Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Segmentation d'images de télédétection par apprentissage profond× | U-Net× | |
|---|---|---|
| Domaine≠ | Télédétection | Apprentissage profond |
| Famille | Machine learning | Machine learning |
| Année d'origine≠ | 2017 | 2015 |
| Auteur d'origine≠ | Zhu et al. | Ronneberger, O., Fischer, P., & Brox, T. |
| Type≠ | Supervised deep learning image analysis | Encoder-decoder convolutional network with skip connections |
| Source fondatrice≠ | Zhu, X. X., et al. (2017). Deep learning in remote sensing: A comprehensive review and list of resources. IEEE Geoscience and Remote Sensing Magazine, 5(4), 8–36. DOI ↗ | Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. In N. Navab et al. (Eds.), Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, LNCS 9351 (pp. 234–241). Springer. DOI ↗ |
| Alias≠ | Deep Learning Remote Sensing, DL-based Remote Sensing Analysis, Neural Remote Sensing Segmentation, Derin Uzaktan Algılama | U-Net, UNet, encoder-decoder with skip connections, fully convolutional segmentation network |
| Apparentées≠ | 2 | 3 |
| Résumé≠ | Deep Learning for Remote Sensing Image Segmentation applies convolutional neural networks and encoder-decoder architectures to automatically classify and delineate objects in satellite or aerial imagery at the pixel level. Systematically reviewed by Zhu et al. (2017) in IEEE Geoscience and Remote Sensing Magazine, this paradigm unified previously fragmented approaches — scene classification, object detection, and semantic segmentation — under a single learned-feature framework capable of exploiting the spatial, spectral, and temporal richness of remote sensing data. | U-Net is a fully convolutional encoder-decoder architecture, introduced by Ronneberger, Fischer, and Brox at MICCAI 2015, that produces dense pixel-wise segmentation masks by combining a contracting path that captures context with a symmetric expanding path that enables precise localization — all bridged by skip connections that preserve fine spatial detail. It established the standard baseline for biomedical image segmentation and has since become one of the most widely adopted architectures for any pixel-level prediction task. |
| ScholarGateJeu de données ↗ |
|
|