Matches in SemOpenAlex for { <https://semopenalex.org/work/W2987305265> ?p ?o ?g. }
- W2987305265 endingPage "2525" @default.
- W2987305265 startingPage "2525" @default.
- W2987305265 abstract "Multi-class detection in remote sensing images (RSIs) has garnered wide attention and introduced several service applications in many fields, including civil and military fields. However, several reasons make detection from aerial images very challenging and more difficult than nature scene images: Objects do not have a fixed size, often appear at very various scales and sometimes appear in dense groups, like vehicles and storage tanks, and have different surroundings or background areas. Furthermore, all of this makes the manual annotation of objects very complex and costly. The powerful effect of the feature extraction methods on object detection and the successes of deep convolutional neural networks (CNN) extract deep features more than traditional methods. This study introduced a novel network structure and designed a unique feature extraction which employs squeeze and excitation network (SENet) and residual network (ResNet) to obtain feature maps, named a shallow-deep feature extraction (SDFE), that improves the resolution and the localization at the same time. Furthermore, this novel model reduces the loss of dense groups and small objects, and provides higher and more stable detection accuracy which is not significantly affected by changing the value of the threshold of the intersection over union (IoU) and overcomes the difficulties of RSIs. Moreover, this study introduced strong evidence about the factors that affect the detection of RSIs. The proposed shallow-deep and multi-scale (SD-MS) method outperforms other approaches for the given ten classes of the NWPU VHR-10 dataset." @default.
- W2987305265 created "2019-11-22" @default.
- W2987305265 creator A5003254047 @default.
- W2987305265 creator A5053931437 @default.
- W2987305265 creator A5067624332 @default.
- W2987305265 creator A5068367341 @default.
- W2987305265 creator A5069181198 @default.
- W2987305265 creator A5088658340 @default.
- W2987305265 date "2019-10-29" @default.
- W2987305265 modified "2023-10-16" @default.
- W2987305265 title "Multi-Scale Geospatial Object Detection Based on Shallow-Deep Feature Extraction" @default.
- W2987305265 cites W1533693043 @default.
- W2987305265 cites W1970782782 @default.
- W2987305265 cites W2003059629 @default.
- W2987305265 cites W2005368619 @default.
- W2987305265 cites W2017448754 @default.
- W2987305265 cites W2064094295 @default.
- W2987305265 cites W2085625911 @default.
- W2987305265 cites W2088049833 @default.
- W2987305265 cites W2100503224 @default.
- W2987305265 cites W2109255472 @default.
- W2987305265 cites W2168356304 @default.
- W2987305265 cites W2183182206 @default.
- W2987305265 cites W2308318555 @default.
- W2987305265 cites W2412558220 @default.
- W2987305265 cites W2512351403 @default.
- W2987305265 cites W2615211237 @default.
- W2987305265 cites W2733535455 @default.
- W2987305265 cites W2774989306 @default.
- W2987305265 cites W2783231089 @default.
- W2987305265 cites W2789436332 @default.
- W2987305265 cites W2789609993 @default.
- W2987305265 cites W2800388963 @default.
- W2987305265 cites W2804356489 @default.
- W2987305265 cites W2884367402 @default.
- W2987305265 cites W2888493720 @default.
- W2987305265 cites W2890319410 @default.
- W2987305265 cites W2904480641 @default.
- W2987305265 cites W2936226716 @default.
- W2987305265 cites W2963420686 @default.
- W2987305265 cites W3106141888 @default.
- W2987305265 cites W4239510810 @default.
- W2987305265 cites W639708223 @default.
- W2987305265 doi "https://doi.org/10.3390/rs11212525" @default.
- W2987305265 hasPublicationYear "2019" @default.
- W2987305265 type Work @default.
- W2987305265 sameAs 2987305265 @default.
- W2987305265 citedByCount "19" @default.
- W2987305265 countsByYear W29873052652020 @default.
- W2987305265 countsByYear W29873052652021 @default.
- W2987305265 countsByYear W29873052652022 @default.
- W2987305265 countsByYear W29873052652023 @default.
- W2987305265 crossrefType "journal-article" @default.
- W2987305265 hasAuthorship W2987305265A5003254047 @default.
- W2987305265 hasAuthorship W2987305265A5053931437 @default.
- W2987305265 hasAuthorship W2987305265A5067624332 @default.
- W2987305265 hasAuthorship W2987305265A5068367341 @default.
- W2987305265 hasAuthorship W2987305265A5069181198 @default.
- W2987305265 hasAuthorship W2987305265A5088658340 @default.
- W2987305265 hasBestOaLocation W29873052651 @default.
- W2987305265 hasConcept C108583219 @default.
- W2987305265 hasConcept C11413529 @default.
- W2987305265 hasConcept C138885662 @default.
- W2987305265 hasConcept C153180895 @default.
- W2987305265 hasConcept C154945302 @default.
- W2987305265 hasConcept C155512373 @default.
- W2987305265 hasConcept C205649164 @default.
- W2987305265 hasConcept C2776151529 @default.
- W2987305265 hasConcept C2776401178 @default.
- W2987305265 hasConcept C2778755073 @default.
- W2987305265 hasConcept C2781238097 @default.
- W2987305265 hasConcept C41008148 @default.
- W2987305265 hasConcept C41895202 @default.
- W2987305265 hasConcept C52622490 @default.
- W2987305265 hasConcept C58640448 @default.
- W2987305265 hasConcept C62649853 @default.
- W2987305265 hasConcept C64543145 @default.
- W2987305265 hasConcept C81363708 @default.
- W2987305265 hasConcept C9770341 @default.
- W2987305265 hasConceptScore W2987305265C108583219 @default.
- W2987305265 hasConceptScore W2987305265C11413529 @default.
- W2987305265 hasConceptScore W2987305265C138885662 @default.
- W2987305265 hasConceptScore W2987305265C153180895 @default.
- W2987305265 hasConceptScore W2987305265C154945302 @default.
- W2987305265 hasConceptScore W2987305265C155512373 @default.
- W2987305265 hasConceptScore W2987305265C205649164 @default.
- W2987305265 hasConceptScore W2987305265C2776151529 @default.
- W2987305265 hasConceptScore W2987305265C2776401178 @default.
- W2987305265 hasConceptScore W2987305265C2778755073 @default.
- W2987305265 hasConceptScore W2987305265C2781238097 @default.
- W2987305265 hasConceptScore W2987305265C41008148 @default.
- W2987305265 hasConceptScore W2987305265C41895202 @default.
- W2987305265 hasConceptScore W2987305265C52622490 @default.
- W2987305265 hasConceptScore W2987305265C58640448 @default.
- W2987305265 hasConceptScore W2987305265C62649853 @default.
- W2987305265 hasConceptScore W2987305265C64543145 @default.
- W2987305265 hasConceptScore W2987305265C81363708 @default.
- W2987305265 hasConceptScore W2987305265C9770341 @default.