SAR target recognition method based on range profile time-frequency image identification dictionary learning

Abstract

The invention provides an SAR target recognition method based on range profile time-frequency image identification dictionary learning. An SAR range profile time-frequency image is used as a recognition feature, so that influence of defocusing caused by target movement or low image quality caused by a factor such as a signal noise ratio on a target recognition effect is avoided; and identification dictionary learning is combined with dictionary learning and classifier training, so that feature information of radar target range profile time-frequency data can be effectively extracted. The invention is conducive to reducing a number of atoms in a dictionary and decreasing operation complexity in a sparse encoding process, and is also conducive to improving precision of sparse encoding, so as to improve recognition accuracy of a radar target. Further, azimuth angle estimation does not need to be performed on an SAR image target in a whole recognition process. Therefore, a recognition complex degree is reduced, and dependency of recognition accuracy on target azimuth angle estimation is also reduced. In addition, the invention has excellent recognition performance, and facilitates improving robust performance of radar target recognition.

Description

technical field [0001] The invention relates to the technical field of radar target recognition, in particular to a SAR target recognition method based on distance image time-frequency map identification dictionary learning. Background technique [0002] Synthetic Aperture Radar (SAR) technology is a pulse radar technology that uses mobile radar mounted on satellites or aircraft to obtain radar target images in high-precision geographic areas. Due to the active imaging characteristics of SAR and the complex scattering mechanism in the imaging process, the target characteristics in SAR images are very different from optical images, which brings many difficulties to target feature extraction and recognition. [0003] Researchers have studied many target recognition algorithms based on two-dimensional SAR images. Among them, the most direct method is to directly use SAR images as features for target recognition. Another radar target recognition method is based on wavelet tran...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the above-mentioned problems existing in the prior art, in order to solve the problem that the SAR image target recognition in the prior art needs to estimate the target azimuth angle and the recognition accuracy is limited, the present invention provides an identification dictionary learning method based on the range image time-frequency map SAR target recognition method, which extracts radar target range image features as SAR target recognition features, and uses discriminant dictionary learning to jointly carry out dictionary learning and classifier training, so that the sparse coding of test data under the dictionary learned based on this algorithm has predictable Discrimination, so as to improve the accuracy of SAR target recognition, and does not need to estimate the target azimuth angle of the SAR image, and can also avoid the influence of factors such as defocus or signal-to-noise ratio on the target recognition effect

Images