Multi-source characteristic integrated SAR image automatic object identification method

Abstract

The invention discloses a multi-source characteristic integrated SAR image automatic object identification method, which aims mainly to solving the problems in the prior art that the identification result is not robust with low probability because of the severe influence brought about by the change in the size, position and rotation of an object as well as by the strong clutters. In this method, the advantages of the cosine Fourier moment characteristics and the peak characteristics are combined so as to perform cascade-connected integration identification to the extracted two kinds of characteristics. The technical schemes comprise the following steps: accessing the SAR images for different targets and the two-dimensional plane projection images of a three-dimensional model and performing standard treatment to these images; using the cosine Fourier invariant moment method to extract the moment characteristics of the projection images obtained from the step 1; using the rayleigh distribution CFAR detection method to extract the SAR image peak characteristics; and utilizing the cascade-connected integration classifier combining the SVM with a matching algorithm to identify the object. The method of the invention is capable of effectively increasing the accurate identifying precision and robustness for an object under the conditions that the characteristic dimension is high and that the attitude changes. In addition, without the additional overhead to a guidance control system, the method can be used to increase the automatic object identification probability of an SAR image.

Description

technical field [0001] The invention belongs to the technical field of radar target recognition, in particular to an automatic target recognition method for multi-source feature fusion of SAR images. It can be used for target classification and recognition in SAR images. Background technique [0002] Synthetic Aperture Radar (SAR), as an active microwave imaging sensor, is applied to the active radar seeker. Interference ability. However, due to the low resolution of SAR imaging, the serious influence of image distortion and background inclusion has brought severe challenges to target recognition. [0003] At present, it is both difficult and hot to study how to increase the utilization rate of target information through multi-source feature fusion of original SAR images, overcome the one-sidedness of single-source sensor in acquiring target information, and improve the accuracy and robustness of automatic target image recognition. On the one hand, because the original SA...

AI Technical Summary

Problems solved by technology

On the one hand, because the original SAR image is sensitive to parameters such as azimuth, the effect of fusing images from different perspectives into an independent image is not ideal

On the other hand, the feature fusion of different categories is very difficult in itself, so the target recognition method of multi-source feature fusion needs further exploration and research

Images