Ghost community identification and housing vacancy rate estimation method based on multi-source remote sensing data

Abstract

The invention discloses a ghost community identification and housing vacancy rate estimation method based on multi-source remote sensing data. According to the method, large-scale multi-source remotesensing data products with spatial resolution advantages are comprehensively applied, ghost city phenomenon evaluation indexes suitable for block scales are constructed, a threshold setting method with regional difference adaptability is sought, and block scale ghost city identification in the whole country is realized; on the basis, a housing vacancy rate estimation model suitable for the block scale is constructed in combination with network streetscape real-time videos and field survey data, and the nationwide housing vacancy rate is estimated.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a ghost community identification and housing vacancy rate estimation based on multi-source remote sensing data. Background technique [0002] The impulse of local planning and construction of new towns and new districts has significantly increased the risk of the phenomenon of "ghost towns". According to the survey by the National Development and Reform Commission's Urban and Small Town Reform and Development Center, as of May 2016, the number of new towns and new districts at or above the county level in the country has reached more than 3,500 , can accommodate a population of 3.4 billion. Comparing the planned population capacity of Xincheng New District (3.4 billion) with the current national total population (approximately 1.39 billion at the end of 2018), it can be found that the number of people that Xincheng New District can accommodate far exceeds the total population of t...

AI Technical Summary

Problems solved by technology

The housing vacancy rate is the most intuitive evaluation indicator for the severity of the "ghost town" phenomenon. The current research's identification accuracy of "ghost towns" limits the estimation of the housing vacancy rate of "ghost towns".

On the other hand, the current research on the housing vacancy rate is also limited by the data accuracy and cannot accurately identify "ghost towns", so the housing vacancy rate of "ghost towns" cannot be obtained

[0004] At present, the identification of "ghost cities" faces the following challenges: 1) The coverage of current research areas is generally small, mostly typical cities and typical areas, and there are few studies on the identification of "ghost cities" nationwide; 2) The spatial resolution of basic data is limited. The recognition accuracy of "ghost towns" stays at the county / district and above administrative units, and it is impossible to identify the precise coverage area of ​​"ghost towns" in the city; 3) The current threshold setting of "ghost towns" indicators is based on rankings, standard deviations, etc. , has a certain degree of subjectivity, and fails to consider the regional differences of cities, which will affect the accuracy and credibility of the "ghost town" recognition results

[0005] The housing vacancy rate is the most fundamental quantitative indicator for the identification of "ghost towns". However, current studies have not considered the identification of "ghost towns" through the housing vacancy rate. The official data of the housing vacancy rate can be used for reference, and there is no authoritative threshold setting standard, that is, how much the housing vacancy rate is higher than that belongs to a "ghost town"; It is also difficult to identify "ghost towns" in terms of method construction. Identifying "ghost towns" by estimating the housing vacancy rate faces problems such as difficulty, low efficiency, and high instability.

Images