Research on Land Use Classification Based on Remote Sensing Technology

It had been increasingly widespread for the application of remote sensing technology in the field of land use classification, and it also had become a focal point at the forefront of scientific and technological innovation with research on achieving high precision and rapid classification. Numerous innovative classification principles and methods had been emerged as technology continuously evolves. This study summarized the research of predecessors, and reviewed remote sensing image classification techniques comprehensively, such as BP neural networks, support vector machines, random forests, and decision tree classification, and conducts an in-depth analysis of the advantages and limitations of these methods. In addition, the study also summarizes several types remote sensing inversion index formulas which were used widely, for example, Normalized Difference Vegetation Index(NDVI), Normalized Difference Build-up Index(NDBI), Soil Adjusted Vegetation Index (SAVI), Modified Normalized Difference Water Index(MNDWI), Red Edge Normalized Difference Vegetation Index(RENDVI), Modified Red Edge Normalized Difference Vegetation Index(MRENDVI), Red-Green Ratio Index(RGRI), Enhanced Vegetation Index(EVI), ratio vegetation index(RVI), Difference Vegetation Index(DVI), Enhanced Vegetation Index(EVI), and so on. And it also discussed potential and prospects in land use classification. The study further outlined the technical process adopted by remote sensing technology in land use classification and provided insights into the limitations of current technology, while also conducting a forward-looking discussion on the future development path of land use classification technology.