Porównaj metody

	Klasyfikacja obrazów oparta na pikselach	Analiza obrazu oparta na obiektach (OBIA)	Random Forest
Dziedzina	Teledetekcja	Teledetekcja	Uczenie maszynowe
Rodzina	Machine learning	Process / pipeline	Machine learning
Rok powstania	2007	2010	2001
Twórca	Remote-sensing classification literature	Thomas Blaschke	Breiman, L.
Typ	Supervised/unsupervised spectral image classification	Image segmentation and classification pipeline	Ensemble (bagging of decision trees)
Źródło pierwotne	Lu, D., & Weng, Q. (2007). A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing, 28(5), 823–870.	Blaschke, T. (2010). Object based image analysis for remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 65(1), 2–16.	Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.
Inne nazwy	Per-Pixel Classification, Spectral Classification, Pixel-by-Pixel Classification, Piksel Tabanlı Sınıflandırma	Geographic Object-Based Image Analysis, GEOBIA, Object-Oriented Image Analysis, Nesne Tabanlı Görüntü Analizi	Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble
Pokrewne	2	3	4
Podsumowanie	Pixel-based image classification is a fundamental remote-sensing technique that assigns each individual pixel in a satellite or aerial image to a thematic land-cover category based solely on its spectral values across multiple bands. Systematically surveyed and formalized by Lu and Weng (2007), the approach encompasses both supervised methods—where labeled training samples guide the classifier—and unsupervised clustering approaches that discover natural spectral groupings without prior labels.	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.	Random Forest is an ensemble learning method, introduced by Leo Breiman in 2001, that grows many decision trees on bootstrap samples of the data and combines their votes to produce strong classification and regression. By pooling many slightly different trees, it produces more accurate and more stable predictions than any single tree.