Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285697898> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4285697898 abstract "The detection performance of small objects in remote sensing images is not satisfactory compared to large objects, especially in low-resolution and noisy images. A generative adversarial network (GAN)-based model called enhanced super-resolution GAN (ESRGAN) shows remarkable image enhancement performance, but reconstructed images miss high-frequency edge information. Therefore, object detection performance degrades for small objects on recovered noisy and low-resolution remote sensing images. Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we apply a new edge-enhanced super-resolution GAN (EESRGAN) to improve the image quality of remote sensing images and use different detector networks in an end-to-end manner where detector loss is backpropagated into the EESRGAN to improve the detection performance. We propose an architecture with three components: ESRGAN, Edge Enhancement Network (EEN), and Detection network. We use residual-in-residual dense blocks (RRDB) for both the ESRGAN and EEN, and for the detector network, we use the faster region-based convolutional network (FRCNN) (two-stage detector) and single-shot multi-box detector (SSD) (one stage detector). Extensive experiments on a public (car overhead with context) and a self-assembled (oil and gas storage tank) satellite dataset show superior performance of our method compared to the standalone state-of-the-art object detectors." @default.
- W4285697898 created "2022-07-18" @default.
- W4285697898 creator A5003177894 @default.
- W4285697898 creator A5006035862 @default.
- W4285697898 creator A5008285988 @default.
- W4285697898 creator A5048216017 @default.
- W4285697898 creator A5082800075 @default.
- W4285697898 date "2020-03-19" @default.
- W4285697898 modified "2023-09-25" @default.
- W4285697898 title "Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network" @default.
- W4285697898 doi "https://doi.org/10.48550/arxiv.2003.09085" @default.
- W4285697898 hasPublicationYear "2020" @default.
- W4285697898 type Work @default.
- W4285697898 citedByCount "0" @default.
- W4285697898 crossrefType "posted-content" @default.
- W4285697898 hasAuthorship W4285697898A5003177894 @default.
- W4285697898 hasAuthorship W4285697898A5006035862 @default.
- W4285697898 hasAuthorship W4285697898A5008285988 @default.
- W4285697898 hasAuthorship W4285697898A5048216017 @default.
- W4285697898 hasAuthorship W4285697898A5082800075 @default.
- W4285697898 hasBestOaLocation W42856978981 @default.
- W4285697898 hasConcept C108583219 @default.
- W4285697898 hasConcept C111919701 @default.
- W4285697898 hasConcept C11413529 @default.
- W4285697898 hasConcept C151730666 @default.
- W4285697898 hasConcept C153180895 @default.
- W4285697898 hasConcept C154945302 @default.
- W4285697898 hasConcept C155512373 @default.
- W4285697898 hasConcept C162307627 @default.
- W4285697898 hasConcept C205372480 @default.
- W4285697898 hasConcept C2776151529 @default.
- W4285697898 hasConcept C2779343474 @default.
- W4285697898 hasConcept C2779960059 @default.
- W4285697898 hasConcept C2988773926 @default.
- W4285697898 hasConcept C31972630 @default.
- W4285697898 hasConcept C41008148 @default.
- W4285697898 hasConcept C76155785 @default.
- W4285697898 hasConcept C86803240 @default.
- W4285697898 hasConcept C94915269 @default.
- W4285697898 hasConceptScore W4285697898C108583219 @default.
- W4285697898 hasConceptScore W4285697898C111919701 @default.
- W4285697898 hasConceptScore W4285697898C11413529 @default.
- W4285697898 hasConceptScore W4285697898C151730666 @default.
- W4285697898 hasConceptScore W4285697898C153180895 @default.
- W4285697898 hasConceptScore W4285697898C154945302 @default.
- W4285697898 hasConceptScore W4285697898C155512373 @default.
- W4285697898 hasConceptScore W4285697898C162307627 @default.
- W4285697898 hasConceptScore W4285697898C205372480 @default.
- W4285697898 hasConceptScore W4285697898C2776151529 @default.
- W4285697898 hasConceptScore W4285697898C2779343474 @default.
- W4285697898 hasConceptScore W4285697898C2779960059 @default.
- W4285697898 hasConceptScore W4285697898C2988773926 @default.
- W4285697898 hasConceptScore W4285697898C31972630 @default.
- W4285697898 hasConceptScore W4285697898C41008148 @default.
- W4285697898 hasConceptScore W4285697898C76155785 @default.
- W4285697898 hasConceptScore W4285697898C86803240 @default.
- W4285697898 hasConceptScore W4285697898C94915269 @default.
- W4285697898 hasLocation W42856978981 @default.
- W4285697898 hasOpenAccess W4285697898 @default.
- W4285697898 hasPrimaryLocation W42856978981 @default.
- W4285697898 hasRelatedWork W1497101000 @default.
- W4285697898 hasRelatedWork W2145985110 @default.
- W4285697898 hasRelatedWork W2547934522 @default.
- W4285697898 hasRelatedWork W2730449274 @default.
- W4285697898 hasRelatedWork W2782964878 @default.
- W4285697898 hasRelatedWork W2922421953 @default.
- W4285697898 hasRelatedWork W2980691083 @default.
- W4285697898 hasRelatedWork W3002270006 @default.
- W4285697898 hasRelatedWork W4281560450 @default.
- W4285697898 hasRelatedWork W4285602384 @default.
- W4285697898 isParatext "false" @default.
- W4285697898 isRetracted "false" @default.
- W4285697898 workType "article" @default.