Multi-source remote sensing information knowledge graph construction method and system for target interpretation

Abstract

The invention discloses a multi-source remote sensing information knowledge graph construction method and system for target interpretation, and the method comprises the steps: carrying out the automatic interpretation of a to-be-processed multi-source remote sensing image according to an attribute feature recognition algorithm model group, and obtaining interpretation information; in combination with a remote sensing image automatic interpretation knowledge graph framework, performing primary classification and archiving on interpreted information to obtain a target automatic interpretation primary fusion information table; according to the target automatic interpretation primary fusion information table, in combination with a typical remote sensing target interpretation analysis ontologylibrary, performing entity construction of interpretation information to obtain a knowledge graph model; and expanding the knowledge graph model, and updating and complementing the historical knowledge graph according to the expanded knowledge graph model to complete the knowledge extraction of the interpreted information. According to the method, automatic extraction of typical targets of multi-source remote sensing images and comprehensive summarization of interpreted information of the remote sensing images can be completed, and a knowledge map with a standardized representation form is formed.

Description

technical field [0001] The invention belongs to the technical field of remote sensing target interpretation, and in particular relates to a target interpretation-oriented multi-source remote sensing information knowledge graph construction method and system. Background technique [0002] With the rapid development of earth observation technology, human beings' ability to observe the earth has reached an unprecedented level. Satellite loads of different imaging methods, different bands and resolutions have made remote sensing data increasingly diversified, and the amount of remote sensing data has also increased significantly. The update cycle has been shortened and the timeliness has become stronger and stronger. Therefore, remote sensing observation data presents obvious characteristics of "big data". [0003] In the process of traditional remote sensing image target interpretation, it is necessary to rely on the knowledge and experience of remote sensing experts, and at t...

AI Technical Summary

Problems solved by technology

[0003] In the process of traditional remote sensing image target interpretation, it is necessary to rely on the knowledge and experience of remote sensing experts, and at the same time, a large amount of data can be consulted before the interpretation results can be obtained. The workload is heavy and the efficiency is low.

Images