Geographic national condition monitoring result reliability quality inspection method and system

Abstract

The invention discloses a geographic national condition monitoring result reliability quality inspection method and system. The method comprises the following steps: establishing a sample data set byutilizing existing orthoimage data T and mask data; performing enhancement processing on the sample data; on the basis, establishing a deep convolutional neural network model CNN; performing deep enhancement and fusion on the model; secondly, performing super-pixel segmentation on the new time-phase image T2 to obtain feature pattern spots; mapping the data to old time phase surface coverage datato obtain geometric information of the changed pattern spots; thirdly, inputting new time-phase image T2 data into the trained deep convolutional neural network model to obtain semantic information ofthe changed pattern spots; and finally, comparing the change information with the detected land surface coverage data to obtain a suspected missed and leaked area, and comparing the suspected missedand leaked area with the new and old time phase images T1 and T2 for verification to obtain a final land surface coverage change reliability quality inspection result. The method can achieve the quickinspection of the reliability of a remote sensing image change detection result, can be used for the quality inspection and acceptance of a geographic national condition monitoring project, and greatly improves the quality inspection efficiency.

Description

technical field [0001] The invention relates to the technical field of geographic information technology, in particular to a reliability quality inspection method and system for geographic national conditions monitoring results. Background technique [0002] Geographical national conditions monitoring is a new practice and major task for the surveying and mapping geographic information department to serve the development of economic and social sciences in the new era. Land cover data are important basic information for geographic monitoring, global change research, and ecological resource management. At present, land cover change detection has been widely used in land cover and land use monitoring, urban development research, resource management, disaster assessment, ecosystem monitoring, and military applications. In addition, change detection is a key technology for land cover update, and geographical conditions The monitored land cover has a large and complex classificat...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to propose a method for reliability quality inspection of geographical and national conditions monitoring results; this method solves the problems of poor reliability, low efficiency, and low degree of automation in the reliability quality inspection of land cover change detection to a certain extent

Images