High-resolution remote sensing image plane extraction method based on skeleton characteristic

Abstract

The invention discloses a high-resolution remote sensing image plane extraction method based on skeleton characteristics, comprising the following steps: selecting a remote sensing image edge detection algorithm based on embedded confidence coefficient for edge detection, and realizing the remote sensing image edge detection algorithm based on embedded confidence coefficient; vectorizing a groundfeature target edge; extracting a ground feature skeleton base line from the vector edge of a ground feature based on a constraint Delaunay triangulation network algorithm; carrying out the target main skeleton extraction algorithm based on a binary tree structure; carrying out feature analysis on the target main skeleton of the plane; and realizing the automatic identification method of a plane target. By means of the invention, the plane target can be automatically identified and extracted and better identification extraction effect is obtained. The plane target skeleton has the excellent characteristics of rotation invariance and high discrimination index with other ground features, the vector edge of the ground feature target can be efficiently and precisely extracted from a remote sensing image with high spatial resolution, and the improved target skeleton can be extracted.

Description

Technical field [0001] The invention relates to a method for extracting remote sensing image information, in particular to a method for extracting high-resolution remote sensing image aircraft based on skeleton feature analysis. Background technique [0002] Target recognition belongs to the category of pattern recognition (Pattern Recognition), and can also be understood as image recognition in a narrow sense. Target recognition is based on target feature extraction, because feature extraction is closely related to target recognition: feature extraction is based on the study of target and environmental characteristics, and aims to extract quantitative features that reflect the essential attributes of the target. These feature vectors are the target The separation from the environment creates conditions. Target recognition is based on feature extraction. The target is separated from the background based on the features of the target object obtained during the feature extraction ...

AI Technical Summary

Problems solved by technology

[0014] Although some progress has been made in aircraft target recognition, the current vector-based methods for automatically identifying aircraft targets have weak centralized recognition capabilities, which is reflected in the fact that most aircraft target recognition methods are based on more detailed aircraft target geometric features, such as fuselage length, wing length etc.

In the real world, new types of aircraft targets emerge in endlessly. Since the geometric characteristics of various types of aircraft are not the same, if many types of aircraft are identified, it will take a lot of manpower and material resources to build a huge aircraft corresponding to each aircraft type. feature sample library

However, the acquisition of aircraft features sometimes involves military secrets, and it is difficult to obtain them comprehensively.

Images