Evaluation Method of Remote Sensing Information Similarity Based on Topological Relationship

Abstract

The method for evaluating the similarity of remote sensing information based on topological relationships includes steps: S1, determining the ideal solution corresponding to each metadata item based on the user's retrieval conditions, thereby establishing an ideal matter element; S2, establishing an alternative matter element for the candidate remote sensing information; S3. Calculate the similarity between each metadata item in the candidate matter element and the ideal solution; S4. Determine the weight of each metadata item according to the user's retrieval history; S5. According to the weight of each metadata item and each element calculated in S3 The similarity between the data item and the corresponding ideal solution calculates the overall similarity between the candidate matter-element and the ideal matter-element. The present invention builds a correlation function based on topological relationships, fully considers the characteristics of remote sensing information and changes in user needs, and can more accurately describe the satisfaction degree of the information to be returned on each metadata item to the user's needs, ensuring the accuracy of the final return result .

Description

technical field [0001] The invention relates to the technical field of image retrieval, in particular to a method for evaluating the similarity of remote sensing information based on topological relationships. Background technique [0002] With the development of earth observation technology, data of different imaging methods, different bands and resolutions coexist, and remote sensing information is increasingly diversified; the amount of remote sensing information data has increased significantly, and has grown exponentially; the speed of data acquisition has accelerated, and the update cycle has shortened. The timeliness is getting stronger and stronger. [0003] The application of remote sensing information has increasingly penetrated into many fields such as national defense, surveying and mapping, urban management, agriculture, and forestry. In order to quickly find the required remote sensing information, most remote sensing information sharing platforms (remote sens...

AI Technical Summary

Problems solved by technology

However, the user satisfaction of search results is generally not high. The reason is that remote sensing information is different from ordinary text data or web page information. It not only has spatial characteristics and spatial relationship characteristics, but also has multi-scale and multi-temporal characteristics.

Therefore, in the face of multi-source and heterogeneous massive remote sensing information, the existing document-oriented similarity evaluation and ranking methods cannot play an effective role.

Images