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.

摘要

本研究旨在比较和评估不同的基于地理对象的图像分析 (GEOBIA) 和使用无人机 (UAV) 多光谱图像的机器学习算法。提供了两个研究地点，位于卡拉布里亚（意大利）的佛手柑和洋葱作物。集成到 Orfeo ToolBox (OTB) 套件中的大规模均值偏移 (LSMS)、在 Python 遥感和地理信息系统软件库 (RSGISLib) 中实现的 Shepherd 算法以及多分辨率分割 (MRS) 算法在 eCognition 中实施，进行了测试。评估了四种分类算法：K-最近邻 (KNN)、支持向量机 (SVM)、随机森林 (RF) 和正态贝叶斯 (NB)。使用几何和非几何索引比较获得的分割，而分类结果在总体、用户和生产者的准确性以及多类F-scoreM方面进行了比较。使用 McNemar 检验评估分类准确度输出的统计显着性。SVM 和 RF 是最稳定的分类器，受所用软件和场景特征的影响较小，OA 值从未低于 81.0% 和 91.20%。NB 算法使用 OTB 和 eCognition 在 Orchard-study 站点中获得了最高的 OA。在 Scikit-learn 中执行的 NB 结果较低（73.80%）。RF 和 SVM 在作物研究站点获得 OA>90%。SVM 和 RF 是最稳定的分类器，受所用软件和场景特征的影响较小，OA 值从未低于 81.0% 和 91.20%。NB 算法使用 OTB 和 eCognition 在 Orchard-study 站点中获得了最高的 OA。在 Scikit-learn 中执行的 NB 结果较低（73.80%）。RF 和 SVM 在作物研究站点获得 OA>90%。SVM 和 RF 是最稳定的分类器，受所用软件和场景特征的影响较小，OA 值从未低于 81.0% 和 91.20%。NB 算法使用 OTB 和 eCognition 在 Orchard-study 站点中获得了最高的 OA。在 Scikit-learn 中执行的 NB 结果较低（73.80%）。RF 和 SVM 在作物研究站点获得 OA>90%。