A Quantification Method of Street Space Quality Based on Machine Learning

Abstract

The present invention provides a method for quantifying street space quality based on machine learning, which mainly involves using semantic segmentation network to quantify the street greenness rate, using the greenness rate as one of the quantified space quality indicators, and using cross-connected convolutional neural network to extract street scenes Image features, the extracted features are used as the input features of the support vector regression model to quantify the quality of street space. The method includes: making a street green view rate data set and training a semantic segmentation network to quantify the street green view rate. Taking the green view rate as one of the spatial quality indicators, a street spatial quality dataset is produced, and then the cross-connected CNN+SVR network is trained to obtain a network model, and the model is used to quantify the street spatial quality on a large scale. The invention gives full play to the advantages of machine learning, reduces the huge workload of researchers in the investigation of street space quality, provides important data support for related research, and provides a new idea for the study of street space quality in the field of urban planning.

Description

Technical field [0001] The present invention relates to a quantitative analysis problem of street spatial quality in the field of image analysis, in particular to a method of quantitative street spatial quality based on machine learning. Background [0002] With the development of science, the combination of artificial intelligence with medical care, education, environmental governance and urban planning will greatly promote the precision of urban public services and comprehensively improve the quality of life of people. Therefore, paying attention to the construction of smart cities is the current hot direction of Our country. Urban public space mainly includes multi-functional areas such as streets, shopping malls, squares and parks, and the streets in them are equivalent to the "bones" of the city. As a stage to show the city's economy and life, the street is also an important window to highlight local characteristics. Good street space quality can not only form a friendly and...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method for quantifying street space quality based on machine learning, combining machine learning with street space quality attributes, giving full play to the advantages of self-learning of machine learning, and solving the problem of the large workload of current researchers investigating street space quality The problem

Images