Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382138813> ?p ?o ?g. }
- W4382138813 endingPage "78" @default.
- W4382138813 startingPage "66" @default.
- W4382138813 abstract "In high-resolution remote sensing images, road scale diversity and occlusions caused by shadows, buildings, and vegetation often pose challenges for road extraction. Currently, end-to-end models constructed using deep convolutional neural networks are widely used in road extraction and have significantly improved the accuracy of this task. However, the connectivity and completeness of their results require improvement. This paper proposes a dual task-driven deep convolutional neural network constructed by combining road shape patterns and scale differences. The mainline task is road-surface segmentation, the encoder of which employs residual convolution for feature extraction. The decoder comprises a multi-scale and multi-direction strip convolution module, the output of which is the final extraction result. The splitting task is road centerline extraction, the input features of which come from the coding layer of the road-surface segmentation branches. The intermediate features are incorporated into the decoder of the road-surface segmentation branches, to fully exploit the road centerline and thus improve the road-surface segmentation result connectivity. Implementation of the proposed method on the CHN6-CUG and DeepGlobe datasets reveals superior performance to comparative methods as regards quantitative evaluation metrics; evident advantages for road coverings, road intersections, and low-scale roads; greater model portability; and better small-sample learning capability." @default.
- W4382138813 created "2023-06-27" @default.
- W4382138813 creator A5000974487 @default.
- W4382138813 creator A5041095541 @default.
- W4382138813 creator A5060969271 @default.
- W4382138813 creator A5084526647 @default.
- W4382138813 creator A5086936523 @default.
- W4382138813 date "2023-01-01" @default.
- W4382138813 modified "2023-10-14" @default.
- W4382138813 title "Dual-Task Network for Road Extraction From High-Resolution Remote Sensing Images" @default.
- W4382138813 cites W1901129140 @default.
- W4382138813 cites W1903029394 @default.
- W4382138813 cites W2020436006 @default.
- W4382138813 cites W2093680168 @default.
- W4382138813 cites W2108598243 @default.
- W4382138813 cites W2114268578 @default.
- W4382138813 cites W2119082135 @default.
- W4382138813 cites W2138317821 @default.
- W4382138813 cites W2191308554 @default.
- W4382138813 cites W2194775991 @default.
- W4382138813 cites W2244429148 @default.
- W4382138813 cites W2412782625 @default.
- W4382138813 cites W2484161688 @default.
- W4382138813 cites W2607333215 @default.
- W4382138813 cites W2774320778 @default.
- W4382138813 cites W2798925380 @default.
- W4382138813 cites W2804199516 @default.
- W4382138813 cites W2884561390 @default.
- W4382138813 cites W2893801697 @default.
- W4382138813 cites W2898504016 @default.
- W4382138813 cites W2928165649 @default.
- W4382138813 cites W2943295486 @default.
- W4382138813 cites W2943898693 @default.
- W4382138813 cites W2963091558 @default.
- W4382138813 cites W2963270775 @default.
- W4382138813 cites W2963881378 @default.
- W4382138813 cites W2964309882 @default.
- W4382138813 cites W2975194617 @default.
- W4382138813 cites W2988288682 @default.
- W4382138813 cites W2997156230 @default.
- W4382138813 cites W3024167159 @default.
- W4382138813 cites W3025884272 @default.
- W4382138813 cites W3081791696 @default.
- W4382138813 cites W3103263155 @default.
- W4382138813 cites W3121619677 @default.
- W4382138813 cites W3134927667 @default.
- W4382138813 cites W3150573203 @default.
- W4382138813 cites W3152984827 @default.
- W4382138813 cites W3203699578 @default.
- W4382138813 cites W3205484198 @default.
- W4382138813 cites W3214248441 @default.
- W4382138813 cites W4221145217 @default.
- W4382138813 cites W4226445372 @default.
- W4382138813 cites W4282967568 @default.
- W4382138813 cites W4295936571 @default.
- W4382138813 cites W4297478639 @default.
- W4382138813 cites W4297963538 @default.
- W4382138813 cites W4308720144 @default.
- W4382138813 cites W4313201808 @default.
- W4382138813 doi "https://doi.org/10.1109/jstars.2023.3289217" @default.
- W4382138813 hasPublicationYear "2023" @default.
- W4382138813 type Work @default.
- W4382138813 citedByCount "0" @default.
- W4382138813 crossrefType "journal-article" @default.
- W4382138813 hasAuthorship W4382138813A5000974487 @default.
- W4382138813 hasAuthorship W4382138813A5041095541 @default.
- W4382138813 hasAuthorship W4382138813A5060969271 @default.
- W4382138813 hasAuthorship W4382138813A5084526647 @default.
- W4382138813 hasAuthorship W4382138813A5086936523 @default.
- W4382138813 hasBestOaLocation W43821388131 @default.
- W4382138813 hasConcept C127413603 @default.
- W4382138813 hasConcept C147176958 @default.
- W4382138813 hasConcept C153180895 @default.
- W4382138813 hasConcept C154945302 @default.
- W4382138813 hasConcept C205649164 @default.
- W4382138813 hasConcept C2780042925 @default.
- W4382138813 hasConcept C31972630 @default.
- W4382138813 hasConcept C41008148 @default.
- W4382138813 hasConcept C45347329 @default.
- W4382138813 hasConcept C50644808 @default.
- W4382138813 hasConcept C52622490 @default.
- W4382138813 hasConcept C62649853 @default.
- W4382138813 hasConcept C81363708 @default.
- W4382138813 hasConcept C89600930 @default.
- W4382138813 hasConceptScore W4382138813C127413603 @default.
- W4382138813 hasConceptScore W4382138813C147176958 @default.
- W4382138813 hasConceptScore W4382138813C153180895 @default.
- W4382138813 hasConceptScore W4382138813C154945302 @default.
- W4382138813 hasConceptScore W4382138813C205649164 @default.
- W4382138813 hasConceptScore W4382138813C2780042925 @default.
- W4382138813 hasConceptScore W4382138813C31972630 @default.
- W4382138813 hasConceptScore W4382138813C41008148 @default.
- W4382138813 hasConceptScore W4382138813C45347329 @default.
- W4382138813 hasConceptScore W4382138813C50644808 @default.
- W4382138813 hasConceptScore W4382138813C52622490 @default.
- W4382138813 hasConceptScore W4382138813C62649853 @default.
- W4382138813 hasConceptScore W4382138813C81363708 @default.
- W4382138813 hasConceptScore W4382138813C89600930 @default.