Method for detecting weak small targets for marine navigation radar

Abstract

The invention discloses a method for detecting weak small targets for a marine navigation radar, and specifically comprises a training process and a detecting process, wherein the training process includes a sea clutter data phase space reconfiguration and a gray neural network training, and specifically the detecting process is a detection for sea clutter targets. The method is based on the differences between inherent properties of echoes of the sea clutters and inherent properties of the targets, sea clutter data without the targets is used for training the gray neural network, and then under the condition of pure sea clutter, an overall error root mean square value or a compensation error tends to be zero; when the sea clutter data contain targets, an overall error root mean square value and a compensation error are large, thereby the detection for the weak small targets can be performed. Compared with a traditional constant false alarm rate target detection method, the method for detecting weak small targets for the marine navigation radar is capable of detecting the weak small targets under the background of strong sea clutters; compared with a method for detection by a radial basis function (RBF) neural network, the method for detecting weak small targets for the marine navigation radar has a faster training speed, less required sample data information, and has an excellent performance for detecting the weak small targets under the background of the sea clutters.

Description

technical field [0001] The invention belongs to the technical field of marine navigation radar, and in particular relates to a small and weak target detection method therein. Background technique [0002] Marine navigation radar is one of the indispensable navigation equipment for ships, but the target detection performance of marine radar is often affected by sea clutter. Sea clutter is the radar reflection echo from the ocean surface, and it is the main clutter source of ship navigation radar. Usually, unlike ground clutter, which is a distributed scattering phenomenon, it shows stronger dynamic characteristics. Therefore, the existence of sea clutter seriously affects the detection performance of radar on sea targets. With the development of shipping industry and port trade economy in recent years, ships have higher and higher requirements for the speed, accuracy and anti-interference ability of navigation radar target detection, so as to be able to accurately and timely...

AI Technical Summary

Problems solved by technology

However, if the target is small and the sea clutter is strong, the constant false alarm target detection method is helpless, it is difficult to detect weak targets, and even leads to missed detection.

[0006] At present, the target detection method based on chaotic characteristics mainly uses Radial Basis Function neural network (Radical Basis Function) for detection. Although this method is indeed feasible, it also has the disadvantage of "curse of dimensionality". The dependence on the dimensionality of the input space is exactly this "curse of dimensionality"

In the RBF neural network, the inherent complexity of the approximation function has an exponential growth relationship with the dimension of the input space. The fundamental reason is that the function defined in the high-dimensional space is likely to be far more complex than the function in the low-dimensional space, and it is not easy to distinguish These complex things, in addition, the training time of RBF network is relatively large

Images