Matches in SemOpenAlex for { <https://semopenalex.org/work/W2909077096> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2909077096 abstract "We present a method for visually detecting and tracking the 3D pose of autonomous underwater vehicles, which aims to enable robust multi-robot convoying. We follow the approach of tracking-by-detection, which combines the robust, drift-free nature of object detection with the temporal consistency of tracking algorithms. Central to our method is a multi-output convolutional network that jointly predicts whether the target robot is present in the image (classification), the 2D bounding box around the target in the image plane, and the 3D orientation of the target. This, combined with camera intrinsic parameters and prior knowledge of the robot’s absolute scale, allows us to recover the full 6-degree-of-freedom pose (translation and orientation) of the target robot. To train our network, we use only synthetic images rendered using the Unreal game engine, which is a cost-effective way to produce a large training set without the need for laborious manual annotations. Our evaluation analyzes the impact of orientation offset on 3D detection accuracy, and demonstrates successful generalization of the learned model to real underwater photographs of the target robot." @default.
- W2909077096 created "2019-01-25" @default.
- W2909077096 creator A5007851877 @default.
- W2909077096 creator A5010648258 @default.
- W2909077096 creator A5035438680 @default.
- W2909077096 creator A5059748305 @default.
- W2909077096 creator A5075441381 @default.
- W2909077096 creator A5084879329 @default.
- W2909077096 date "2018-10-01" @default.
- W2909077096 modified "2023-09-27" @default.
- W2909077096 title "Synthetically Trained 3D Visual Tracker of Underwater Vehicles" @default.
- W2909077096 cites W1591870335 @default.
- W2909077096 cites W1980595574 @default.
- W2909077096 cites W2029554003 @default.
- W2909077096 cites W2045701406 @default.
- W2909077096 cites W2071634722 @default.
- W2909077096 cites W2115826585 @default.
- W2909077096 cites W2133294759 @default.
- W2909077096 cites W2138302688 @default.
- W2909077096 cites W2140133974 @default.
- W2909077096 cites W2140676941 @default.
- W2909077096 cites W2146447720 @default.
- W2909077096 cites W2158439138 @default.
- W2909077096 cites W2200124539 @default.
- W2909077096 cites W2229637417 @default.
- W2909077096 cites W2605102758 @default.
- W2909077096 cites W2908986427 @default.
- W2909077096 cites W2962759496 @default.
- W2909077096 cites W2964057995 @default.
- W2909077096 cites W2964217490 @default.
- W2909077096 cites W4240661838 @default.
- W2909077096 cites W4250952223 @default.
- W2909077096 doi "https://doi.org/10.1109/oceans.2018.8604597" @default.
- W2909077096 hasPublicationYear "2018" @default.
- W2909077096 type Work @default.
- W2909077096 sameAs 2909077096 @default.
- W2909077096 citedByCount "9" @default.
- W2909077096 countsByYear W29090770962018 @default.
- W2909077096 countsByYear W29090770962019 @default.
- W2909077096 countsByYear W29090770962020 @default.
- W2909077096 countsByYear W29090770962021 @default.
- W2909077096 countsByYear W29090770962022 @default.
- W2909077096 crossrefType "proceedings-article" @default.
- W2909077096 hasAuthorship W2909077096A5007851877 @default.
- W2909077096 hasAuthorship W2909077096A5010648258 @default.
- W2909077096 hasAuthorship W2909077096A5035438680 @default.
- W2909077096 hasAuthorship W2909077096A5059748305 @default.
- W2909077096 hasAuthorship W2909077096A5075441381 @default.
- W2909077096 hasAuthorship W2909077096A5084879329 @default.
- W2909077096 hasConcept C111368507 @default.
- W2909077096 hasConcept C127313418 @default.
- W2909077096 hasConcept C145424490 @default.
- W2909077096 hasConcept C154945302 @default.
- W2909077096 hasConcept C19966478 @default.
- W2909077096 hasConcept C31972630 @default.
- W2909077096 hasConcept C41008148 @default.
- W2909077096 hasConcept C90509273 @default.
- W2909077096 hasConcept C98083399 @default.
- W2909077096 hasConceptScore W2909077096C111368507 @default.
- W2909077096 hasConceptScore W2909077096C127313418 @default.
- W2909077096 hasConceptScore W2909077096C145424490 @default.
- W2909077096 hasConceptScore W2909077096C154945302 @default.
- W2909077096 hasConceptScore W2909077096C19966478 @default.
- W2909077096 hasConceptScore W2909077096C31972630 @default.
- W2909077096 hasConceptScore W2909077096C41008148 @default.
- W2909077096 hasConceptScore W2909077096C90509273 @default.
- W2909077096 hasConceptScore W2909077096C98083399 @default.
- W2909077096 hasLocation W29090770961 @default.
- W2909077096 hasOpenAccess W2909077096 @default.
- W2909077096 hasPrimaryLocation W29090770961 @default.
- W2909077096 hasRelatedWork W1647058919 @default.
- W2909077096 hasRelatedWork W174324061 @default.
- W2909077096 hasRelatedWork W1928779108 @default.
- W2909077096 hasRelatedWork W1970096684 @default.
- W2909077096 hasRelatedWork W2593945244 @default.
- W2909077096 hasRelatedWork W2742702720 @default.
- W2909077096 hasRelatedWork W2888809869 @default.
- W2909077096 hasRelatedWork W2897935372 @default.
- W2909077096 hasRelatedWork W2969953311 @default.
- W2909077096 hasRelatedWork W2607471452 @default.
- W2909077096 isParatext "false" @default.
- W2909077096 isRetracted "false" @default.
- W2909077096 magId "2909077096" @default.
- W2909077096 workType "article" @default.