Intelligent Analysis of Urban Green Zones Based on Unmanned Aerial Vehicle Data
Abstract
Urban green zones play a critical role in maintaining ecological stability, improving air quality, mitigating the urban heat island effect, and supporting public health in rapidly urbanizing environments. However, continuous and accurate monitoring of urban vegetation remains a significant challenge due to heterogeneous land cover, shadow effects, and complex background structures typical of urban landscapes. Traditional ground-based surveys are time-consuming, labor-intensive, and often lack spatial completeness. This study proposes an integrated intelligent approach for the assessment of urban green zones based on unmanned aerial vehicle (UAV) data. The proposed method combines spectral vegetation analysis using the Normalized Difference Vegetation Index (NDVI) with complementary color and texture features extracted from high-resolution RGB and multispectral imagery. Image preprocessing, vegetation segmentation, feature extraction, and classification stages are systematically integrated into a unified processing pipeline. Experimental results obtained under real urban conditions demonstrate that the proposed method significantly improves vegetation health classification accuracy compared to conventional NDVI-based assessment. The integration of spectral, color, and texture descriptors enhances robustness against urban-specific distortions such as shadows and asphalt surfaces. The developed approach provides a computationally efficient, interpretable, and scalable solution for intelligent ecological monitoring and sustainable urban environmental management.