FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3190941789> ?p ?o ?g. }

• W3190941789 endingPage "112603" @default.
• W3190941789 startingPage "112603" @default.
• W3190941789 abstract "The aim of this paper is to map agricultural crops by classifying satellite image time series. Domain experts in agriculture work with crop type labels that are organised in a hierarchical tree structure, where coarse classes (like orchards) are subdivided into finer ones (like apples, pears, vines, etc.). We develop a crop classification method that exploits this expert knowledge and significantly improves the mapping of rare crop types. The three-level label hierarchy is encoded in a convolutional, recurrent neural network (convRNN), such that for each pixel the model predicts three labels at different level of granularity. This end-to-end trainable, hierarchical network architecture allows the model to learn joint feature representations of rare classes (e.g., apples, pears) at a coarser level (e.g., orchard), thereby boosting classification performance at the fine-grained level. Additionally, labelling at different granularity also makes it possible to adjust the output according to the classification scores; as coarser labels with high confidence are sometimes more useful for agricultural practice than fine-grained but very uncertain labels. We validate the proposed method on a new, large dataset that we make public. ZueriCrop covers an area of 50 km × 48 km in the Swiss cantons of Zurich and Thurgau with a total of 116′000 individual fields spanning 48 crop classes, and 28,000 (multi-temporal) image patches from Sentinel-2. We compare our proposed hierarchical convRNN model with several baselines, including methods designed for imbalanced class distributions. The hierarchical approach performs superior by at least 9.9 percentage points in F1-score." @default.
• W3190941789 created "2021-08-16" @default.
• W3190941789 creator A5005404030 @default.
• W3190941789 creator A5008566906 @default.
• W3190941789 creator A5033593467 @default.
• W3190941789 creator A5047745210 @default.
• W3190941789 creator A5049999878 @default.
• W3190941789 creator A5071121905 @default.
• W3190941789 creator A5078213725 @default.
• W3190941789 date "2021-10-01" @default.
• W3190941789 modified "2023-10-16" @default.
• W3190941789 title "Crop mapping from image time series: Deep learning with multi-scale label hierarchies" @default.
• W3190941789 cites W1963809378 @default.
• W3190941789 cites W1966672892 @default.
• W3190941789 cites W1973981085 @default.
• W3190941789 cites W1985505755 @default.
• W3190941789 cites W1986738039 @default.
• W3190941789 cites W2020708554 @default.
• W3190941789 cites W2030165874 @default.
• W3190941789 cites W2032729760 @default.
• W3190941789 cites W2037136693 @default.
• W3190941789 cites W2067049630 @default.
• W3190941789 cites W2077524583 @default.
• W3190941789 cites W2090151803 @default.
• W3190941789 cites W2095693034 @default.
• W3190941789 cites W2108358988 @default.
• W3190941789 cites W2118037698 @default.
• W3190941789 cites W2118978333 @default.
• W3190941789 cites W2136251662 @default.
• W3190941789 cites W2146500689 @default.
• W3190941789 cites W2148143831 @default.
• W3190941789 cites W2155939589 @default.
• W3190941789 cites W2171599506 @default.
• W3190941789 cites W2307094448 @default.
• W3190941789 cites W2756182389 @default.
• W3190941789 cites W2767953525 @default.
• W3190941789 cites W2798869704 @default.
• W3190941789 cites W2883026662 @default.
• W3190941789 cites W2903282641 @default.
• W3190941789 cites W2906848991 @default.
• W3190941789 cites W2913318911 @default.
• W3190941789 cites W2955034228 @default.
• W3190941789 cites W2955477134 @default.
• W3190941789 cites W2963131120 @default.
• W3190941789 cites W2963246338 @default.
• W3190941789 cites W2963910238 @default.
• W3190941789 cites W2974859516 @default.
• W3190941789 cites W2975225574 @default.
• W3190941789 cites W2981830988 @default.
• W3190941789 cites W3002710521 @default.
• W3190941789 cites W3006962608 @default.
• W3190941789 cites W3037496421 @default.
• W3190941789 cites W3104839310 @default.
• W3190941789 cites W3134677142 @default.
• W3190941789 doi "https://doi.org/10.1016/j.rse.2021.112603" @default.
• W3190941789 hasPublicationYear "2021" @default.
• W3190941789 type Work @default.
• W3190941789 sameAs 3190941789 @default.
• W3190941789 citedByCount "43" @default.
• W3190941789 countsByYear W31909417892021 @default.
• W3190941789 countsByYear W31909417892022 @default.
• W3190941789 countsByYear W31909417892023 @default.
• W3190941789 crossrefType "journal-article" @default.
• W3190941789 hasAuthorship W3190941789A5005404030 @default.
• W3190941789 hasAuthorship W3190941789A5008566906 @default.
• W3190941789 hasAuthorship W3190941789A5033593467 @default.
• W3190941789 hasAuthorship W3190941789A5047745210 @default.
• W3190941789 hasAuthorship W3190941789A5049999878 @default.
• W3190941789 hasAuthorship W3190941789A5071121905 @default.
• W3190941789 hasAuthorship W3190941789A5078213725 @default.
• W3190941789 hasBestOaLocation W31909417891 @default.
• W3190941789 hasConcept C111919701 @default.
• W3190941789 hasConcept C115961682 @default.
• W3190941789 hasConcept C119857082 @default.
• W3190941789 hasConcept C124101348 @default.
• W3190941789 hasConcept C138885662 @default.
• W3190941789 hasConcept C153180895 @default.
• W3190941789 hasConcept C154945302 @default.
• W3190941789 hasConcept C162324750 @default.
• W3190941789 hasConcept C177774035 @default.
• W3190941789 hasConcept C2776401178 @default.
• W3190941789 hasConcept C31170391 @default.
• W3190941789 hasConcept C34447519 @default.
• W3190941789 hasConcept C41008148 @default.
• W3190941789 hasConcept C41895202 @default.
• W3190941789 hasConcept C46686674 @default.
• W3190941789 hasConcept C75294576 @default.
• W3190941789 hasConcept C81363708 @default.
• W3190941789 hasConceptScore W3190941789C111919701 @default.
• W3190941789 hasConceptScore W3190941789C115961682 @default.
• W3190941789 hasConceptScore W3190941789C119857082 @default.
• W3190941789 hasConceptScore W3190941789C124101348 @default.
• W3190941789 hasConceptScore W3190941789C138885662 @default.
• W3190941789 hasConceptScore W3190941789C153180895 @default.
• W3190941789 hasConceptScore W3190941789C154945302 @default.
• W3190941789 hasConceptScore W3190941789C162324750 @default.
• W3190941789 hasConceptScore W3190941789C177774035 @default.
• W3190941789 hasConceptScore W3190941789C2776401178 @default.

• next