Object-Oriented Multi-Scale Segmentation and Multi-Feature Fusion-Based Method for Identifying Typical Fruit Trees in Arid Regions Using Sentinel-1/2 Satellite Images

Abstract

The rapid and accurate identification of fruit trees provides a foundation for dynamic monitoring of orchard planting areas and estimating orchard yields objectively. This study aims to evaluate the applicability of time series Sentinel-1/2 satellite data for fruit tree classification and to provide a new method for accurately extracting fruit tree categories. Therefore, the study area selected is the Tarim Basin, the most important fruit-growing region in northwest China. The main focus is on the identification of three major fruit tree species in this region. Time series Sentinel-1/2 satellite images acquired from the Google Earth Engine (GEE) platform are used for the study. A multi-scale segmentation approach is applied, and six categories of features including spectral, phenological, texture, polarization, vegetation index, and red edge index features are constructed. A total of 44 features are extracted and optimized using the Vi feature importance index to determine the best time phase. Based on this, an object-oriented segmentation combined with Random Forest (RF) method is used to identify fruit tree categories. The results are compared with three other commonly used traditional machine learning algorithms, including Classification and Regression Tree(CART), Gradient Boosting Decision Tree(GBDT), and Support Vector Machine(SVM)classification methods, to determine the best approach for fruit tree identification. The results show that: (1) the object-oriented segmentation method helps to improve the accuracy of fruit tree identification features; September satellite images provide the best time window for fruit tree identification, with spectral, phenological, and texture features contributing the most to fruit tree category identification; (2) the RF model has a higher accuracy in identifying fruit tree categories than other machine learning models, with an Overall Accuracy (OA) and Kappa Coefficient(KC) of 94.60% and 93.74% respectively, indicating that the combination of object-oriented segmentation and RF algorithm has great value and potential for fruit tree identification and classification. This method can be applied to large-scale fruit tree remote sensing classification and provide an effective technical means for monitoring fruit tree planting areas using medium to high-resolution remote sensing images.