4328110740C120665830 @default.
- W4328110740 hasConceptScore W4328110740C121332964 @default.
- W4328110740 hasConceptScore W4328110740C12713177 @default.
- W4328110740 hasConceptScore W4328110740C134306372 @default.
- W4328110740 hasConceptScore W4328110740C138885662 @default.
- W4328110740 hasConceptScore W4328110740C153180895 @default.
- W4328110740 hasConceptScore W4328110740C154945302 @default.
- W4328110740 hasConceptScore W4328110740C158525013 @default.
- W4328110740 hasConceptScore W4328110740C19118579 @default.
- W4328110740 hasConceptScore W4328110740C192209626 @default.
- W4328110740 hasConceptScore W4328110740C203595873 @default.
- W4328110740 hasConceptScore W4328110740C205649164 @default.
- W4328110740 hasConceptScore W4328110740C2776401178 @default.
- W4328110740 hasConceptScore W4328110740C2778755073 @default.
- W4328110740 hasConceptScore W4328110740C2781137444 @default.
- W4328110740 hasConceptScore W4328110740C31972630 @default.
- W4328110740 hasConceptScore W4328110740C33923547 @default.