Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313296763> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4313296763 endingPage "178" @default.
- W4313296763 startingPage "171" @default.
- W4313296763 abstract "Solid propellants (SPs), as a high-energy material, are commonly used in military and industrial power systems, such as solid rocket and missiles. The SPs, however, confronts severe difficulties of inevitable defects while being made, thus bringing about the significance of inspection. However, the literatures before typically tackled this problem separately, which subsequently combines different models for the variety of defect patterns. Despite of the effectiveness, this act of matters usually brings excessive complexity and additionally computational burden. In this article, we managed to solve this problem in an integrated framework, which unite both the size detection task and shape detection task at the same time, but with different training strategies. To be specific, our framework is mostly consisted of two stage. Firstly, the SPs region is output using a semantic segmentation network, and size measurements are completed with traditional image processing to determine the size defects of the SPs. Then, the depth features of the segmentation network are combined with the semantic segmentation map to make a spatial attention mechanism, which is input to the deep classifier to complete the shape defect detection. The focus of model is gradually shifted from the segmentation task to the classification task as the number of training sessions increases by introducing dynamic balancing factors. The experimental results show that the multi-task learning approach can greatly improve the generalization and robustness of the model, and the accuracy and speed are improved for appearance defect detection of SPs." @default.
- W4313296763 created "2023-01-06" @default.
- W4313296763 creator A5002487860 @default.
- W4313296763 creator A5011688144 @default.
- W4313296763 creator A5024616908 @default.
- W4313296763 creator A5070572694 @default.
- W4313296763 creator A5081396213 @default.
- W4313296763 date "2022-12-27" @default.
- W4313296763 modified "2023-10-05" @default.
- W4313296763 title "A Deep Detection Model based on Multi-task Learning for Appearance Defect of Solid Propellants" @default.
- W4313296763 cites W1901129140 @default.
- W4313296763 cites W1903029394 @default.
- W4313296763 cites W2561295453 @default.
- W4313296763 cites W2768228228 @default.
- W4313296763 cites W2769988472 @default.
- W4313296763 cites W2782812883 @default.
- W4313296763 cites W2919709195 @default.
- W4313296763 cites W2942426505 @default.
- W4313296763 cites W2964229212 @default.
- W4313296763 cites W2964309882 @default.
- W4313296763 cites W3020097243 @default.
- W4313296763 cites W3023057433 @default.
- W4313296763 cites W3104156061 @default.
- W4313296763 cites W3111404230 @default.
- W4313296763 cites W3165012668 @default.
- W4313296763 cites W3209750255 @default.
- W4313296763 cites W4210894209 @default.
- W4313296763 cites W4284696739 @default.
- W4313296763 doi "https://doi.org/10.54097/hset.v24i.3909" @default.
- W4313296763 hasPublicationYear "2022" @default.
- W4313296763 type Work @default.
- W4313296763 citedByCount "0" @default.
- W4313296763 crossrefType "journal-article" @default.
- W4313296763 hasAuthorship W4313296763A5002487860 @default.
- W4313296763 hasAuthorship W4313296763A5011688144 @default.
- W4313296763 hasAuthorship W4313296763A5024616908 @default.
- W4313296763 hasAuthorship W4313296763A5070572694 @default.
- W4313296763 hasAuthorship W4313296763A5081396213 @default.
- W4313296763 hasBestOaLocation W43132967631 @default.
- W4313296763 hasConcept C104317684 @default.
- W4313296763 hasConcept C108583219 @default.
- W4313296763 hasConcept C119857082 @default.
- W4313296763 hasConcept C127413603 @default.
- W4313296763 hasConcept C134306372 @default.
- W4313296763 hasConcept C146978453 @default.
- W4313296763 hasConcept C153180895 @default.
- W4313296763 hasConcept C154945302 @default.
- W4313296763 hasConcept C177148314 @default.
- W4313296763 hasConcept C185592680 @default.
- W4313296763 hasConcept C201995342 @default.
- W4313296763 hasConcept C2780451532 @default.
- W4313296763 hasConcept C33923547 @default.
- W4313296763 hasConcept C41008148 @default.
- W4313296763 hasConcept C55493867 @default.
- W4313296763 hasConcept C63479239 @default.
- W4313296763 hasConcept C76737569 @default.
- W4313296763 hasConcept C89600930 @default.
- W4313296763 hasConcept C95623464 @default.
- W4313296763 hasConceptScore W4313296763C104317684 @default.
- W4313296763 hasConceptScore W4313296763C108583219 @default.
- W4313296763 hasConceptScore W4313296763C119857082 @default.
- W4313296763 hasConceptScore W4313296763C127413603 @default.
- W4313296763 hasConceptScore W4313296763C134306372 @default.
- W4313296763 hasConceptScore W4313296763C146978453 @default.
- W4313296763 hasConceptScore W4313296763C153180895 @default.
- W4313296763 hasConceptScore W4313296763C154945302 @default.
- W4313296763 hasConceptScore W4313296763C177148314 @default.
- W4313296763 hasConceptScore W4313296763C185592680 @default.
- W4313296763 hasConceptScore W4313296763C201995342 @default.
- W4313296763 hasConceptScore W4313296763C2780451532 @default.
- W4313296763 hasConceptScore W4313296763C33923547 @default.
- W4313296763 hasConceptScore W4313296763C41008148 @default.
- W4313296763 hasConceptScore W4313296763C55493867 @default.
- W4313296763 hasConceptScore W4313296763C63479239 @default.
- W4313296763 hasConceptScore W4313296763C76737569 @default.
- W4313296763 hasConceptScore W4313296763C89600930 @default.
- W4313296763 hasConceptScore W4313296763C95623464 @default.
- W4313296763 hasLocation W43132967631 @default.
- W4313296763 hasOpenAccess W4313296763 @default.
- W4313296763 hasPrimaryLocation W43132967631 @default.
- W4313296763 hasRelatedWork W2790662084 @default.
- W4313296763 hasRelatedWork W3014300295 @default.
- W4313296763 hasRelatedWork W3164822677 @default.
- W4313296763 hasRelatedWork W4223943233 @default.
- W4313296763 hasRelatedWork W4225161397 @default.
- W4313296763 hasRelatedWork W4312200629 @default.
- W4313296763 hasRelatedWork W4360585206 @default.
- W4313296763 hasRelatedWork W4364306694 @default.
- W4313296763 hasRelatedWork W4380075502 @default.
- W4313296763 hasRelatedWork W4380086463 @default.
- W4313296763 hasVolume "24" @default.
- W4313296763 isParatext "false" @default.
- W4313296763 isRetracted "false" @default.
- W4313296763 workType "article" @default.