Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386453675> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4386453675 endingPage "1" @default.
- W4386453675 startingPage "1" @default.
- W4386453675 abstract "There have been significant advancements in deep learning based object detection algorithms, which have found widespread applications across various fields, including remote sensing. However, existing algorithms often fall short in detecting complex objects in remote sensing images, resulting in suboptimal overall performance. To address this issue, this letter proposes a novel object detection algorithm called OYOLO, which builds upon the YOLOv4 network and incorporates several optimization techniques. Firstly, a novel feature enhancement network is designed to better learn the contextual information and the object feature. Specifically, this section introduces Adaptive Spatial Feature Fusion and proposes an optimized Spatial Pyramid Pooling method, <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>i.e</i> ., SPPCPC. Furthermore, the Effective Intersection over Union loss function is introduced to refine the bounding box regression, thereby minimizing the interference of non-essential features. Lastly, this letter proposes an improved backbone network, <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>i.e</i> ., DSCDarknet53 to enhance the detection speed of the model. Verified through experiments, OYOLO demonstrates an increase of 2.1% and 1.6% in mean Average Precision (mAP) values on the TGRS-HRRSD and RSOD datasets, respectively, compared to the original YOLOv4 algorithm. The detection speeds of the two datasets are also enhanced by 5.3 Frame Per Second (FPS) and 5.3 FPS, respectively. Specifically, OYOLO exhibits remarkable improvements on a dataset with complex objects, with an mAP gain of 7.9%. Moreover, experimental results demonstrate that OYOLO outperforms other YOLO methods." @default.
- W4386453675 created "2023-09-06" @default.
- W4386453675 creator A5004345759 @default.
- W4386453675 creator A5066989731 @default.
- W4386453675 creator A5084574747 @default.
- W4386453675 date "2023-01-01" @default.
- W4386453675 modified "2023-09-27" @default.
- W4386453675 title "OYOLO: An Optimized YOLO Method for Complex Objects in Remote Sensing Image Detection" @default.
- W4386453675 doi "https://doi.org/10.1109/lgrs.2023.3312168" @default.
- W4386453675 hasPublicationYear "2023" @default.
- W4386453675 type Work @default.
- W4386453675 citedByCount "0" @default.
- W4386453675 crossrefType "journal-article" @default.
- W4386453675 hasAuthorship W4386453675A5004345759 @default.
- W4386453675 hasAuthorship W4386453675A5066989731 @default.
- W4386453675 hasAuthorship W4386453675A5084574747 @default.
- W4386453675 hasConcept C115961682 @default.
- W4386453675 hasConcept C124101348 @default.
- W4386453675 hasConcept C126042441 @default.
- W4386453675 hasConcept C127413603 @default.
- W4386453675 hasConcept C138885662 @default.
- W4386453675 hasConcept C142575187 @default.
- W4386453675 hasConcept C146978453 @default.
- W4386453675 hasConcept C147037132 @default.
- W4386453675 hasConcept C153180895 @default.
- W4386453675 hasConcept C154945302 @default.
- W4386453675 hasConcept C2524010 @default.
- W4386453675 hasConcept C2776151529 @default.
- W4386453675 hasConcept C2776401178 @default.
- W4386453675 hasConcept C2781238097 @default.
- W4386453675 hasConcept C33923547 @default.
- W4386453675 hasConcept C41008148 @default.
- W4386453675 hasConcept C41895202 @default.
- W4386453675 hasConcept C52622490 @default.
- W4386453675 hasConcept C63584917 @default.
- W4386453675 hasConcept C64543145 @default.
- W4386453675 hasConcept C70437156 @default.
- W4386453675 hasConcept C76155785 @default.
- W4386453675 hasConceptScore W4386453675C115961682 @default.
- W4386453675 hasConceptScore W4386453675C124101348 @default.
- W4386453675 hasConceptScore W4386453675C126042441 @default.
- W4386453675 hasConceptScore W4386453675C127413603 @default.
- W4386453675 hasConceptScore W4386453675C138885662 @default.
- W4386453675 hasConceptScore W4386453675C142575187 @default.
- W4386453675 hasConceptScore W4386453675C146978453 @default.
- W4386453675 hasConceptScore W4386453675C147037132 @default.
- W4386453675 hasConceptScore W4386453675C153180895 @default.
- W4386453675 hasConceptScore W4386453675C154945302 @default.
- W4386453675 hasConceptScore W4386453675C2524010 @default.
- W4386453675 hasConceptScore W4386453675C2776151529 @default.
- W4386453675 hasConceptScore W4386453675C2776401178 @default.
- W4386453675 hasConceptScore W4386453675C2781238097 @default.
- W4386453675 hasConceptScore W4386453675C33923547 @default.
- W4386453675 hasConceptScore W4386453675C41008148 @default.
- W4386453675 hasConceptScore W4386453675C41895202 @default.
- W4386453675 hasConceptScore W4386453675C52622490 @default.
- W4386453675 hasConceptScore W4386453675C63584917 @default.
- W4386453675 hasConceptScore W4386453675C64543145 @default.
- W4386453675 hasConceptScore W4386453675C70437156 @default.
- W4386453675 hasConceptScore W4386453675C76155785 @default.
- W4386453675 hasFunder F4320321001 @default.
- W4386453675 hasFunder F4320322769 @default.
- W4386453675 hasFunder F4320335769 @default.
- W4386453675 hasLocation W43864536751 @default.
- W4386453675 hasOpenAccess W4386453675 @default.
- W4386453675 hasPrimaryLocation W43864536751 @default.
- W4386453675 hasRelatedWork W2756241593 @default.
- W4386453675 hasRelatedWork W2801801420 @default.
- W4386453675 hasRelatedWork W2894878591 @default.
- W4386453675 hasRelatedWork W2921865287 @default.
- W4386453675 hasRelatedWork W2974375613 @default.
- W4386453675 hasRelatedWork W3130645678 @default.
- W4386453675 hasRelatedWork W3197089899 @default.
- W4386453675 hasRelatedWork W4285742308 @default.
- W4386453675 hasRelatedWork W4297824084 @default.
- W4386453675 hasRelatedWork W4386099271 @default.
- W4386453675 isParatext "false" @default.
- W4386453675 isRetracted "false" @default.
- W4386453675 workType "article" @default.