Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313289050> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4313289050 abstract "Existing vehicle detection methods in remote sensing images encounter challenges when detecting vehicles with large aspect ratios. Due to the big scale gap between the long edge and the short edge, large aspect ratio vehicles are hard to extract fine features. In addition, large aspect ratio results in strong orientation information and the inconsistency between regression task and classification task is even more severe. To address these issues, this paper proposes a Large Aspect Ratio Vehicles Detector (LARDet). Aiming at the difficulty of feature extraction for objects with large aspect ratios, we adopt more data augmentation and introduce PAN structure to pass through the short edge feature from shallow layer to deep layer, so as to extract more discriminative features. A lightweight Boxes Quality Predication Module (BQPM) is designed to alleviate the inconsistency between classification score and location accuracy. To alleviate the feature inconsistency between regression and classification, we further design the Align Classification Module (ACM), change the regression branch and classification branch from parallel to serial, then apply AlignConv to extract rotation-invariance feature for classification. A Large Aspect Ratio Vehicles Dataset (LAR1024) is proposed to evaluate our method. Compared with other SOTA methods, LARDet gains 5.0% AP on LAR1024 with the fastest speed of 23.9 FPS, which achieves a better speed-accuracy trade-off in the detection of large aspect ratio vehicles." @default.
- W4313289050 created "2023-01-06" @default.
- W4313289050 creator A5028104934 @default.
- W4313289050 creator A5064775642 @default.
- W4313289050 creator A5070645997 @default.
- W4313289050 creator A5070670691 @default.
- W4313289050 creator A5075556321 @default.
- W4313289050 creator A5090566800 @default.
- W4313289050 date "2022-10-28" @default.
- W4313289050 modified "2023-10-18" @default.
- W4313289050 title "Oriented Object Detection for Large Aspect Ratio Vehicles in Remote Sensing Images" @default.
- W4313289050 cites W2176924101 @default.
- W4313289050 cites W2194775991 @default.
- W4313289050 cites W2565639579 @default.
- W4313289050 cites W2788202095 @default.
- W4313289050 cites W2886904239 @default.
- W4313289050 cites W2962749812 @default.
- W4313289050 cites W2963351448 @default.
- W4313289050 cites W2963857746 @default.
- W4313289050 cites W2964979676 @default.
- W4313289050 cites W3170033848 @default.
- W4313289050 cites W3174873843 @default.
- W4313289050 cites W4226456028 @default.
- W4313289050 doi "https://doi.org/10.1109/icus55513.2022.9986649" @default.
- W4313289050 hasPublicationYear "2022" @default.
- W4313289050 type Work @default.
- W4313289050 citedByCount "0" @default.
- W4313289050 crossrefType "proceedings-article" @default.
- W4313289050 hasAuthorship W4313289050A5028104934 @default.
- W4313289050 hasAuthorship W4313289050A5064775642 @default.
- W4313289050 hasAuthorship W4313289050A5070645997 @default.
- W4313289050 hasAuthorship W4313289050A5070670691 @default.
- W4313289050 hasAuthorship W4313289050A5075556321 @default.
- W4313289050 hasAuthorship W4313289050A5090566800 @default.
- W4313289050 hasConcept C124101348 @default.
- W4313289050 hasConcept C127413603 @default.
- W4313289050 hasConcept C138885662 @default.
- W4313289050 hasConcept C153180895 @default.
- W4313289050 hasConcept C154945302 @default.
- W4313289050 hasConcept C159985019 @default.
- W4313289050 hasConcept C162307627 @default.
- W4313289050 hasConcept C16345878 @default.
- W4313289050 hasConcept C192562407 @default.
- W4313289050 hasConcept C201995342 @default.
- W4313289050 hasConcept C2524010 @default.
- W4313289050 hasConcept C2776151529 @default.
- W4313289050 hasConcept C2776401178 @default.
- W4313289050 hasConcept C2780451532 @default.
- W4313289050 hasConcept C31972630 @default.
- W4313289050 hasConcept C33923547 @default.
- W4313289050 hasConcept C41008148 @default.
- W4313289050 hasConcept C41895202 @default.
- W4313289050 hasConcept C52622490 @default.
- W4313289050 hasConcept C76155785 @default.
- W4313289050 hasConcept C82558694 @default.
- W4313289050 hasConcept C94915269 @default.
- W4313289050 hasConcept C97931131 @default.
- W4313289050 hasConceptScore W4313289050C124101348 @default.
- W4313289050 hasConceptScore W4313289050C127413603 @default.
- W4313289050 hasConceptScore W4313289050C138885662 @default.
- W4313289050 hasConceptScore W4313289050C153180895 @default.
- W4313289050 hasConceptScore W4313289050C154945302 @default.
- W4313289050 hasConceptScore W4313289050C159985019 @default.
- W4313289050 hasConceptScore W4313289050C162307627 @default.
- W4313289050 hasConceptScore W4313289050C16345878 @default.
- W4313289050 hasConceptScore W4313289050C192562407 @default.
- W4313289050 hasConceptScore W4313289050C201995342 @default.
- W4313289050 hasConceptScore W4313289050C2524010 @default.
- W4313289050 hasConceptScore W4313289050C2776151529 @default.
- W4313289050 hasConceptScore W4313289050C2776401178 @default.
- W4313289050 hasConceptScore W4313289050C2780451532 @default.
- W4313289050 hasConceptScore W4313289050C31972630 @default.
- W4313289050 hasConceptScore W4313289050C33923547 @default.
- W4313289050 hasConceptScore W4313289050C41008148 @default.
- W4313289050 hasConceptScore W4313289050C41895202 @default.
- W4313289050 hasConceptScore W4313289050C52622490 @default.
- W4313289050 hasConceptScore W4313289050C76155785 @default.
- W4313289050 hasConceptScore W4313289050C82558694 @default.
- W4313289050 hasConceptScore W4313289050C94915269 @default.
- W4313289050 hasConceptScore W4313289050C97931131 @default.
- W4313289050 hasLocation W43132890501 @default.
- W4313289050 hasOpenAccess W4313289050 @default.
- W4313289050 hasPrimaryLocation W43132890501 @default.
- W4313289050 hasRelatedWork W2024160000 @default.
- W4313289050 hasRelatedWork W2061273563 @default.
- W4313289050 hasRelatedWork W2285052147 @default.
- W4313289050 hasRelatedWork W2546942002 @default.
- W4313289050 hasRelatedWork W2729514902 @default.
- W4313289050 hasRelatedWork W2766932195 @default.
- W4313289050 hasRelatedWork W2773500201 @default.
- W4313289050 hasRelatedWork W2806866760 @default.
- W4313289050 hasRelatedWork W2970216048 @default.
- W4313289050 hasRelatedWork W2073139667 @default.
- W4313289050 isParatext "false" @default.
- W4313289050 isRetracted "false" @default.
- W4313289050 workType "article" @default.