earticle

영어

High-resolution land cover maps are essential in fields such as forest resource management, urban green space planning, and environmental protection. In recent years, Unmanned Aerial Vehicles (UAVs) have increasingly become influential in land cover mapping due to their flexibility, low cost, and fast data acquisition capability. However, accurately classifying high-resolution image data collected by UAVs remains a challenge due to the complexity of the data and the substantial computational resources required for processing. To address this problem, this study combines UAV remote sensing data with Object-Based Image Analysis (OBIA) to optimize feature selection to improve the accuracy of land cover classification and provide more reliable data support. In this study, combinations of four feature types were evaluated using a Decision Tree (DT) algorithm in eight scenarios. The results showed that a comparison with spectral features alone and the combination of other feature types can significantly improve the classification accuracy. Height features contribute the most to enhancing the classification results, followed by spectral and geometric features, while the contribution of texture features is relatively limited. In addition, the optimal feature combination selected by the Recursive Feature Elimination (RFE) method further validates its effectiveness in improving land cover classification results. Finally, the best feature combination achieved a classification accuracy of 72.00% and a Kappa coefficient of 0.6543, proving the effectiveness of the feature selection and optimization strategy.