Matches in SemOpenAlex for { <https://semopenalex.org/work/W3025656547> ?p ?o ?g. }
- W3025656547 endingPage "105391" @default.
- W3025656547 startingPage "105391" @default.
- W3025656547 abstract "Abstract Prior livestock research provides evidence for the importance of accurate detection of pig positions and postures for better understanding animal welfare. Position and posture detection can be accomplished by machine vision systems. However, current machine vision systems require rigid setups of fixed vertical lighting, vertical top-view camera perspectives or complex camera systems, which hinder their adoption in practice. Moreover, existing detection systems focus on specific pen contexts and may be difficult to apply in other livestock facilities. Our main contribution is twofold: First, we design a deep learning system for position and posture detection that only requires standard 2D camera imaging with no adaptations to the application setting. This deep learning system applies the state-of-the-art Faster R-CNN object detection pipeline and the state-of-the-art Neural Architecture Search (NAS) base network for feature extraction. Second, we provide a labelled open access dataset with 7277 human-made annotations from 21 standard 2D cameras, covering 31 different one-hour long video recordings and 18 different pens to train and test the approach under realistic conditions. On unseen pens under similar experimental conditions with sufficient similar training images of pig fattening, the deep learning system detects pig position with an Average Precision (AP) of 87.4%, and pig position and posture with a mean Average Precision (mAP) of 80.2%. Given different and more difficult experimental conditions of pig rearing with no or little similar images in the training set, an AP of over 67.7% was achieved for position detection. However, detecting the position and posture achieved a mAP between 44.8% and 58.8% only. Furthermore, we demonstrate exemplary applications that can aid pen design by visualizing where pigs are lying and how their lying behavior changes through the day. Finally, we contribute open data that can be used for further studies, replication, and pig position detection applications." @default.
- W3025656547 created "2020-05-21" @default.
- W3025656547 creator A5016291304 @default.
- W3025656547 creator A5019850639 @default.
- W3025656547 creator A5027607952 @default.
- W3025656547 creator A5064322543 @default.
- W3025656547 creator A5067995345 @default.
- W3025656547 date "2020-07-01" @default.
- W3025656547 modified "2023-10-17" @default.
- W3025656547 title "Automatically detecting pig position and posture by 2D camera imaging and deep learning" @default.
- W3025656547 cites W1861492603 @default.
- W3025656547 cites W1958294650 @default.
- W3025656547 cites W1968561415 @default.
- W3025656547 cites W1972780278 @default.
- W3025656547 cites W2009070949 @default.
- W3025656547 cites W2016210396 @default.
- W3025656547 cites W2020611861 @default.
- W3025656547 cites W2029988511 @default.
- W3025656547 cites W2031489346 @default.
- W3025656547 cites W2037227137 @default.
- W3025656547 cites W2047495463 @default.
- W3025656547 cites W2076063813 @default.
- W3025656547 cites W2083978531 @default.
- W3025656547 cites W2087352304 @default.
- W3025656547 cites W2091991228 @default.
- W3025656547 cites W210617966 @default.
- W3025656547 cites W2149034145 @default.
- W3025656547 cites W2152918182 @default.
- W3025656547 cites W2157044442 @default.
- W3025656547 cites W2295239695 @default.
- W3025656547 cites W2343728412 @default.
- W3025656547 cites W2479887945 @default.
- W3025656547 cites W2509451677 @default.
- W3025656547 cites W2527150209 @default.
- W3025656547 cites W2584728594 @default.
- W3025656547 cites W2616251437 @default.
- W3025656547 cites W2724679680 @default.
- W3025656547 cites W2771389134 @default.
- W3025656547 cites W2775111183 @default.
- W3025656547 cites W2775823666 @default.
- W3025656547 cites W2790979755 @default.
- W3025656547 cites W2791489312 @default.
- W3025656547 cites W2792559640 @default.
- W3025656547 cites W2794696101 @default.
- W3025656547 cites W2794876710 @default.
- W3025656547 cites W2807360606 @default.
- W3025656547 cites W2845797600 @default.
- W3025656547 cites W2899609705 @default.
- W3025656547 cites W2919115771 @default.
- W3025656547 cites W639708223 @default.
- W3025656547 doi "https://doi.org/10.1016/j.compag.2020.105391" @default.
- W3025656547 hasPublicationYear "2020" @default.
- W3025656547 type Work @default.
- W3025656547 sameAs 3025656547 @default.
- W3025656547 citedByCount "65" @default.
- W3025656547 countsByYear W30256565472020 @default.
- W3025656547 countsByYear W30256565472021 @default.
- W3025656547 countsByYear W30256565472022 @default.
- W3025656547 countsByYear W30256565472023 @default.
- W3025656547 crossrefType "journal-article" @default.
- W3025656547 hasAuthorship W3025656547A5016291304 @default.
- W3025656547 hasAuthorship W3025656547A5019850639 @default.
- W3025656547 hasAuthorship W3025656547A5027607952 @default.
- W3025656547 hasAuthorship W3025656547A5064322543 @default.
- W3025656547 hasAuthorship W3025656547A5067995345 @default.
- W3025656547 hasBestOaLocation W30256565471 @default.
- W3025656547 hasConcept C10138342 @default.
- W3025656547 hasConcept C108583219 @default.
- W3025656547 hasConcept C121684516 @default.
- W3025656547 hasConcept C127413603 @default.
- W3025656547 hasConcept C144133560 @default.
- W3025656547 hasConcept C154945302 @default.
- W3025656547 hasConcept C198082294 @default.
- W3025656547 hasConcept C31972630 @default.
- W3025656547 hasConcept C41008148 @default.
- W3025656547 hasConceptScore W3025656547C10138342 @default.
- W3025656547 hasConceptScore W3025656547C108583219 @default.
- W3025656547 hasConceptScore W3025656547C121684516 @default.
- W3025656547 hasConceptScore W3025656547C127413603 @default.
- W3025656547 hasConceptScore W3025656547C144133560 @default.
- W3025656547 hasConceptScore W3025656547C154945302 @default.
- W3025656547 hasConceptScore W3025656547C198082294 @default.
- W3025656547 hasConceptScore W3025656547C31972630 @default.
- W3025656547 hasConceptScore W3025656547C41008148 @default.
- W3025656547 hasFunder F4320323499 @default.
- W3025656547 hasLocation W30256565471 @default.
- W3025656547 hasOpenAccess W3025656547 @default.
- W3025656547 hasPrimaryLocation W30256565471 @default.
- W3025656547 hasRelatedWork W1865242774 @default.
- W3025656547 hasRelatedWork W2034268939 @default.
- W3025656547 hasRelatedWork W2057434567 @default.
- W3025656547 hasRelatedWork W2111029314 @default.
- W3025656547 hasRelatedWork W2162639903 @default.
- W3025656547 hasRelatedWork W2360764675 @default.
- W3025656547 hasRelatedWork W2395511366 @default.
- W3025656547 hasRelatedWork W43236265 @default.
- W3025656547 hasRelatedWork W78974484 @default.
- W3025656547 hasRelatedWork W2117956613 @default.