Matches in SemOpenAlex for { <https://semopenalex.org/work/W4360897689> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4360897689 endingPage "29697" @default.
- W4360897689 startingPage "29684" @default.
- W4360897689 abstract "Slender flexible objects are ubiquitous in real-world circumstances. The existing object detection and segmentation algorithms have achieved high accuracy and speed in rigid objects, but the detection effect of slender flexible objects is not ideal. Extreme aspect ratios and dynamically changeable geometric appearance characterize slender flexible objects, to the extent that it is difficult to locate them in instance segmentation. In this paper, a new instance segmentation method based on the object correlation module and loss function optimization is proposed for the detection of slender flexible objects. In order to achieve more accurate anchor box positioning, a GIoU bounding-box regression loss function is selected to overcome the problem of inconsistency between training objectives and assessment indicators. Furthermore, due to the Mask Scoring R-CNN detection network ignoring the relationships between objects, the object correlation module is proposed to achieve end-to-end learning and modeling of the correlation features between all objects in the image to improve slender flexible objects detection accuracy. The results of the experiments on the self-built flexible object dataset for the power grid operation sites demonstrate that the method presented in this research can efficiently recognize and segment slender flexible objects, with a detection accuracy of 44.8%. The ablation experiment also shows that the addition object correlation module and the revised bounding-box regression loss function are both effective and can enhance slender flexible object detection accuracy by 1.2% and 0.5%, respectively. The proposed instance segmentation method considers the correlation characteristics between objects and improves the bounding-box regression loss function to increase the segmentation accuracy of slender flexible objects." @default.
- W4360897689 created "2023-03-26" @default.
- W4360897689 creator A5000968129 @default.
- W4360897689 creator A5016914541 @default.
- W4360897689 creator A5066762898 @default.
- W4360897689 creator A5069237390 @default.
- W4360897689 date "2023-01-01" @default.
- W4360897689 modified "2023-09-26" @default.
- W4360897689 title "Slender Flexible Object Segmentation Based on Object Correlation Module and Loss Function Optimization" @default.
- W4360897689 cites W1832500336 @default.
- W4360897689 cites W2557889580 @default.
- W4360897689 cites W2558156561 @default.
- W4360897689 cites W2565639579 @default.
- W4360897689 cites W2761891891 @default.
- W4360897689 cites W2790722345 @default.
- W4360897689 cites W2920326761 @default.
- W4360897689 cites W2962766617 @default.
- W4360897689 cites W2963150697 @default.
- W4360897689 cites W2963857746 @default.
- W4360897689 cites W2963927307 @default.
- W4360897689 cites W2964080601 @default.
- W4360897689 cites W2968226676 @default.
- W4360897689 cites W2982161360 @default.
- W4360897689 cites W2993182889 @default.
- W4360897689 cites W3107166765 @default.
- W4360897689 cites W3155149973 @default.
- W4360897689 cites W3174389852 @default.
- W4360897689 cites W3177105943 @default.
- W4360897689 cites W4225834318 @default.
- W4360897689 cites W4285507602 @default.
- W4360897689 cites W4285817873 @default.
- W4360897689 cites W4286377446 @default.
- W4360897689 cites W4312637554 @default.
- W4360897689 cites W4316362245 @default.
- W4360897689 doi "https://doi.org/10.1109/access.2023.3261543" @default.
- W4360897689 hasPublicationYear "2023" @default.
- W4360897689 type Work @default.
- W4360897689 citedByCount "2" @default.
- W4360897689 countsByYear W43608976892023 @default.
- W4360897689 crossrefType "journal-article" @default.
- W4360897689 hasAuthorship W4360897689A5000968129 @default.
- W4360897689 hasAuthorship W4360897689A5016914541 @default.
- W4360897689 hasAuthorship W4360897689A5066762898 @default.
- W4360897689 hasAuthorship W4360897689A5069237390 @default.
- W4360897689 hasBestOaLocation W43608976891 @default.
- W4360897689 hasConcept C115961682 @default.
- W4360897689 hasConcept C124504099 @default.
- W4360897689 hasConcept C14036430 @default.
- W4360897689 hasConcept C147037132 @default.
- W4360897689 hasConcept C153180895 @default.
- W4360897689 hasConcept C154945302 @default.
- W4360897689 hasConcept C2776151529 @default.
- W4360897689 hasConcept C2781238097 @default.
- W4360897689 hasConcept C31972630 @default.
- W4360897689 hasConcept C41008148 @default.
- W4360897689 hasConcept C63584917 @default.
- W4360897689 hasConcept C78458016 @default.
- W4360897689 hasConcept C86803240 @default.
- W4360897689 hasConcept C89600930 @default.
- W4360897689 hasConceptScore W4360897689C115961682 @default.
- W4360897689 hasConceptScore W4360897689C124504099 @default.
- W4360897689 hasConceptScore W4360897689C14036430 @default.
- W4360897689 hasConceptScore W4360897689C147037132 @default.
- W4360897689 hasConceptScore W4360897689C153180895 @default.
- W4360897689 hasConceptScore W4360897689C154945302 @default.
- W4360897689 hasConceptScore W4360897689C2776151529 @default.
- W4360897689 hasConceptScore W4360897689C2781238097 @default.
- W4360897689 hasConceptScore W4360897689C31972630 @default.
- W4360897689 hasConceptScore W4360897689C41008148 @default.
- W4360897689 hasConceptScore W4360897689C63584917 @default.
- W4360897689 hasConceptScore W4360897689C78458016 @default.
- W4360897689 hasConceptScore W4360897689C86803240 @default.
- W4360897689 hasConceptScore W4360897689C89600930 @default.
- W4360897689 hasFunder F4320321001 @default.
- W4360897689 hasFunder F4320321878 @default.
- W4360897689 hasLocation W43608976891 @default.
- W4360897689 hasOpenAccess W4360897689 @default.
- W4360897689 hasPrimaryLocation W43608976891 @default.
- W4360897689 hasRelatedWork W2019566805 @default.
- W4360897689 hasRelatedWork W2095705906 @default.
- W4360897689 hasRelatedWork W2801801420 @default.
- W4360897689 hasRelatedWork W2921865287 @default.
- W4360897689 hasRelatedWork W2975200075 @default.
- W4360897689 hasRelatedWork W3130645678 @default.
- W4360897689 hasRelatedWork W4213013926 @default.
- W4360897689 hasRelatedWork W4223573735 @default.
- W4360897689 hasRelatedWork W4285742308 @default.
- W4360897689 hasRelatedWork W1967061043 @default.
- W4360897689 hasVolume "11" @default.
- W4360897689 isParatext "false" @default.
- W4360897689 isRetracted "false" @default.
- W4360897689 workType "article" @default.