Comparer des méthodes

	Segmentation d'images de télédétection par apprentissage profond	Analyse d'images basée sur les objets (OBIA)
Domaine	Télédétection	Télédétection
Famille	Machine learning	Process / pipeline
Année d'origine	2017	2010
Auteur d'origine	Zhu et al.	Thomas Blaschke
Type	Supervised deep learning image analysis	Image segmentation and classification pipeline
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.	Blaschke, T. (2010). Object based image analysis for remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 65(1), 2–16.
Alias	Deep Learning Remote Sensing, DL-based Remote Sensing Analysis, Neural Remote Sensing Segmentation, Derin Uzaktan Algılama	Geographic Object-Based Image Analysis, GEOBIA, Object-Oriented Image Analysis, Nesne Tabanlı Görüntü Analizi
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.	Object-Based Image Analysis (OBIA) is a remote sensing image processing paradigm that groups pixels into meaningful image objects before classification, rather than analysing each pixel independently. Formally articulated and consolidated by Thomas Blaschke in his landmark 2010 ISPRS review, OBIA draws on multiresolution segmentation algorithms and combines spectral, spatial, contextual, and textural object attributes to produce semantically rich land-cover maps from high-resolution imagery.