Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312912241> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4312912241 abstract "This paper presents an attention-based, deep learning framework that converts robot camera frames with dynamic content into static frames to more easily apply simultaneous localization and mapping (SLAM) algorithms. The vast majority of SLAM methods have difficulty in the presence of dynamic objects appearing in the environment and occluding the area being captured by the camera. Despite past attempts to deal with dynamic objects, challenges remain to reconstruct large, occluded areas with complex backgrounds. Our proposed Dynamic-GAN framework employs a generative adversarial network to remove dynamic objects from a scene and inpaint a static image free of dynamic objects. The Dynamic-GAN framework utilizes spatial-temporal transformers, and a novel spatial-temporal loss function. The evaluation of Dynamic-GAN was comprehensively conducted both quantitatively and qualitatively by testing it on benchmark datasets, and on a mobile robot in indoor navigation environments. As people appeared dynamically in close proximity to the robot, results showed that large, feature-rich occluded areas can be accurately reconstructed with our attention-based deep learning framework for dynamic object removal. Through experiments we demonstrate that our proposed algorithm has up to 25% better performance on average as compared to the standard benchmark algorithms." @default.
- W4312912241 created "2023-01-05" @default.
- W4312912241 creator A5014589091 @default.
- W4312912241 creator A5053792979 @default.
- W4312912241 creator A5089902968 @default.
- W4312912241 date "2022-10-23" @default.
- W4312912241 modified "2023-10-16" @default.
- W4312912241 title "Dynamic-GAN: Learning Spatial-Temporal Attention for Dynamic Object Removal in Feature Dense Environments" @default.
- W4312912241 cites W1970504153 @default.
- W4312912241 cites W1999360130 @default.
- W4312912241 cites W2012875423 @default.
- W4312912241 cites W2021851106 @default.
- W4312912241 cites W2025650452 @default.
- W4312912241 cites W2117228865 @default.
- W4312912241 cites W2151290401 @default.
- W4312912241 cites W2752922896 @default.
- W4312912241 cites W2963420272 @default.
- W4312912241 cites W2963881378 @default.
- W4312912241 cites W2968297929 @default.
- W4312912241 cites W2970723181 @default.
- W4312912241 cites W2988407809 @default.
- W4312912241 cites W3003179103 @default.
- W4312912241 cites W3009337785 @default.
- W4312912241 cites W3043547428 @default.
- W4312912241 cites W3090298435 @default.
- W4312912241 cites W3092631798 @default.
- W4312912241 cites W3102327032 @default.
- W4312912241 cites W3120093105 @default.
- W4312912241 cites W3124420883 @default.
- W4312912241 cites W3139856562 @default.
- W4312912241 cites W3172509117 @default.
- W4312912241 cites W4214759957 @default.
- W4312912241 cites W3143852338 @default.
- W4312912241 doi "https://doi.org/10.1109/iros47612.2022.9981102" @default.
- W4312912241 hasPublicationYear "2022" @default.
- W4312912241 type Work @default.
- W4312912241 citedByCount "0" @default.
- W4312912241 crossrefType "proceedings-article" @default.
- W4312912241 hasAuthorship W4312912241A5014589091 @default.
- W4312912241 hasAuthorship W4312912241A5053792979 @default.
- W4312912241 hasAuthorship W4312912241A5089902968 @default.
- W4312912241 hasConcept C108583219 @default.
- W4312912241 hasConcept C13280743 @default.
- W4312912241 hasConcept C138885662 @default.
- W4312912241 hasConcept C154945302 @default.
- W4312912241 hasConcept C185798385 @default.
- W4312912241 hasConcept C19966478 @default.
- W4312912241 hasConcept C205649164 @default.
- W4312912241 hasConcept C2776401178 @default.
- W4312912241 hasConcept C2781238097 @default.
- W4312912241 hasConcept C31972630 @default.
- W4312912241 hasConcept C41008148 @default.
- W4312912241 hasConcept C41895202 @default.
- W4312912241 hasConcept C86369673 @default.
- W4312912241 hasConcept C90509273 @default.
- W4312912241 hasConceptScore W4312912241C108583219 @default.
- W4312912241 hasConceptScore W4312912241C13280743 @default.
- W4312912241 hasConceptScore W4312912241C138885662 @default.
- W4312912241 hasConceptScore W4312912241C154945302 @default.
- W4312912241 hasConceptScore W4312912241C185798385 @default.
- W4312912241 hasConceptScore W4312912241C19966478 @default.
- W4312912241 hasConceptScore W4312912241C205649164 @default.
- W4312912241 hasConceptScore W4312912241C2776401178 @default.
- W4312912241 hasConceptScore W4312912241C2781238097 @default.
- W4312912241 hasConceptScore W4312912241C31972630 @default.
- W4312912241 hasConceptScore W4312912241C41008148 @default.
- W4312912241 hasConceptScore W4312912241C41895202 @default.
- W4312912241 hasConceptScore W4312912241C86369673 @default.
- W4312912241 hasConceptScore W4312912241C90509273 @default.
- W4312912241 hasFunder F4320306076 @default.
- W4312912241 hasLocation W43129122411 @default.
- W4312912241 hasOpenAccess W4312912241 @default.
- W4312912241 hasPrimaryLocation W43129122411 @default.
- W4312912241 hasRelatedWork W1535005230 @default.
- W4312912241 hasRelatedWork W1937705922 @default.
- W4312912241 hasRelatedWork W2028864324 @default.
- W4312912241 hasRelatedWork W2058063222 @default.
- W4312912241 hasRelatedWork W2116298349 @default.
- W4312912241 hasRelatedWork W2134943711 @default.
- W4312912241 hasRelatedWork W2167293474 @default.
- W4312912241 hasRelatedWork W2734306012 @default.
- W4312912241 hasRelatedWork W2786306966 @default.
- W4312912241 hasRelatedWork W2972219788 @default.
- W4312912241 isParatext "false" @default.
- W4312912241 isRetracted "false" @default.
- W4312912241 workType "article" @default.