Comparison and assessment of different object-based classifications using machine learning algorithms and UAVs multispectral imagery: a case study in a citrus orchard and an onion crop. Issue 1 (1st January 2021)

• Record Type: Journal Article
• Authors: Modica, Giuseppe; De Luca, Giandomenico; Messina, Gaetano; Praticò, Salvatore
• Is Part Of: European journal of remote sensing. Volume 54:Issue 1(2021)
• Page Start: 431
• Page End: 460
• Publication Date: 2021-01-01
• Subjects: Precision agriculture (PA) -- Geographic Object-Based Image Analysis (GEOBIA) -- Segmentation and classification accuracy assessment -- Orfeo Toolbox (OTB) -- RGISLib and Scikit-learn -- eCognition; Remote sensing -- Periodicals; Remote sensing; Electronic journals; Periodicals; 621.3678
• DOI: 10.1080/22797254.2021.1951623
• Languages: English
• ISSNs: 2279-7254

Abstract

ABSTRACT: This study aimed to compare and assess different Geographic Object-Based Image Analysis (GEOBIA) and machine learning algorithms using unmanned aerial vehicles (UAVs) multispectral imagery. Two study sites were provided, a bergamot and an onion crop located in Calabria (Italy). The Large-Scale Mean-Shift (LSMS), integrated into the Orfeo ToolBox (OTB) suite, the Shepherd algorithm implemented in the Python Remote Sensing and Geographical Information Systems software Library (RSGISLib), and the Multi-Resolution Segmentation (MRS) algorithm implemented in eCognition, were tested. Four classification algorithms were assessed: K-Nearest Neighbour (KNN), Support Vector Machines (SVM), Random Forests (RF), and Normal Bayes (NB). The obtained segmentations were compared using geometric and non-geometric indices, while the classification results were compared in terms of overall, user's and producer's accuracy, and multi-class F-scoreM. The statistical significance of the classification accuracy outputs was assessed using McNemar's test. The SVM and RF resulted as the most stable classifiers and less influenced by the software used and the scene's characteristics, with OA values never lower than 81.0% and 91.20%. The NB algorithm obtained the highest OA in the Orchard-study site, using OTB and eCognition. NB performed in Scikit-learn results in the lower (73.80%). RF and SVM obtained an OA>90% in the Crop-study site.