Matches in SemOpenAlex for { <https://semopenalex.org/work/W3080296883> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3080296883 abstract "Feature extraction methods of multi-spectral remote sensing images is of great significance for remote sensing image analysis, but it still faces some challenges. The ability of traditional feature extraction methods based on artificial features or shallow machine learning have some shortcomings and limitations. Recently, a series of proposed R-CNN networks, especially Faster R-CNN, have achieved excellent results in the field of target recognition. However, Faster R-CNN for multi-spectral imagery object detection has several drawbacks: (1) the object spectral information cannot be fully utilized in Faster R-CNN used to process RGB images; (2) the spatial semantic relationship information which could not be mined by Faster R-CNN among remote sensing image features can improve the feature extraction ability of the network; (3) objects occupy relatively few pixels because of the low resolution of multi-spectral images, and Faster R-CNN has poor detection performance for small objects. To address the above problems, we propose an effective and novel object detection method for multi-spectral images with small objects. First, we design a feature extractor by adopting a 3D convolution neural network which can simultaneously extract spectral information and spatial information. Secondly, an object relation module for mining context information is introduced into the network. Finally, in order to solve the problem of small targets, a multi-scale object proposal network for generating regions of objects from several intermediate layers is used. We conducted a set of controlled trials on the satellite imagery feature detection dataset released by Dstl on the Kaggle website and the results showed that our approach was very effective." @default.
- W3080296883 created "2020-09-01" @default.
- W3080296883 creator A5003799076 @default.
- W3080296883 creator A5030699864 @default.
- W3080296883 creator A5031315906 @default.
- W3080296883 creator A5033914791 @default.
- W3080296883 date "2019-12-01" @default.
- W3080296883 modified "2023-09-24" @default.
- W3080296883 title "AN IMPROVED FEATURE EXTRACTION METHOD BASED ON CONTEXT FEATURES FOR MULTI-SPECTRAL REMOTE SENSING IMAGERY" @default.
- W3080296883 cites W1535289548 @default.
- W3080296883 cites W1536680647 @default.
- W3080296883 cites W1970782782 @default.
- W3080296883 cites W2000803298 @default.
- W3080296883 cites W2024106491 @default.
- W3080296883 cites W2081175893 @default.
- W3080296883 cites W2153538582 @default.
- W3080296883 cites W2308318555 @default.
- W3080296883 cites W2565639579 @default.
- W3080296883 cites W2919115771 @default.
- W3080296883 cites W2964080601 @default.
- W3080296883 cites W3101640299 @default.
- W3080296883 cites W639708223 @default.
- W3080296883 doi "https://doi.org/10.1109/icsidp47821.2019.9172952" @default.
- W3080296883 hasPublicationYear "2019" @default.
- W3080296883 type Work @default.
- W3080296883 sameAs 3080296883 @default.
- W3080296883 citedByCount "0" @default.
- W3080296883 crossrefType "proceedings-article" @default.
- W3080296883 hasAuthorship W3080296883A5003799076 @default.
- W3080296883 hasAuthorship W3080296883A5030699864 @default.
- W3080296883 hasAuthorship W3080296883A5031315906 @default.
- W3080296883 hasAuthorship W3080296883A5033914791 @default.
- W3080296883 hasConcept C127313418 @default.
- W3080296883 hasConcept C138885662 @default.
- W3080296883 hasConcept C151730666 @default.
- W3080296883 hasConcept C153180895 @default.
- W3080296883 hasConcept C154945302 @default.
- W3080296883 hasConcept C160633673 @default.
- W3080296883 hasConcept C2776151529 @default.
- W3080296883 hasConcept C2776401178 @default.
- W3080296883 hasConcept C2779343474 @default.
- W3080296883 hasConcept C31972630 @default.
- W3080296883 hasConcept C41008148 @default.
- W3080296883 hasConcept C41895202 @default.
- W3080296883 hasConcept C45347329 @default.
- W3080296883 hasConcept C50644808 @default.
- W3080296883 hasConcept C52622490 @default.
- W3080296883 hasConcept C62649853 @default.
- W3080296883 hasConcept C81363708 @default.
- W3080296883 hasConcept C82990744 @default.
- W3080296883 hasConcept C86803240 @default.
- W3080296883 hasConceptScore W3080296883C127313418 @default.
- W3080296883 hasConceptScore W3080296883C138885662 @default.
- W3080296883 hasConceptScore W3080296883C151730666 @default.
- W3080296883 hasConceptScore W3080296883C153180895 @default.
- W3080296883 hasConceptScore W3080296883C154945302 @default.
- W3080296883 hasConceptScore W3080296883C160633673 @default.
- W3080296883 hasConceptScore W3080296883C2776151529 @default.
- W3080296883 hasConceptScore W3080296883C2776401178 @default.
- W3080296883 hasConceptScore W3080296883C2779343474 @default.
- W3080296883 hasConceptScore W3080296883C31972630 @default.
- W3080296883 hasConceptScore W3080296883C41008148 @default.
- W3080296883 hasConceptScore W3080296883C41895202 @default.
- W3080296883 hasConceptScore W3080296883C45347329 @default.
- W3080296883 hasConceptScore W3080296883C50644808 @default.
- W3080296883 hasConceptScore W3080296883C52622490 @default.
- W3080296883 hasConceptScore W3080296883C62649853 @default.
- W3080296883 hasConceptScore W3080296883C81363708 @default.
- W3080296883 hasConceptScore W3080296883C82990744 @default.
- W3080296883 hasConceptScore W3080296883C86803240 @default.
- W3080296883 hasLocation W30802968831 @default.
- W3080296883 hasOpenAccess W3080296883 @default.
- W3080296883 hasPrimaryLocation W30802968831 @default.
- W3080296883 hasRelatedWork W1000462 @default.
- W3080296883 hasRelatedWork W10677893 @default.
- W3080296883 hasRelatedWork W12901231 @default.
- W3080296883 hasRelatedWork W13423774 @default.
- W3080296883 hasRelatedWork W13815759 @default.
- W3080296883 hasRelatedWork W2376444 @default.
- W3080296883 hasRelatedWork W2585641 @default.
- W3080296883 hasRelatedWork W2712644 @default.
- W3080296883 hasRelatedWork W9465030 @default.
- W3080296883 hasRelatedWork W9826774 @default.
- W3080296883 isParatext "false" @default.
- W3080296883 isRetracted "false" @default.
- W3080296883 magId "3080296883" @default.
- W3080296883 workType "article" @default.