Matches in SemOpenAlex for { <https://semopenalex.org/work/W3000696750> ?p ?o ?g. }
- W3000696750 endingPage "563" @default.
- W3000696750 startingPage "563" @default.
- W3000696750 abstract "This study proposes and evaluates five deep fully convolutional networks (FCNs) for the semantic segmentation of a single tree species: SegNet, U-Net, FC-DenseNet, and two DeepLabv3+ variants. The performance of the FCN designs is evaluated experimentally in terms of classification accuracy and computational load. We also verify the benefits of fully connected conditional random fields (CRFs) as a post-processing step to improve the segmentation maps. The analysis is conducted on a set of images captured by an RGB camera aboard a UAV flying over an urban area. The dataset also contains a mask that indicates the occurrence of an endangered species called Dipteryx alata Vogel, also known as cumbaru, taken as the species to be identified. The experimental analysis shows the effectiveness of each design and reports average overall accuracy ranging from 88.9% to 96.7%, an F1-score between 87.0% and 96.1%, and IoU from 77.1% to 92.5%. We also realize that CRF consistently improves the performance, but at a high computational cost." @default.
- W3000696750 created "2020-01-23" @default.
- W3000696750 creator A5002170017 @default.
- W3000696750 creator A5008084391 @default.
- W3000696750 creator A5010406637 @default.
- W3000696750 creator A5017880637 @default.
- W3000696750 creator A5055931859 @default.
- W3000696750 creator A5058090682 @default.
- W3000696750 creator A5067983564 @default.
- W3000696750 creator A5071340024 @default.
- W3000696750 creator A5076941451 @default.
- W3000696750 date "2020-01-20" @default.
- W3000696750 modified "2023-10-17" @default.
- W3000696750 title "Applying Fully Convolutional Architectures for Semantic Segmentation of a Single Tree Species in Urban Environment on High Resolution UAV Optical Imagery" @default.
- W3000696750 cites W1994940828 @default.
- W3000696750 cites W2006588449 @default.
- W3000696750 cites W2050520595 @default.
- W3000696750 cites W2055733088 @default.
- W3000696750 cites W2059862423 @default.
- W3000696750 cites W2063396028 @default.
- W3000696750 cites W2068624850 @default.
- W3000696750 cites W2074464158 @default.
- W3000696750 cites W2089212648 @default.
- W3000696750 cites W2109191549 @default.
- W3000696750 cites W2109445997 @default.
- W3000696750 cites W2124624125 @default.
- W3000696750 cites W2184923025 @default.
- W3000696750 cites W2308318555 @default.
- W3000696750 cites W2342299051 @default.
- W3000696750 cites W2412782625 @default.
- W3000696750 cites W2418346537 @default.
- W3000696750 cites W2515306179 @default.
- W3000696750 cites W2565950292 @default.
- W3000696750 cites W2618943282 @default.
- W3000696750 cites W2770340534 @default.
- W3000696750 cites W2778539913 @default.
- W3000696750 cites W2804532080 @default.
- W3000696750 cites W2902190145 @default.
- W3000696750 cites W2904280379 @default.
- W3000696750 cites W2911027460 @default.
- W3000696750 cites W2921499963 @default.
- W3000696750 cites W2952142982 @default.
- W3000696750 cites W2963923251 @default.
- W3000696750 cites W2965034661 @default.
- W3000696750 cites W2967268202 @default.
- W3000696750 cites W2969394118 @default.
- W3000696750 cites W2990265654 @default.
- W3000696750 doi "https://doi.org/10.3390/s20020563" @default.
- W3000696750 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7014541" @default.
- W3000696750 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31968589" @default.
- W3000696750 hasPublicationYear "2020" @default.
- W3000696750 type Work @default.
- W3000696750 sameAs 3000696750 @default.
- W3000696750 citedByCount "64" @default.
- W3000696750 countsByYear W30006967502020 @default.
- W3000696750 countsByYear W30006967502021 @default.
- W3000696750 countsByYear W30006967502022 @default.
- W3000696750 countsByYear W30006967502023 @default.
- W3000696750 crossrefType "journal-article" @default.
- W3000696750 hasAuthorship W3000696750A5002170017 @default.
- W3000696750 hasAuthorship W3000696750A5008084391 @default.
- W3000696750 hasAuthorship W3000696750A5010406637 @default.
- W3000696750 hasAuthorship W3000696750A5017880637 @default.
- W3000696750 hasAuthorship W3000696750A5055931859 @default.
- W3000696750 hasAuthorship W3000696750A5058090682 @default.
- W3000696750 hasAuthorship W3000696750A5067983564 @default.
- W3000696750 hasAuthorship W3000696750A5071340024 @default.
- W3000696750 hasAuthorship W3000696750A5076941451 @default.
- W3000696750 hasBestOaLocation W30006967501 @default.
- W3000696750 hasConcept C108583219 @default.
- W3000696750 hasConcept C113174947 @default.
- W3000696750 hasConcept C115051666 @default.
- W3000696750 hasConcept C124504099 @default.
- W3000696750 hasConcept C134306372 @default.
- W3000696750 hasConcept C152565575 @default.
- W3000696750 hasConcept C153180895 @default.
- W3000696750 hasConcept C154945302 @default.
- W3000696750 hasConcept C169258074 @default.
- W3000696750 hasConcept C177264268 @default.
- W3000696750 hasConcept C199360897 @default.
- W3000696750 hasConcept C205649164 @default.
- W3000696750 hasConcept C2775953691 @default.
- W3000696750 hasConcept C31972630 @default.
- W3000696750 hasConcept C33923547 @default.
- W3000696750 hasConcept C41008148 @default.
- W3000696750 hasConcept C62649853 @default.
- W3000696750 hasConcept C76155785 @default.
- W3000696750 hasConcept C81363708 @default.
- W3000696750 hasConcept C82990744 @default.
- W3000696750 hasConcept C89600930 @default.
- W3000696750 hasConceptScore W3000696750C108583219 @default.
- W3000696750 hasConceptScore W3000696750C113174947 @default.
- W3000696750 hasConceptScore W3000696750C115051666 @default.
- W3000696750 hasConceptScore W3000696750C124504099 @default.
- W3000696750 hasConceptScore W3000696750C134306372 @default.
- W3000696750 hasConceptScore W3000696750C152565575 @default.
- W3000696750 hasConceptScore W3000696750C153180895 @default.
- W3000696750 hasConceptScore W3000696750C154945302 @default.