Matches in SemOpenAlex for { <https://semopenalex.org/work/W3157157071> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3157157071 endingPage "1764" @default.
- W3157157071 startingPage "1764" @default.
- W3157157071 abstract "Depth estimation can provide tremendous help for object detection, localization, path planning, etc. However, the existing methods based on deep learning have high requirements on computing power and often cannot be directly applied to autonomous moving platforms (AMP). Fifth-generation (5G) mobile and wireless communication systems have attracted the attention of researchers because it provides the network foundation for cloud computing and edge computing, which makes it possible to utilize deep learning method on AMP. This paper proposes a depth prediction method for AMP based on unsupervised learning, which can learn from video sequences and simultaneously estimate the depth structure of the scene and the ego-motion. Compared with the existing unsupervised learning methods, our method makes the spatial correspondence among pixel points consistent with the image area by smoothing the 3D corresponding vector field based on 2D image, which effectively improves the depth prediction ability of the neural network. Our experiments on the KITTI driving dataset demonstrated that our method outperformed other previous learning-based methods. The results on the Apolloscape and Cityscapes datasets show that our proposed method has a strong universality." @default.
- W3157157071 created "2021-05-10" @default.
- W3157157071 creator A5000423121 @default.
- W3157157071 creator A5019281790 @default.
- W3157157071 creator A5082583182 @default.
- W3157157071 creator A5084611031 @default.
- W3157157071 creator A5090035461 @default.
- W3157157071 date "2021-05-01" @default.
- W3157157071 modified "2023-09-26" @default.
- W3157157071 title "Unsupervised Learning of Depth from Monocular Videos Using 3D-2D Corresponding Constraints" @default.
- W3157157071 cites W1803059841 @default.
- W3157157071 cites W2133665775 @default.
- W3157157071 cites W2474281075 @default.
- W3157157071 cites W2621274416 @default.
- W3157157071 cites W2765955268 @default.
- W3157157071 cites W2892614179 @default.
- W3157157071 cites W3101889877 @default.
- W3157157071 cites W3103648783 @default.
- W3157157071 cites W3132905414 @default.
- W3157157071 cites W3135879932 @default.
- W3157157071 doi "https://doi.org/10.3390/rs13091764" @default.
- W3157157071 hasPublicationYear "2021" @default.
- W3157157071 type Work @default.
- W3157157071 sameAs 3157157071 @default.
- W3157157071 citedByCount "3" @default.
- W3157157071 countsByYear W31571570712022 @default.
- W3157157071 countsByYear W31571570712023 @default.
- W3157157071 crossrefType "journal-article" @default.
- W3157157071 hasAuthorship W3157157071A5000423121 @default.
- W3157157071 hasAuthorship W3157157071A5019281790 @default.
- W3157157071 hasAuthorship W3157157071A5082583182 @default.
- W3157157071 hasAuthorship W3157157071A5084611031 @default.
- W3157157071 hasAuthorship W3157157071A5090035461 @default.
- W3157157071 hasBestOaLocation W31571570711 @default.
- W3157157071 hasConcept C108583219 @default.
- W3157157071 hasConcept C115961682 @default.
- W3157157071 hasConcept C153180895 @default.
- W3157157071 hasConcept C154945302 @default.
- W3157157071 hasConcept C155542232 @default.
- W3157157071 hasConcept C31972630 @default.
- W3157157071 hasConcept C3770464 @default.
- W3157157071 hasConcept C41008148 @default.
- W3157157071 hasConcept C50644808 @default.
- W3157157071 hasConcept C65909025 @default.
- W3157157071 hasConcept C8038995 @default.
- W3157157071 hasConceptScore W3157157071C108583219 @default.
- W3157157071 hasConceptScore W3157157071C115961682 @default.
- W3157157071 hasConceptScore W3157157071C153180895 @default.
- W3157157071 hasConceptScore W3157157071C154945302 @default.
- W3157157071 hasConceptScore W3157157071C155542232 @default.
- W3157157071 hasConceptScore W3157157071C31972630 @default.
- W3157157071 hasConceptScore W3157157071C3770464 @default.
- W3157157071 hasConceptScore W3157157071C41008148 @default.
- W3157157071 hasConceptScore W3157157071C50644808 @default.
- W3157157071 hasConceptScore W3157157071C65909025 @default.
- W3157157071 hasConceptScore W3157157071C8038995 @default.
- W3157157071 hasFunder F4320335777 @default.
- W3157157071 hasIssue "9" @default.
- W3157157071 hasLocation W31571570711 @default.
- W3157157071 hasLocation W31571570712 @default.
- W3157157071 hasOpenAccess W3157157071 @default.
- W3157157071 hasPrimaryLocation W31571570711 @default.
- W3157157071 hasRelatedWork W1970467378 @default.
- W3157157071 hasRelatedWork W1990911012 @default.
- W3157157071 hasRelatedWork W2115944530 @default.
- W3157157071 hasRelatedWork W2156208915 @default.
- W3157157071 hasRelatedWork W2592071824 @default.
- W3157157071 hasRelatedWork W2610028676 @default.
- W3157157071 hasRelatedWork W2792355643 @default.
- W3157157071 hasRelatedWork W2992415220 @default.
- W3157157071 hasRelatedWork W3198126099 @default.
- W3157157071 hasRelatedWork W4281553171 @default.
- W3157157071 hasVolume "13" @default.
- W3157157071 isParatext "false" @default.
- W3157157071 isRetracted "false" @default.
- W3157157071 magId "3157157071" @default.
- W3157157071 workType "article" @default.