Object-Based Classification of Greenhouses Using Sentinel-2 MSI and SPOT-7 Images: A Case Study from Anamur (Mersin), Turkey

Abstract

Accurate and reliable greenhouse mapping using remotely sensed data and image classification methods has a significant role since it can comprehensively improve the urban and rural planning, and sustainable natural resource and agricultural management. This research is mainly focused on the determination of greenhouses from SPOT-7 and Sentinel-2 MultiSpectral Instrument (MSI) images by using an object-based image classification method with three different classifiers which are k-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM) in the selected test region. First, the image acquired by using multi-resolution segmentation. Second, spectral features, textural features, and remote sensing indices were obtained for each image object. Third, different classifiers were employed to classify greenhouses. Then, classification accuracy assessment analysis was conducted to test the agreement between the classified data and field collected data using the confusion matrix. The results highlighted that the KNN and RF classifier have a slightly higher overall accuracy (OA) and Kappa statistics for SPOT-7 image with the 91.43% and 0.88. Furthermore, the KNN classifier for Sentinel-2 MSI image has the highest OA and Kappa statistics of 88.38% and 0.83. The achieved results underlined the potential of Sentinel-2 MSI and SPOT-7 data for object-based greenhouse mapping using different machine learning classifiers in the Mediterranean Region.

Keywords

• Greenhouse mapping
• object-based image analysis (OBIA)
• random forest (RF)
• remote sensing
• Sentinel-2 MultiSpectral Instrument (MSI)
• support vector machine (SVM)