Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386434097> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4386434097 endingPage "107023" @default.
- W4386434097 startingPage "107023" @default.
- W4386434097 abstract "A significant challenge in automated defect inspection (ADI) of aluminum strip surfaces is improving segmentation speed to satisfy the online inspection requirements of the production line while maintaining the precision of defect identification. This study proposes a lightweight and efficient defect segmentation model that can be applied in aluminum processing enterprises for fast and precise segmentation of aluminum strip surface defects. A novel fusion attention (FA) mechanism is first established to enhance the focus on critical characteristics along the spatial and channel dimensions. This mechanism adopts continuous dilated convolutions with appropriate dilation rates to effectively increase the range of the receptive field and improve defect localization accuracy. Subsequently, a lightweight MobileViTv2 with an embedded FA mechanism is employed as a multi-scale feature extractor to learn comprehensive representations from defect images. Next, a novel feature fusion method, named large-scale feature pyramid network (LSFPN), is introduced to enhance the focus on details within large-scale features. LSFPN establishes four progressively shallower top-down pathways with fast normalized fusion weights and incorporates lightweight aggregation nodes based on the MoblieNetv2 block. Surface images of straightened aluminum strips with five universal defects were collected, whereby a new dataset was established. The experimental outcomes demonstrate the proposed model outperforms other state-of-the-art techniques synthetically, achieving a mean Intersection over Union (mIoU) of 87.01%, a segmentation speed of 61.67 fps, and a model size of 16.23 MB. This model may serve as a valuable theoretical foundation for the online segmentation of aluminum strip surface defects in embedded devices." @default.
- W4386434097 created "2023-09-05" @default.
- W4386434097 creator A5039954783 @default.
- W4386434097 creator A5047955780 @default.
- W4386434097 creator A5080904739 @default.
- W4386434097 creator A5081370716 @default.
- W4386434097 date "2023-11-01" @default.
- W4386434097 modified "2023-09-30" @default.
- W4386434097 title "Online surface defect segmentation on aluminum strip production line using a lightweight and efficient model" @default.
- W4386434097 cites W1572063013 @default.
- W4386434097 cites W1903029394 @default.
- W4386434097 cites W2109255472 @default.
- W4386434097 cites W2560023338 @default.
- W4386434097 cites W2565639579 @default.
- W4386434097 cites W2589306531 @default.
- W4386434097 cites W2598666589 @default.
- W4386434097 cites W2883780447 @default.
- W4386434097 cites W2884436604 @default.
- W4386434097 cites W2884585870 @default.
- W4386434097 cites W2962834855 @default.
- W4386434097 cites W2963857746 @default.
- W4386434097 cites W2963881378 @default.
- W4386434097 cites W2964309882 @default.
- W4386434097 cites W2994615081 @default.
- W4386434097 cites W2998291476 @default.
- W4386434097 cites W3003792425 @default.
- W4386434097 cites W3034552520 @default.
- W4386434097 cites W3034971973 @default.
- W4386434097 cites W3035414587 @default.
- W4386434097 cites W3085201316 @default.
- W4386434097 cites W3106250896 @default.
- W4386434097 cites W3158083292 @default.
- W4386434097 cites W3177052299 @default.
- W4386434097 cites W3195110827 @default.
- W4386434097 cites W3215747716 @default.
- W4386434097 cites W4200236189 @default.
- W4386434097 cites W4206003336 @default.
- W4386434097 cites W4281252421 @default.
- W4386434097 cites W4288057881 @default.
- W4386434097 cites W4319456411 @default.
- W4386434097 cites W4324131279 @default.
- W4386434097 cites W4362674750 @default.
- W4386434097 cites W4365460408 @default.
- W4386434097 doi "https://doi.org/10.1016/j.engappai.2023.107023" @default.
- W4386434097 hasPublicationYear "2023" @default.
- W4386434097 type Work @default.
- W4386434097 citedByCount "0" @default.
- W4386434097 crossrefType "journal-article" @default.
- W4386434097 hasAuthorship W4386434097A5039954783 @default.
- W4386434097 hasAuthorship W4386434097A5047955780 @default.
- W4386434097 hasAuthorship W4386434097A5080904739 @default.
- W4386434097 hasAuthorship W4386434097A5081370716 @default.
- W4386434097 hasConcept C108583219 @default.
- W4386434097 hasConcept C120665830 @default.
- W4386434097 hasConcept C121332964 @default.
- W4386434097 hasConcept C138885662 @default.
- W4386434097 hasConcept C142575187 @default.
- W4386434097 hasConcept C153180895 @default.
- W4386434097 hasConcept C154945302 @default.
- W4386434097 hasConcept C192209626 @default.
- W4386434097 hasConcept C200925200 @default.
- W4386434097 hasConcept C2776401178 @default.
- W4386434097 hasConcept C31972630 @default.
- W4386434097 hasConcept C41008148 @default.
- W4386434097 hasConcept C41895202 @default.
- W4386434097 hasConcept C89600930 @default.
- W4386434097 hasConceptScore W4386434097C108583219 @default.
- W4386434097 hasConceptScore W4386434097C120665830 @default.
- W4386434097 hasConceptScore W4386434097C121332964 @default.
- W4386434097 hasConceptScore W4386434097C138885662 @default.
- W4386434097 hasConceptScore W4386434097C142575187 @default.
- W4386434097 hasConceptScore W4386434097C153180895 @default.
- W4386434097 hasConceptScore W4386434097C154945302 @default.
- W4386434097 hasConceptScore W4386434097C192209626 @default.
- W4386434097 hasConceptScore W4386434097C200925200 @default.
- W4386434097 hasConceptScore W4386434097C2776401178 @default.
- W4386434097 hasConceptScore W4386434097C31972630 @default.
- W4386434097 hasConceptScore W4386434097C41008148 @default.
- W4386434097 hasConceptScore W4386434097C41895202 @default.
- W4386434097 hasConceptScore W4386434097C89600930 @default.
- W4386434097 hasLocation W43864340971 @default.
- W4386434097 hasOpenAccess W4386434097 @default.
- W4386434097 hasPrimaryLocation W43864340971 @default.
- W4386434097 hasRelatedWork W1669643531 @default.
- W4386434097 hasRelatedWork W1982826852 @default.
- W4386434097 hasRelatedWork W2005437358 @default.
- W4386434097 hasRelatedWork W2008656436 @default.
- W4386434097 hasRelatedWork W2023558673 @default.
- W4386434097 hasRelatedWork W2110230079 @default.
- W4386434097 hasRelatedWork W2134924024 @default.
- W4386434097 hasRelatedWork W2517104666 @default.
- W4386434097 hasRelatedWork W2613186388 @default.
- W4386434097 hasRelatedWork W2790662084 @default.
- W4386434097 hasVolume "126" @default.
- W4386434097 isParatext "false" @default.
- W4386434097 isRetracted "false" @default.
- W4386434097 workType "article" @default.