Matches in SemOpenAlex for { <https://semopenalex.org/work/W3015167329> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3015167329 endingPage "1099" @default.
- W3015167329 startingPage "1099" @default.
- W3015167329 abstract "Change detection (CD) networks based on supervised learning have been used in diverse CD tasks. However, such supervised CD networks require a large amount of data and only use information from current images. In addition, it is time consuming to manually acquire the ground truth data for newly obtained images. Here, we proposed a novel method for CD in case of a lack of training data in an area near by another one with the available ground truth data. The proposed method automatically entails generating training data and fine-tuning the CD network. To detect changes in target images without ground truth data, the difference images were generated using spectral similarity measure, and the training data were selected via fuzzy c-means clustering. Recurrent fully convolutional networks with multiscale three-dimensional filters were used to extract objects of various sizes from unmanned aerial vehicle (UAV) images. The CD network was pre-trained on labeled source domain data; then, the network was fine-tuned on target images using generated training data. Two further CD networks were trained with a combined weighted loss function. The training data in the target domain were iteratively updated using he prediction map of the CD network. Experiments on two hyperspectral UAV datasets confirmed that the proposed method is capable of transferring change rules and improving CD results based on training data extracted in an unsupervised way." @default.
- W3015167329 created "2020-04-10" @default.
- W3015167329 creator A5076998023 @default.
- W3015167329 creator A5082613258 @default.
- W3015167329 date "2020-03-30" @default.
- W3015167329 modified "2023-10-06" @default.
- W3015167329 title "Transfer Change Rules from Recurrent Fully Convolutional Networks for Hyperspectral Unmanned Aerial Vehicle Images without Ground Truth Data" @default.
- W3015167329 cites W1965038887 @default.
- W3015167329 cites W1970475948 @default.
- W3015167329 cites W1990368529 @default.
- W3015167329 cites W1990784258 @default.
- W3015167329 cites W2008265903 @default.
- W3015167329 cites W2009539575 @default.
- W3015167329 cites W2010319424 @default.
- W3015167329 cites W2013421447 @default.
- W3015167329 cites W2033676720 @default.
- W3015167329 cites W2048104909 @default.
- W3015167329 cites W2085997253 @default.
- W3015167329 cites W2094304765 @default.
- W3015167329 cites W2104374858 @default.
- W3015167329 cites W2221448138 @default.
- W3015167329 cites W2419285013 @default.
- W3015167329 cites W2431738724 @default.
- W3015167329 cites W2462460776 @default.
- W3015167329 cites W2572303978 @default.
- W3015167329 cites W2765366036 @default.
- W3015167329 cites W2766049824 @default.
- W3015167329 cites W2789923217 @default.
- W3015167329 cites W2792827505 @default.
- W3015167329 cites W2811044316 @default.
- W3015167329 cites W2900587135 @default.
- W3015167329 cites W2901221751 @default.
- W3015167329 cites W2931139621 @default.
- W3015167329 cites W2942855565 @default.
- W3015167329 cites W2944063455 @default.
- W3015167329 cites W2951267175 @default.
- W3015167329 cites W2963183385 @default.
- W3015167329 cites W2997043451 @default.
- W3015167329 cites W3000764263 @default.
- W3015167329 cites W3009755915 @default.
- W3015167329 cites W3102955142 @default.
- W3015167329 cites W3103590434 @default.
- W3015167329 doi "https://doi.org/10.3390/rs12071099" @default.
- W3015167329 hasPublicationYear "2020" @default.
- W3015167329 type Work @default.
- W3015167329 sameAs 3015167329 @default.
- W3015167329 citedByCount "8" @default.
- W3015167329 countsByYear W30151673292019 @default.
- W3015167329 countsByYear W30151673292020 @default.
- W3015167329 countsByYear W30151673292021 @default.
- W3015167329 countsByYear W30151673292022 @default.
- W3015167329 countsByYear W30151673292023 @default.
- W3015167329 crossrefType "journal-article" @default.
- W3015167329 hasAuthorship W3015167329A5076998023 @default.
- W3015167329 hasAuthorship W3015167329A5082613258 @default.
- W3015167329 hasBestOaLocation W30151673291 @default.
- W3015167329 hasConcept C124101348 @default.
- W3015167329 hasConcept C146849305 @default.
- W3015167329 hasConcept C153180895 @default.
- W3015167329 hasConcept C154945302 @default.
- W3015167329 hasConcept C159078339 @default.
- W3015167329 hasConcept C41008148 @default.
- W3015167329 hasConcept C73555534 @default.
- W3015167329 hasConceptScore W3015167329C124101348 @default.
- W3015167329 hasConceptScore W3015167329C146849305 @default.
- W3015167329 hasConceptScore W3015167329C153180895 @default.
- W3015167329 hasConceptScore W3015167329C154945302 @default.
- W3015167329 hasConceptScore W3015167329C159078339 @default.
- W3015167329 hasConceptScore W3015167329C41008148 @default.
- W3015167329 hasConceptScore W3015167329C73555534 @default.
- W3015167329 hasFunder F4320322120 @default.
- W3015167329 hasIssue "7" @default.
- W3015167329 hasLocation W30151673291 @default.
- W3015167329 hasOpenAccess W3015167329 @default.
- W3015167329 hasPrimaryLocation W30151673291 @default.
- W3015167329 hasRelatedWork W1869808405 @default.
- W3015167329 hasRelatedWork W1966869234 @default.
- W3015167329 hasRelatedWork W2028628118 @default.
- W3015167329 hasRelatedWork W2031007444 @default.
- W3015167329 hasRelatedWork W2139206670 @default.
- W3015167329 hasRelatedWork W2783789044 @default.
- W3015167329 hasRelatedWork W2920797426 @default.
- W3015167329 hasRelatedWork W3173596272 @default.
- W3015167329 hasRelatedWork W3211035526 @default.
- W3015167329 hasRelatedWork W4291701050 @default.
- W3015167329 hasVolume "12" @default.
- W3015167329 isParatext "false" @default.
- W3015167329 isRetracted "false" @default.
- W3015167329 magId "3015167329" @default.
- W3015167329 workType "article" @default.