Deep Learning Model Construction of Urban Planning Image Data Processing and Health Intelligence System

Abstract

In order to study the deep learning model of urban planning image data processing and health intelligent system, based on existing remote sensing image change detection methods, the author introduces and proposes the use of deep belief networks in deep learning to classify high-resolution remote sensing images and analyze urban expansion change detection. Compared with traditional methods, deep learning has the highest overall accuracy and Kappa coefficient. Deep learning has the highest producer accuracy and relatively low misjudgment rate, making it the most suitable for studying the trend of urban built-up areas. By calculating the information entropy of the image to predict the number of hidden layer nodes, the time for deep learning is greatly reduced. Under the same experimental conditions, the training time for each image can be shortened by 12 525 seconds has improved classification efficiency and made a significant contribution to research on urban expansion applications. Finally, the improved deep belief network was applied to classify and detect changes in the three phase remote sensing images of Beijing, and the urban expansion trend and characteristics of Beijing were analyzed. Provide technical reference and inspiration for urban planning and land use protection.