Intelligent clutter suppression method for sea surface surveillance radar

Abstract

The invention discloses an intelligent clutter suppression method for a sea surface surveillance radar, which is applied to the field of radar target detection and aims to solve the problem that the existing sea surface clutter suppression technology is difficult to deal with a complex and changeable marine environment. According to the method, two paths of mirror symmetry generative adversarial networks are constructed, one path learns mapping from original clutter data to data after clutter suppression, the other path learns mapping from the data after clutter suppression to the original clutter data in turn, two types of data sets are input into two paths of GANs respectively, and finally a clutter suppression network with a sea clutter suppression function is obtained through mutual constraint of two groups of generators and countermeasures and dynamic identification of radar data before and after clutter suppression. By adopting the method, the signal-to-clutter ratio of the target can be remarkably improved, and the original information of the target can be completely reserved.

Description

technical field [0001] The invention belongs to the field of radar target detection, in particular to a radar sea surface clutter suppression technology. Background technique [0002] Sea surface surveillance radar is mainly used to detect sea ships, track and measure sea targets, and has important significance in both military and civilian use. In the sea detection process of sea surface surveillance radar, the echoes not only include target echoes, but also include backscattered echoes from the ocean surface, also known as sea clutter. Sea clutter has very complex dynamic characteristics. When detecting sea targets, especially small targets, the presence of sea clutter will greatly reduce the detection signal-to-clutter ratio of the target due to the weak echo of the target itself, thus Seriously affect the detection performance of the sea surface surveillance radar system. Therefore, in order to improve the detection performance of low detectable targets on the sea surf...

AI Technical Summary

Problems solved by technology

The document "HF-over-the-horizon radar ship detection with short dwells using clutter cancellation. Root, Benjamin T. Radio Science 33.4(1998): 1095-1111" proposed the sea clutter circular cancellation method, which assumes that the sea clutter Satisfying the sinusoidal signal model, each iteration removes the strongest single-frequency component until the clutter is suppressed to the noise floor level. This method requires a strong signal-to-clutter ratio, and if the target and clutter Doppler frequencies are too close, it may will cause the target to be suppressed

The document "An Improved OTHR Adaptive Sea Clutter Suppression Method. Zhao Zhiguo, Chen Jianwen, Bao Zheng. Systems Engineering and Electronic Technology, 2012, 34(05): 909-914" proposes an improved eigenvalue decomposition method, which The method is based on subspace estimation, and suppresses sea clutter according to the aggregation characteristics of clutter in subspace. This method can suppress sea clutter when the Doppler frequency difference between the target and sea clutter is large, but when When the two frequencies are close to or overlap, the target will be canceled by mistake, resulting in missed alarms

[0004] Although the above sea clutter suppression method can suppress sea clutter well under certain conditions, its generalization ability is weak and it is difficult to cope with the complex and changeable marine environment.

Images