Matches in SemOpenAlex for { <https://semopenalex.org/work/W3115878113> ?p ?o ?g. }
- W3115878113 endingPage "1800" @default.
- W3115878113 startingPage "1785" @default.
- W3115878113 abstract "Macroalgae are a fundamental component of coastal ecosystems and play a key role in shaping community structure and functioning. Macroalgae are currently threatened by diverse stressors, particularly climate change and invasive species, but they do not all respond in the same way to the stressors. Effective methods of collecting qualitative and quantitative information are essential to enable better, more efficient management of macroalgae. Acquisition of high-resolution images, in which macroalgae can be distinguished on the basis of their texture and colour, and the automated processing of these images are thus essential. Although ground images are useful, labelling is tedious. This study focuses on the semantic segmentation of five macroalgal species in high-resolution ground images taken in 0.5 × 0.5 m quadrats placed along an intertidal rocky shore at low tide. The target species, Bifurcaria bifurcata, Cystoseira tamariscifolia, Sargassum muticum, Sacchoriza polyschides and Codium spp., which predominate on intertidal shores, belong to different morpho-functional groups. An explanation of how to convert vector-labelled data to raster-labelled data for adaptation to Convolutional Neural Network (CNN) input is provided. Three CNNs (MobileNetV2, Resnet18, Xception) were compared, and ResNet18 yielded the highest accuracy (91.9%). The macroalgae were correctly segmented, and the main confusion occurred at the borders between different macroalgal species, a problem derived from labelling errors. In addition, the interior and exterior of the quadrats were correctly delimited by the CNNs. The results were obtained from only one hundred labelled images and the method can be performed on personal computers, without the need to use external servers. The proposed method helps automation of the labelling process." @default.
- W3115878113 created "2021-01-05" @default.
- W3115878113 creator A5013978713 @default.
- W3115878113 creator A5018450332 @default.
- W3115878113 creator A5020948539 @default.
- W3115878113 creator A5043726537 @default.
- W3115878113 creator A5068750080 @default.
- W3115878113 date "2020-12-20" @default.
- W3115878113 modified "2023-10-01" @default.
- W3115878113 title "Semantic segmentation of major macroalgae in coastal environments using high-resolution ground imagery and deep learning" @default.
- W3115878113 cites W1634471347 @default.
- W3115878113 cites W1963894231 @default.
- W3115878113 cites W1982121622 @default.
- W3115878113 cites W2013038450 @default.
- W3115878113 cites W2027248998 @default.
- W3115878113 cites W2027966871 @default.
- W3115878113 cites W2082044670 @default.
- W3115878113 cites W2090908656 @default.
- W3115878113 cites W2092855163 @default.
- W3115878113 cites W2100735135 @default.
- W3115878113 cites W2136758825 @default.
- W3115878113 cites W2168884338 @default.
- W3115878113 cites W2194775991 @default.
- W3115878113 cites W2322922525 @default.
- W3115878113 cites W2510978004 @default.
- W3115878113 cites W2531409750 @default.
- W3115878113 cites W2759938411 @default.
- W3115878113 cites W2765684918 @default.
- W3115878113 cites W2766659087 @default.
- W3115878113 cites W2774482877 @default.
- W3115878113 cites W2779864294 @default.
- W3115878113 cites W2792623257 @default.
- W3115878113 cites W2804043600 @default.
- W3115878113 cites W2876772800 @default.
- W3115878113 cites W2886075188 @default.
- W3115878113 cites W2888517496 @default.
- W3115878113 cites W2888766590 @default.
- W3115878113 cites W2898521778 @default.
- W3115878113 cites W2900355025 @default.
- W3115878113 cites W2904414252 @default.
- W3115878113 cites W2937996078 @default.
- W3115878113 cites W2945459718 @default.
- W3115878113 cites W2956013814 @default.
- W3115878113 cites W2959434432 @default.
- W3115878113 cites W2963163009 @default.
- W3115878113 cites W2964309882 @default.
- W3115878113 cites W2965633594 @default.
- W3115878113 cites W2973767015 @default.
- W3115878113 cites W2979429364 @default.
- W3115878113 cites W2980222335 @default.
- W3115878113 cites W2991100582 @default.
- W3115878113 cites W3003984144 @default.
- W3115878113 cites W3004976349 @default.
- W3115878113 doi "https://doi.org/10.1080/01431161.2020.1842543" @default.
- W3115878113 hasPublicationYear "2020" @default.
- W3115878113 type Work @default.
- W3115878113 sameAs 3115878113 @default.
- W3115878113 citedByCount "20" @default.
- W3115878113 countsByYear W31158781132021 @default.
- W3115878113 countsByYear W31158781132022 @default.
- W3115878113 countsByYear W31158781132023 @default.
- W3115878113 crossrefType "journal-article" @default.
- W3115878113 hasAuthorship W3115878113A5013978713 @default.
- W3115878113 hasAuthorship W3115878113A5018450332 @default.
- W3115878113 hasAuthorship W3115878113A5020948539 @default.
- W3115878113 hasAuthorship W3115878113A5043726537 @default.
- W3115878113 hasAuthorship W3115878113A5068750080 @default.
- W3115878113 hasBestOaLocation W31158781132 @default.
- W3115878113 hasConcept C107394435 @default.
- W3115878113 hasConcept C152382732 @default.
- W3115878113 hasConcept C154945302 @default.
- W3115878113 hasConcept C174580923 @default.
- W3115878113 hasConcept C18903297 @default.
- W3115878113 hasConcept C205649164 @default.
- W3115878113 hasConcept C2778091200 @default.
- W3115878113 hasConcept C2778102629 @default.
- W3115878113 hasConcept C41008148 @default.
- W3115878113 hasConcept C505870484 @default.
- W3115878113 hasConcept C54840010 @default.
- W3115878113 hasConcept C62649853 @default.
- W3115878113 hasConcept C81363708 @default.
- W3115878113 hasConcept C86803240 @default.
- W3115878113 hasConceptScore W3115878113C107394435 @default.
- W3115878113 hasConceptScore W3115878113C152382732 @default.
- W3115878113 hasConceptScore W3115878113C154945302 @default.
- W3115878113 hasConceptScore W3115878113C174580923 @default.
- W3115878113 hasConceptScore W3115878113C18903297 @default.
- W3115878113 hasConceptScore W3115878113C205649164 @default.
- W3115878113 hasConceptScore W3115878113C2778091200 @default.
- W3115878113 hasConceptScore W3115878113C2778102629 @default.
- W3115878113 hasConceptScore W3115878113C41008148 @default.
- W3115878113 hasConceptScore W3115878113C505870484 @default.
- W3115878113 hasConceptScore W3115878113C54840010 @default.
- W3115878113 hasConceptScore W3115878113C62649853 @default.
- W3115878113 hasConceptScore W3115878113C81363708 @default.
- W3115878113 hasConceptScore W3115878113C86803240 @default.
- W3115878113 hasFunder F4320337808 @default.
- W3115878113 hasIssue "5" @default.