A method and device for underwater target recognition

Abstract

The invention discloses a method and a device for identifying underwater targets. The method includes computing static characteristics and transient characteristics of known underwater targets and forming covariance matrixes of the transient characteristics of the known underwater targets; decomposing eigenvalues of the covariance matrixes of the transient characteristics of the known underwater targets to obtain principle characteristic component vectors corresponding to the large eigenvalues; extracting principle component weights of transient characteristics of training sample sonograms according to the principle characteristic component vectors; determining principle component centers according to the principle component weights of the transient characteristics of the training sample sonograms; computing static characteristics and transient characteristics of underwater targets to be classified according to sonograms of the underwater target to be classified; extracting principle component weights of the transient characteristics of the underwater targets to be classified according to the principle characteristic component vectors; and computing distances from the principle component weights of the transient characteristics of the underwater targets to be classified to the principle component centers of the training sample sonograms and classifying the underwater targets to be classified. The method and the device have the advantages that the characteristics of the targets can be accurately and steadily reflected, and the target identification time is shortened.

Description

technical field [0001] The present invention relates to underwater target recognition technology, in particular to an underwater target recognition method and its device Background technique [0002] Under normal circumstances, most of the security protection systems are for intrusion monitoring or defense of land and air facilities. In recent years, the rapid development of small underwater diving equipment, the maturity of frogman, underwater vehicle and underwater robot technology, such The emerging attack method with good concealment and great destructive power is favored by terrorists. The U.S. Department of National Security has learned that terrorist organizations have mastered the diving technology of frogmen wearing scuba and have begun to use frogmen to carry out terrorist attacks. Therefore, intrusion monitoring for small underwater targets such as swimmers and frogmen has become a necessary component of the security system. [0003] From around 2000, Western co...

AI Technical Summary

Problems solved by technology

For example, by using static features to classify the underwater targets of the sector scanning sonar, this technology mainly uses the static information of a single frame target to classify artificial targets; Target classification, this technology uses transient information to identify underwater frogman targets, but due to the high dimensionality of transient features, it is necessary to implement learning and feature screening based on training samples, and use sequence forward selection to select important features Entering the classifier for target recognition, the real-time and flexibility of the algorithm are poor, and it is not conducive to the application of the multi-target classification system of the actual sonar system

Another example, using ultra-wideband active sonar (60KH Z ~120KH Z ) to classify underwater frogmen. This technology requires the use of frequency domain information and system bandwidth, which increases the complexity of the system. Especially for early warning sonars with a wide range and wide coverage angles such as frogman detection sonars, it will be extremely difficult. Greatly increase hardware cost and system implementation difficulty

Images