Radar target constraint element learner intelligent identification method

Abstract

The invention discloses an intelligent recognition method for a radar target constraint element learner, and belongs to the field of radar signal processing. A normalized exponential loss constraint element learner is combined with a multi-class balance center cosine loss basic learner to construct a small sample radar target high-resolution distance pixel learning recognition framework; by designing a regularized parameter updating mode, mutual influence of loss of different tasks in the same meta-test task set is fully considered while difference learning experience of different meta-training tasks is introduced, effective fusion of different task experience in the parameter updating process is ensured, difference characteristics of different task learning experience are fully utilized, and the parameter updating efficiency is improved. According to the method, the regularized constraint migration reference of different task learning experiences is realized, the method is used for guiding a new recognition task to carry out effective small sample recognition, the multi-class recognition accuracy of the radar target high-resolution range profile under the small sample condition is improved, and the method has popularization and application values.

Description

1. Technical field [0001] The invention belongs to the field of radar signal processing, and in particular relates to an intelligent identification method of a radar target constraint meta-learner. 2. Background technology [0002] High Resolution Range Profile (HRRP) is the projection of the main scattering point of the target in the direction of radar irradiation, which reflects the relative position information of the target scattering point, and reflects the partial structure information of the target to a certain extent. Therefore, it has broad application prospects in the field of target recognition. For cooperative targets, a large number of target HRRP samples can be obtained, but in practical applications, the targets targeted by the radar are often non-cooperative targets, and it is difficult to obtain a sufficient number of non-cooperative target HRRP data. Therefore, HRRP recognition of radar targets under the condition of small samples with small amount of data...

AI Technical Summary

Problems solved by technology

[0007] Aiming at the problem of poor HRRP multi-category recognition accuracy of radar targets under the condition of small samples, how to build a suitable meta-learning recognition framework, decouple the characteristics of a single task from the commonality between tasks, and design a suitable basic learner and meta-learner for a single task. Experience transfer of characteristics and commonality between tasks to achieve effective small-sample recognition of radar targets; how to design an appropriate loss function for the construction of basic learners to avoid the recognition rate of class targets with a small number of samples caused by the unbalanced number of samples in multiple categories The problem of descent; for the construction of meta-learners, how to design a regularized parameter update method, while introducing the differential learning experience of different meta-training tasks, fully take into account the mutual influence of different task losses in the same meta-test task set, and ensure the parameter update process The effective integration of different task experience, making full use of the difference characteristics of different task learning experience, realizes the regularization and constraint transfer of different task learning experience, which is used to guide the effective small sample recognition of new recognition tasks and improve the small sample recognition of new tasks. Sample Target Recognition Accuracy

Images