Matches in SemOpenAlex for { <https://semopenalex.org/work/W3129930510> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W3129930510 abstract "Deep learning (DL) based object detection methods have been making great achievements for natural images, which guides the vehicle detection of optical remote sensing videos (ORSV). Compared with natural images, objects in ORSV are smaller and blurrier, and most of vehicles are crowded. Thus, it is difficult for DL to detect these small objects only using the single-frame image. To address this problem, a motion guided R-CNN (MG-RCNN) is proposed. In MG-RCNN, motion information from consecutive frames is extracted by the mean differencing method and merged into apparent information to obtain motion-related discriminative features. Then, high-quality proposals are generated on the feature maps by mini-region proposal network (MRPN). For small targets, an improved loss function is defined by incorporating smooth factor, which makes the regression of shapes more stable. Experiments on ORSV demonstrate the proposed method shows superior detection performance over state-of-the-art deep learning methods." @default.
- W3129930510 created "2021-03-01" @default.
- W3129930510 creator A5015157242 @default.
- W3129930510 creator A5020325182 @default.
- W3129930510 creator A5032650845 @default.
- W3129930510 creator A5045546082 @default.
- W3129930510 creator A5049776440 @default.
- W3129930510 creator A5059262797 @default.
- W3129930510 creator A5086657787 @default.
- W3129930510 date "2020-09-26" @default.
- W3129930510 modified "2023-09-24" @default.
- W3129930510 title "Small Object Detection in Optical Remote Sensing Video with Motion Guided R-CNN" @default.
- W3129930510 cites W2004506571 @default.
- W3129930510 cites W2522520073 @default.
- W3129930510 cites W2963179609 @default.
- W3129930510 cites W2982770724 @default.
- W3129930510 cites W2989604896 @default.
- W3129930510 doi "https://doi.org/10.1109/igarss39084.2020.9323690" @default.
- W3129930510 hasPublicationYear "2020" @default.
- W3129930510 type Work @default.
- W3129930510 sameAs 3129930510 @default.
- W3129930510 citedByCount "2" @default.
- W3129930510 countsByYear W31299305102022 @default.
- W3129930510 countsByYear W31299305102023 @default.
- W3129930510 crossrefType "proceedings-article" @default.
- W3129930510 hasAuthorship W3129930510A5015157242 @default.
- W3129930510 hasAuthorship W3129930510A5020325182 @default.
- W3129930510 hasAuthorship W3129930510A5032650845 @default.
- W3129930510 hasAuthorship W3129930510A5045546082 @default.
- W3129930510 hasAuthorship W3129930510A5049776440 @default.
- W3129930510 hasAuthorship W3129930510A5059262797 @default.
- W3129930510 hasAuthorship W3129930510A5086657787 @default.
- W3129930510 hasConcept C104114177 @default.
- W3129930510 hasConcept C121684516 @default.
- W3129930510 hasConcept C127313418 @default.
- W3129930510 hasConcept C153180895 @default.
- W3129930510 hasConcept C154945302 @default.
- W3129930510 hasConcept C2776151529 @default.
- W3129930510 hasConcept C2781238097 @default.
- W3129930510 hasConcept C31972630 @default.
- W3129930510 hasConcept C41008148 @default.
- W3129930510 hasConcept C62649853 @default.
- W3129930510 hasConceptScore W3129930510C104114177 @default.
- W3129930510 hasConceptScore W3129930510C121684516 @default.
- W3129930510 hasConceptScore W3129930510C127313418 @default.
- W3129930510 hasConceptScore W3129930510C153180895 @default.
- W3129930510 hasConceptScore W3129930510C154945302 @default.
- W3129930510 hasConceptScore W3129930510C2776151529 @default.
- W3129930510 hasConceptScore W3129930510C2781238097 @default.
- W3129930510 hasConceptScore W3129930510C31972630 @default.
- W3129930510 hasConceptScore W3129930510C41008148 @default.
- W3129930510 hasConceptScore W3129930510C62649853 @default.
- W3129930510 hasFunder F4320321001 @default.
- W3129930510 hasFunder F4320321133 @default.
- W3129930510 hasLocation W31299305101 @default.
- W3129930510 hasOpenAccess W3129930510 @default.
- W3129930510 hasPrimaryLocation W31299305101 @default.
- W3129930510 hasRelatedWork W1971759388 @default.
- W3129930510 hasRelatedWork W2004370856 @default.
- W3129930510 hasRelatedWork W2007544051 @default.
- W3129930510 hasRelatedWork W2021186063 @default.
- W3129930510 hasRelatedWork W2025800131 @default.
- W3129930510 hasRelatedWork W2035456249 @default.
- W3129930510 hasRelatedWork W2095705906 @default.
- W3129930510 hasRelatedWork W2129974284 @default.
- W3129930510 hasRelatedWork W2375636617 @default.
- W3129930510 hasRelatedWork W2975200075 @default.
- W3129930510 isParatext "false" @default.
- W3129930510 isRetracted "false" @default.
- W3129930510 magId "3129930510" @default.
- W3129930510 workType "article" @default.