Matches in SemOpenAlex for { <https://semopenalex.org/work/W3106221618> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W3106221618 abstract "Recent advances in deep learning have made it possible to quantify urban metrics at fine resolution, and over large extents using street-level images. Here, we focus on measuring urban tree cover using Google Street View (GSV) images. First, we provide a small-scale labelled validation dataset and propose standard metrics to compare the performance of automated estimations of street tree cover using GSV. We apply state-of-the-art deep learning models, and compare their performance to a previously established benchmark of an unsupervised method. Our training procedure for deep learning models is novel; we utilize the abundance of openly available and similarly labelled street-level image datasets to pre-train our model. We then perform additional training on a small training dataset consisting of GSV images. We find that deep learning models significantly outperform the unsupervised benchmark method. Our semantic segmentation model increased mean intersection-over-union (IoU) from 44.10% to 60.42% relative to the unsupervised method and our end-to-end model decreased Mean Absolute Error from 10.04% to 4.67%. We also employ a recently developed method called gradient-weighted class activation map (Grad-CAM) to interpret the features learned by the end-to-end model. This technique confirms that the end-to-end model has accurately learned to identify tree cover area as key features for predicting percentage tree cover. Our paper provides an example of applying advanced deep learning techniques on a large-scale, geo-tagged and image-based dataset to efficiently estimate important urban metrics. The results demonstrate that deep learning models are highly accurate, can be interpretable, and can also be efficient in terms of data-labelling effort and computational resources." @default.
- W3106221618 created "2020-11-23" @default.
- W3106221618 creator A5042250944 @default.
- W3106221618 creator A5047846505 @default.
- W3106221618 creator A5053970487 @default.
- W3106221618 creator A5074760532 @default.
- W3106221618 date "2018-07-01" @default.
- W3106221618 modified "2023-10-13" @default.
- W3106221618 title "Treepedia 2.0: Applying Deep Learning for Large-Scale Quantification of Urban Tree Cover" @default.
- W3106221618 cites W1978338723 @default.
- W3106221618 cites W2036921154 @default.
- W3106221618 cites W2055971368 @default.
- W3106221618 cites W2067191022 @default.
- W3106221618 cites W2068241800 @default.
- W3106221618 cites W2104922698 @default.
- W3106221618 cites W2117539524 @default.
- W3106221618 cites W2176950688 @default.
- W3106221618 cites W2194775991 @default.
- W3106221618 cites W2340897893 @default.
- W3106221618 cites W2438072089 @default.
- W3106221618 cites W2560023338 @default.
- W3106221618 cites W2617647211 @default.
- W3106221618 cites W3103856189 @default.
- W3106221618 cites W4205747193 @default.
- W3106221618 cites W631895740 @default.
- W3106221618 cites W987751915 @default.
- W3106221618 doi "https://doi.org/10.1109/bigdatacongress.2018.00014" @default.
- W3106221618 hasPublicationYear "2018" @default.
- W3106221618 type Work @default.
- W3106221618 sameAs 3106221618 @default.
- W3106221618 citedByCount "23" @default.
- W3106221618 countsByYear W31062216182018 @default.
- W3106221618 countsByYear W31062216182019 @default.
- W3106221618 countsByYear W31062216182020 @default.
- W3106221618 countsByYear W31062216182021 @default.
- W3106221618 countsByYear W31062216182022 @default.
- W3106221618 countsByYear W31062216182023 @default.
- W3106221618 crossrefType "proceedings-article" @default.
- W3106221618 hasAuthorship W3106221618A5042250944 @default.
- W3106221618 hasAuthorship W3106221618A5047846505 @default.
- W3106221618 hasAuthorship W3106221618A5053970487 @default.
- W3106221618 hasAuthorship W3106221618A5074760532 @default.
- W3106221618 hasBestOaLocation W31062216182 @default.
- W3106221618 hasConcept C108583219 @default.
- W3106221618 hasConcept C113174947 @default.
- W3106221618 hasConcept C119857082 @default.
- W3106221618 hasConcept C134306372 @default.
- W3106221618 hasConcept C153180895 @default.
- W3106221618 hasConcept C154945302 @default.
- W3106221618 hasConcept C185798385 @default.
- W3106221618 hasConcept C205649164 @default.
- W3106221618 hasConcept C2778755073 @default.
- W3106221618 hasConcept C33923547 @default.
- W3106221618 hasConcept C41008148 @default.
- W3106221618 hasConcept C52622490 @default.
- W3106221618 hasConcept C58640448 @default.
- W3106221618 hasConcept C64543145 @default.
- W3106221618 hasConcept C8038995 @default.
- W3106221618 hasConcept C89600930 @default.
- W3106221618 hasConceptScore W3106221618C108583219 @default.
- W3106221618 hasConceptScore W3106221618C113174947 @default.
- W3106221618 hasConceptScore W3106221618C119857082 @default.
- W3106221618 hasConceptScore W3106221618C134306372 @default.
- W3106221618 hasConceptScore W3106221618C153180895 @default.
- W3106221618 hasConceptScore W3106221618C154945302 @default.
- W3106221618 hasConceptScore W3106221618C185798385 @default.
- W3106221618 hasConceptScore W3106221618C205649164 @default.
- W3106221618 hasConceptScore W3106221618C2778755073 @default.
- W3106221618 hasConceptScore W3106221618C33923547 @default.
- W3106221618 hasConceptScore W3106221618C41008148 @default.
- W3106221618 hasConceptScore W3106221618C52622490 @default.
- W3106221618 hasConceptScore W3106221618C58640448 @default.
- W3106221618 hasConceptScore W3106221618C64543145 @default.
- W3106221618 hasConceptScore W3106221618C8038995 @default.
- W3106221618 hasConceptScore W3106221618C89600930 @default.
- W3106221618 hasLocation W31062216181 @default.
- W3106221618 hasLocation W31062216182 @default.
- W3106221618 hasLocation W31062216183 @default.
- W3106221618 hasOpenAccess W3106221618 @default.
- W3106221618 hasPrimaryLocation W31062216181 @default.
- W3106221618 hasRelatedWork W2592385986 @default.
- W3106221618 hasRelatedWork W2597787948 @default.
- W3106221618 hasRelatedWork W2946016983 @default.
- W3106221618 hasRelatedWork W3123344745 @default.
- W3106221618 hasRelatedWork W3192794374 @default.
- W3106221618 hasRelatedWork W3208584567 @default.
- W3106221618 hasRelatedWork W4221031031 @default.
- W3106221618 hasRelatedWork W4246751904 @default.
- W3106221618 hasRelatedWork W4302303815 @default.
- W3106221618 hasRelatedWork W4319781722 @default.
- W3106221618 isParatext "false" @default.
- W3106221618 isRetracted "false" @default.
- W3106221618 magId "3106221618" @default.
- W3106221618 workType "article" @default.