Urban green land high-resolution remote sensing monitoring method and system

Abstract

The invention relates to an urban green land high-resolution remote sensing monitoring method and system, and the method comprises a training sample set construction step, a multi-dimensional featurespace construction step, a UNet + model construction step, and an image post-processing step, and comprises the steps: constructing a multi-dimensional feature space, enhancing the feature richness, and constructing a UNet + deep learning model at the same time; and by combining an image post-processing method, improving generalization and robustness of the monitoring method to solve the overfitting problem which is easy to occur due to limited training samples, so that the precision and timeliness of urban green land high-resolution remote sensing monitoring are improved.

Description

technical field [0001] The invention relates to the technical field of remote sensing monitoring, in particular to a high-resolution remote sensing monitoring method and system for urban green spaces. Background technique [0002] Urban green space plays a very important role in the urban ecosystem and is closely related to human health, quality of life of residents, biodiversity, and social security. The distribution of urban green space is heterogeneous and highly dispersed. How to accurately quantify the spatio-temporal pattern of urban green space is a hot issue in current research and is crucial to urban green space planning and management. [0003] At present, there have been a large number of studies on the classification and extraction of urban green space. With the development of remote sensing technology, more and more high-resolution remote sensing images are used in urban green space mapping and change analysis, such as SPOT, IKONOS, Quick-Bird, Worldview, high ...

AI Technical Summary

Problems solved by technology

For example, the structure of the model, the generalization and robustness of the model, the calculation mode of the loss function, etc.; especially the small-scale image data set will cause the over-fitting of the deep learning model, the robustness of the model and the deterioration of the generalization ability of the model. And other issues

(2) Insufficient richness of feature learning

The number of bands of Gaofen-2 remote sensing images is limited, the spectral information is relatively lacking, and the richness of features is less, which limits the richness of deep learning in feature learning to a certain extent.

(3) Model misclassification problem

Images