Typical ship target identification method based on graded invariance features

Abstract

The invention provides a typical ship target identification method based on graded invariance features. At first, the binary entropy and the normalized inertia moment of each image ship target are extracted as the primary feature; and then each image is subjected to wavelet decomposition to form four sub-images, and the weighted Hu moment, Zernike moment, and Fourier descriptor of the each sub-image ship target are extracted to be the secondary feature; the polar coordinate shape matrix of each image ship target is taken as the trinary feature; and all of the features are modified to have the properties of translation, rotation, and scaling invariance. The experimental result of a recognition classifier shows that the algorithm can describe the typical ship targets in satellite remote sensing images in details step by step, and the recognition accuracy is high. The method can be applied to the typical ship target recognition of the satellite remote sensing image database, and is an engineering method that is high in universality.

Description

technical field [0001] The invention relates to a typical ship target recognition method of satellite remote sensing images, in particular to a typical ship target recognition method based on hierarchical invariant features, which belongs to the field of aerospace remote sensing. Background technique [0002] With the rapid growth of my country's maritime security interests, optical remote sensing satellites can observe a large area of ​​the earth, accurately perceive and obtain marine information, and provide timely decision support, which will help quickly resolve marine emergencies. On-orbit identification of marine ship targets through remote sensing satellites can quickly obtain information such as the position and type of ship targets, which can meet the user's application requirements for marine target monitoring. [0003] Shape is the main feature for detection and recognition of typical ship targets. The shape characteristics of typical ship targets in satellite im...

AI Technical Summary

Problems solved by technology

However, the Zernike moments are still global features, and based on such features, it is not easy to identify targets with local nuances.

The Fourier descriptor can characterize the closed contour of the target, but the Fourier descriptor measures the distance of the entire boundary of the shape, so the recognition ability of the ship target with local nuances is not high

[0004] Looking at the existing classic feature extraction algorithms, the advantages are that they have a solid theoretical foundation and stable performance, but they have limited ability to represent the shape of the target and cannot accurately reflect local details.

The number of typical ship target pixels in satellite images is very small. To identify specific types, every detail on the target shape contributes to the recognition. These feature extraction algorithms cannot meet the actual requirements of typical ship target type recognition

Images