Matches in SemOpenAlex for { <https://semopenalex.org/work/W2895832001> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2895832001 abstract "Road extraction from aerial and satellite image is one of complex and challenging tasks in remote sensing field. The task is required for a wide range of application, such as autonomous driving, urban planning and automatic mapping for GIS data collection. Most approaches cast the road extraction as image segmentation and use thinning algorithm to get road centerline. However, these methods can easily produce spurs around the true centerline which affects the accuracy of road centerline extraction and lacks the topology of road network. In this paper, we propose a novel method to directly extract accurate road centerline from aerial images and construct the topology of the road network. First, an end-to-end regression network based on convolutional neural network is designed to learn and predict a road centerline confidence map which is a 2D representation of the probability of each pixel to be on the road centerline. Our network combines multi-scale and multi-level feature information to produce refined confidence map. Then a canny-like non-maximum suppression is followed to attain accurate road centerline. Finally, we use spoke wheel to find the road direction of the initialized road center point and take advantage of road tracking to construct the topology of road network. The results on the Massachusetts Road dataset shows an significant improvement on the accuracy of location of extracted road centerline." @default.
- W2895832001 created "2018-10-26" @default.
- W2895832001 creator A5004788238 @default.
- W2895832001 creator A5022461898 @default.
- W2895832001 creator A5032507421 @default.
- W2895832001 date "2018-08-01" @default.
- W2895832001 modified "2023-09-27" @default.
- W2895832001 title "End-to-End Road Centerline Extraction via Learning a Confidence Map" @default.
- W2895832001 cites W1686810756 @default.
- W2895832001 cites W1987365705 @default.
- W2895832001 cites W2000666616 @default.
- W2895832001 cites W2052516389 @default.
- W2895832001 cites W2102048636 @default.
- W2895832001 cites W2114010427 @default.
- W2895832001 cites W2128906900 @default.
- W2895832001 cites W2416190443 @default.
- W2895832001 cites W2593886839 @default.
- W2895832001 cites W845365781 @default.
- W2895832001 cites W203741292 @default.
- W2895832001 doi "https://doi.org/10.1109/prrs.2018.8486185" @default.
- W2895832001 hasPublicationYear "2018" @default.
- W2895832001 type Work @default.
- W2895832001 sameAs 2895832001 @default.
- W2895832001 citedByCount "2" @default.
- W2895832001 countsByYear W28958320012019 @default.
- W2895832001 crossrefType "proceedings-article" @default.
- W2895832001 hasAuthorship W2895832001A5004788238 @default.
- W2895832001 hasAuthorship W2895832001A5022461898 @default.
- W2895832001 hasAuthorship W2895832001A5032507421 @default.
- W2895832001 hasConcept C115961682 @default.
- W2895832001 hasConcept C124101348 @default.
- W2895832001 hasConcept C127413603 @default.
- W2895832001 hasConcept C146978453 @default.
- W2895832001 hasConcept C154945302 @default.
- W2895832001 hasConcept C199360897 @default.
- W2895832001 hasConcept C201995342 @default.
- W2895832001 hasConcept C204323151 @default.
- W2895832001 hasConcept C2776429412 @default.
- W2895832001 hasConcept C2780451532 @default.
- W2895832001 hasConcept C2780801425 @default.
- W2895832001 hasConcept C31972630 @default.
- W2895832001 hasConcept C41008148 @default.
- W2895832001 hasConcept C52622490 @default.
- W2895832001 hasConcept C81363708 @default.
- W2895832001 hasConcept C89600930 @default.
- W2895832001 hasConceptScore W2895832001C115961682 @default.
- W2895832001 hasConceptScore W2895832001C124101348 @default.
- W2895832001 hasConceptScore W2895832001C127413603 @default.
- W2895832001 hasConceptScore W2895832001C146978453 @default.
- W2895832001 hasConceptScore W2895832001C154945302 @default.
- W2895832001 hasConceptScore W2895832001C199360897 @default.
- W2895832001 hasConceptScore W2895832001C201995342 @default.
- W2895832001 hasConceptScore W2895832001C204323151 @default.
- W2895832001 hasConceptScore W2895832001C2776429412 @default.
- W2895832001 hasConceptScore W2895832001C2780451532 @default.
- W2895832001 hasConceptScore W2895832001C2780801425 @default.
- W2895832001 hasConceptScore W2895832001C31972630 @default.
- W2895832001 hasConceptScore W2895832001C41008148 @default.
- W2895832001 hasConceptScore W2895832001C52622490 @default.
- W2895832001 hasConceptScore W2895832001C81363708 @default.
- W2895832001 hasConceptScore W2895832001C89600930 @default.
- W2895832001 hasLocation W28958320011 @default.
- W2895832001 hasOpenAccess W2895832001 @default.
- W2895832001 hasPrimaryLocation W28958320011 @default.
- W2895832001 hasRelatedWork W2008348169 @default.
- W2895832001 hasRelatedWork W2080425500 @default.
- W2895832001 hasRelatedWork W2110554513 @default.
- W2895832001 hasRelatedWork W2415731916 @default.
- W2895832001 hasRelatedWork W2534909612 @default.
- W2895832001 hasRelatedWork W2807025966 @default.
- W2895832001 hasRelatedWork W2887315704 @default.
- W2895832001 hasRelatedWork W2971721951 @default.
- W2895832001 hasRelatedWork W4290028944 @default.
- W2895832001 hasRelatedWork W2039030422 @default.
- W2895832001 isParatext "false" @default.
- W2895832001 isRetracted "false" @default.
- W2895832001 magId "2895832001" @default.
- W2895832001 workType "article" @default.