Influence of Building Recognition of High-point Monitoring Image by the Optimized Faster R-CNN on Urban Planning

Abstract

The purpose of the study is to obtain more powerful data in the process of urban planning, and more excellent building recognition algorithms for the high-point monitoring images in the city.26 A new algorithm based on Faster R-CNN (Faster Regions-Convolutional Neural Networks) is proposed, and the optimization methods involved are systematically described, and then a simple description of the Faster R-CNN algorithm is made for optimization. Subsequently, experiments are carried out on the MS COCO (Microsoft Common Objects in Context) datasets, and a series of relevant experimental demonstrations are conducted on the optimization scheme. Different features are used to extract networks; some practical optimization methods are added and the training method is modified; the speed and accuracy are paid attention to, and the expected goal of target detection is achieved. Based on this high-point monitoring image, the speed and accuracy of building recognition are greatly optimized. Urban managers will have more reliable information in urban planning, which has a positive impact on urban development.