Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361761993> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4361761993 endingPage "61559" @default.
- W4361761993 startingPage "61546" @default.
- W4361761993 abstract "A lightweight rotational object detection algorithm, R-YOLOv5, is proposed to address the limitations of traditional object detection algorithms that do not consider the diversity of vehicle scales in drone images and fail to obtain information on rotation angles. The proposed algorithm incorporated an angle prediction branch and introduced a circular smooth label (CSL) angle classification method to make it suitable for detection scenarios based on rotational boxes. A cascaded Swin Transformer block (STrB) is used to reduce computational complexity during feature fusion in the backbone network, further enhancing semantic information and global perception capabilities for small objects. A feature enhancement attention module (FEAM) is proposed to improve the utilization of detailed information through local feature self-supervision. An adaptive spatial feature fusion structure (ASFF) is introduced, which employs features extracted from different levels of the backbone network to perform multi-scale feature fusion. The experimental results show that the detection accuracy reaches 84.91% on the Drone-Vehicle dataset and 90.23% on the UCAS-AOD remote sensing dataset. The lightweight model has a parameter count of only 2.02 million and can achieve 82.6 FPS for high-resolution images, which is significantly better than existing lightweight models and more suitable for real-time detection of rotating vehicles in dense scenes, making it suitable for deployment on a large majority of embedded platforms." @default.
- W4361761993 created "2023-04-04" @default.
- W4361761993 creator A5034126906 @default.
- W4361761993 creator A5043185150 @default.
- W4361761993 creator A5054486930 @default.
- W4361761993 creator A5065844410 @default.
- W4361761993 date "2023-01-01" @default.
- W4361761993 modified "2023-10-16" @default.
- W4361761993 title "R-YOLOv5: A Lightweight Rotational Object Detection Algorithm for Real-Time Detection of Vehicles in Dense Scenes" @default.
- W4361761993 cites W1536680647 @default.
- W4361761993 cites W2031489346 @default.
- W4361761993 cites W2102605133 @default.
- W4361761993 cites W2107634464 @default.
- W4361761993 cites W2161969291 @default.
- W4361761993 cites W2296151615 @default.
- W4361761993 cites W2400138547 @default.
- W4361761993 cites W2565639579 @default.
- W4361761993 cites W2612624696 @default.
- W4361761993 cites W2962749812 @default.
- W4361761993 cites W2963150697 @default.
- W4361761993 cites W2963351448 @default.
- W4361761993 cites W2963857746 @default.
- W4361761993 cites W2964979676 @default.
- W4361761993 cites W2991359031 @default.
- W4361761993 cites W2997747012 @default.
- W4361761993 cites W3022917557 @default.
- W4361761993 cites W3034971973 @default.
- W4361761993 cites W3095320185 @default.
- W4361761993 cites W3104434399 @default.
- W4361761993 cites W3109055651 @default.
- W4361761993 cites W3121842289 @default.
- W4361761993 cites W3138516171 @default.
- W4361761993 cites W3174389852 @default.
- W4361761993 cites W3180084293 @default.
- W4361761993 cites W3207919963 @default.
- W4361761993 cites W3209499093 @default.
- W4361761993 cites W3210586215 @default.
- W4361761993 cites W4296211555 @default.
- W4361761993 doi "https://doi.org/10.1109/access.2023.3262601" @default.
- W4361761993 hasPublicationYear "2023" @default.
- W4361761993 type Work @default.
- W4361761993 citedByCount "3" @default.
- W4361761993 countsByYear W43617619932023 @default.
- W4361761993 crossrefType "journal-article" @default.
- W4361761993 hasAuthorship W4361761993A5034126906 @default.
- W4361761993 hasAuthorship W4361761993A5043185150 @default.
- W4361761993 hasAuthorship W4361761993A5054486930 @default.
- W4361761993 hasAuthorship W4361761993A5065844410 @default.
- W4361761993 hasBestOaLocation W43617619931 @default.
- W4361761993 hasConcept C11413529 @default.
- W4361761993 hasConcept C138885662 @default.
- W4361761993 hasConcept C153180895 @default.
- W4361761993 hasConcept C154945302 @default.
- W4361761993 hasConcept C2524010 @default.
- W4361761993 hasConcept C2776151529 @default.
- W4361761993 hasConcept C2776401178 @default.
- W4361761993 hasConcept C2777210771 @default.
- W4361761993 hasConcept C31258907 @default.
- W4361761993 hasConcept C31972630 @default.
- W4361761993 hasConcept C33923547 @default.
- W4361761993 hasConcept C41008148 @default.
- W4361761993 hasConcept C41895202 @default.
- W4361761993 hasConcept C52622490 @default.
- W4361761993 hasConcept C88796919 @default.
- W4361761993 hasConceptScore W4361761993C11413529 @default.
- W4361761993 hasConceptScore W4361761993C138885662 @default.
- W4361761993 hasConceptScore W4361761993C153180895 @default.
- W4361761993 hasConceptScore W4361761993C154945302 @default.
- W4361761993 hasConceptScore W4361761993C2524010 @default.
- W4361761993 hasConceptScore W4361761993C2776151529 @default.
- W4361761993 hasConceptScore W4361761993C2776401178 @default.
- W4361761993 hasConceptScore W4361761993C2777210771 @default.
- W4361761993 hasConceptScore W4361761993C31258907 @default.
- W4361761993 hasConceptScore W4361761993C31972630 @default.
- W4361761993 hasConceptScore W4361761993C33923547 @default.
- W4361761993 hasConceptScore W4361761993C41008148 @default.
- W4361761993 hasConceptScore W4361761993C41895202 @default.
- W4361761993 hasConceptScore W4361761993C52622490 @default.
- W4361761993 hasConceptScore W4361761993C88796919 @default.
- W4361761993 hasLocation W43617619931 @default.
- W4361761993 hasOpenAccess W4361761993 @default.
- W4361761993 hasPrimaryLocation W43617619931 @default.
- W4361761993 hasRelatedWork W1497101000 @default.
- W4361761993 hasRelatedWork W1504288058 @default.
- W4361761993 hasRelatedWork W2095705906 @default.
- W4361761993 hasRelatedWork W2331674254 @default.
- W4361761993 hasRelatedWork W2546942002 @default.
- W4361761993 hasRelatedWork W2754428891 @default.
- W4361761993 hasRelatedWork W2782964878 @default.
- W4361761993 hasRelatedWork W2922421953 @default.
- W4361761993 hasRelatedWork W3002270006 @default.
- W4361761993 hasRelatedWork W4281560450 @default.
- W4361761993 hasVolume "11" @default.
- W4361761993 isParatext "false" @default.
- W4361761993 isRetracted "false" @default.
- W4361761993 workType "article" @default.