Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950372006> ?p ?o ?g. }
- W2950372006 abstract "We present a novel weed segmentation and mapping framework that processes multispectral images obtained from an unmanned aerial vehicle (UAV) using a deep neural network (DNN). Most studies on crop/weed semantic segmentation only consider single images for processing and classification. Images taken by UAVs often cover only a few hundred square meters with either color only or color and near-infrared (NIR) channels. Computing a single large and accurate vegetation map (e.g., crop/weed) using a DNN is non-trivial due to difficulties arising from: (1) limited ground sample distances (GSDs) in high-altitude datasets, (2) sacrificed resolution resulting from downsampling high-fidelity images, and (3) multispectral image alignment. To address these issues, we adopt a stand sliding window approach that operates on only small portions of multispectral orthomosaic maps (tiles), which are channel-wise aligned and calibrated radiometrically across the entire map. We define the tile size to be the same as that of the DNN input to avoid resolution loss. Compared to our baseline model (i.e., SegNet with 3 channel RGB inputs) yielding an area under the curve (AUC) of [background=0.607, crop=0.681, weed=0.576], our proposed model with 9 input channels achieves [0.839, 0.863, 0.782]. Additionally, we provide an extensive analysis of 20 trained models, both qualitatively and quantitatively, in order to evaluate the effects of varying input channels and tunable network hyperparameters. Furthermore, we release a large sugar beet/weed aerial dataset with expertly guided annotations for further research in the fields of remote sensing, precision agriculture, and agricultural robotics." @default.
- W2950372006 created "2019-06-27" @default.
- W2950372006 creator A5004221958 @default.
- W2950372006 creator A5011166267 @default.
- W2950372006 creator A5033593467 @default.
- W2950372006 creator A5041969138 @default.
- W2950372006 creator A5065532121 @default.
- W2950372006 creator A5072802898 @default.
- W2950372006 creator A5079471643 @default.
- W2950372006 creator A5081047560 @default.
- W2950372006 creator A5082343972 @default.
- W2950372006 creator A5083003222 @default.
- W2950372006 date "2018-07-31" @default.
- W2950372006 modified "2023-09-30" @default.
- W2950372006 title "WeedMap: A large-scale semantic weed mapping framework using aerial multispectral imaging and deep neural network for precision farming" @default.
- W2950372006 cites W1518917059 @default.
- W2950372006 cites W1523762189 @default.
- W2950372006 cites W1594573182 @default.
- W2950372006 cites W1686810756 @default.
- W2950372006 cites W1901129140 @default.
- W2950372006 cites W1903029394 @default.
- W2950372006 cites W1905829557 @default.
- W2950372006 cites W2074464158 @default.
- W2950372006 cites W2091695913 @default.
- W2950372006 cites W2102605133 @default.
- W2950372006 cites W2156598602 @default.
- W2950372006 cites W2183341477 @default.
- W2950372006 cites W2353457699 @default.
- W2950372006 cites W2419448466 @default.
- W2950372006 cites W2586545389 @default.
- W2950372006 cites W2587218622 @default.
- W2950372006 cites W2609077090 @default.
- W2950372006 cites W2624423843 @default.
- W2950372006 cites W2625071945 @default.
- W2950372006 cites W2746411854 @default.
- W2950372006 cites W2759532730 @default.
- W2950372006 cites W2760340275 @default.
- W2950372006 cites W2766710466 @default.
- W2950372006 cites W2771162534 @default.
- W2950372006 cites W2775795276 @default.
- W2950372006 cites W2782347622 @default.
- W2950372006 cites W2790979755 @default.
- W2950372006 cites W2792247930 @default.
- W2950372006 cites W2949086864 @default.
- W2950372006 cites W2952865063 @default.
- W2950372006 cites W2962782553 @default.
- W2950372006 cites W2963108767 @default.
- W2950372006 cites W2963881378 @default.
- W2950372006 doi "https://doi.org/10.48550/arxiv.1808.00100" @default.
- W2950372006 hasPublicationYear "2018" @default.
- W2950372006 type Work @default.
- W2950372006 sameAs 2950372006 @default.
- W2950372006 citedByCount "0" @default.
- W2950372006 crossrefType "posted-content" @default.
- W2950372006 hasAuthorship W2950372006A5004221958 @default.
- W2950372006 hasAuthorship W2950372006A5011166267 @default.
- W2950372006 hasAuthorship W2950372006A5033593467 @default.
- W2950372006 hasAuthorship W2950372006A5041969138 @default.
- W2950372006 hasAuthorship W2950372006A5065532121 @default.
- W2950372006 hasAuthorship W2950372006A5072802898 @default.
- W2950372006 hasAuthorship W2950372006A5079471643 @default.
- W2950372006 hasAuthorship W2950372006A5081047560 @default.
- W2950372006 hasAuthorship W2950372006A5082343972 @default.
- W2950372006 hasAuthorship W2950372006A5083003222 @default.
- W2950372006 hasBestOaLocation W29503720061 @default.
- W2950372006 hasConcept C118518473 @default.
- W2950372006 hasConcept C120217122 @default.
- W2950372006 hasConcept C127162648 @default.
- W2950372006 hasConcept C153180895 @default.
- W2950372006 hasConcept C154945302 @default.
- W2950372006 hasConcept C160633673 @default.
- W2950372006 hasConcept C166957645 @default.
- W2950372006 hasConcept C173163844 @default.
- W2950372006 hasConcept C197513456 @default.
- W2950372006 hasConcept C205372480 @default.
- W2950372006 hasConcept C205649164 @default.
- W2950372006 hasConcept C2775891814 @default.
- W2950372006 hasConcept C31258907 @default.
- W2950372006 hasConcept C31972630 @default.
- W2950372006 hasConcept C41008148 @default.
- W2950372006 hasConcept C50644808 @default.
- W2950372006 hasConcept C62649853 @default.
- W2950372006 hasConcept C6557445 @default.
- W2950372006 hasConcept C81363708 @default.
- W2950372006 hasConcept C82789328 @default.
- W2950372006 hasConcept C82990744 @default.
- W2950372006 hasConcept C86803240 @default.
- W2950372006 hasConceptScore W2950372006C118518473 @default.
- W2950372006 hasConceptScore W2950372006C120217122 @default.
- W2950372006 hasConceptScore W2950372006C127162648 @default.
- W2950372006 hasConceptScore W2950372006C153180895 @default.
- W2950372006 hasConceptScore W2950372006C154945302 @default.
- W2950372006 hasConceptScore W2950372006C160633673 @default.
- W2950372006 hasConceptScore W2950372006C166957645 @default.
- W2950372006 hasConceptScore W2950372006C173163844 @default.
- W2950372006 hasConceptScore W2950372006C197513456 @default.
- W2950372006 hasConceptScore W2950372006C205372480 @default.
- W2950372006 hasConceptScore W2950372006C205649164 @default.
- W2950372006 hasConceptScore W2950372006C2775891814 @default.
- W2950372006 hasConceptScore W2950372006C31258907 @default.