Underwater target detection and identification method, system and device and readable storage medium

An underwater target and identification method technology, applied in the field of underwater target detection, can solve the problems of inability to accurately perceive the surrounding environment and targets, target false alarm or missed detection of the battlefield situation, and difficult to represent the enemy's security situation, etc., to achieve the elimination of redundant The effects of remaining attributes and "inferior" information, resolving conflicts between predicted information and reality, and avoiding difficulties in model parameter estimation

CN113361579APending Publication Date: 2021-09-07XI AN JIAOTONG UNIV
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2021-09-07

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses an underwater target detection and identification method, system and device, and a readable storage medium, and aims to realize current and electricity information composite detection by fusing a flow field pressure signal generated by a dynamic target and electric field distortion, and solve the problems of incomplete information representation and detection blind area influenced by environmental interference in the existing underwater sound detection method. The method can be used as an effective supplementary technology for underwater non-acoustic detection, fusion of single flow / electric field information is realized based on a Neyman-Pearson rule, an optimal flow / electric signal is selected as a basis for heterogeneous fusion under the condition that the detection probability of an isomorphic detection system is optimal, the reliability of the single-field information is improved, data fusion of BPNN, GRNN and GRNN is realized based on a D-S evidence theory, the system prediction error is minimized, then fusion of flow / electricity information is realized, and underwater target detection with more comprehensive information representation, more stable system performance and more accurate identification capability is formed.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of underwater target detection, and in particular relates to an underwater target detection and identification method, system, equipment and readable storage medium. Background technique

[0002] Underwater high-sensitivity, high-precision, large-range, and high-intelligence target detection is the key technology of modern marine equipment systems, and its effectiveness determines the combat performance and efficiency of marine equipment. Due to the characteristics of seawater itself, such as rapid attenuation of electromagnetic waves and extremely low light penetration, underwater targets are extremely concealed. In order to improve the "stealth" performance of underwater equipment, countries around the world continue to invest a lot of scientific and technological research and development forces in research, which has continuously strengthened the concealment of underwater targets. Therefore, if the effective infor...

Examples

Embodiment

[0143] Embodiment: an underwater target detection and identification system, comprising:

[0144] The signal acquisition and processing module is used to obtain the flow field pressure signal, flow field pressure noise sequence, electric field distortion signal and electric field noise sequence of known types of underwater targets, and perform low-pass filter preprocessing and DC filter processing respectively;

[0145] The pre-training module is used to fuse the preprocessed flow field pressure signal and the flow field pressure noise sequence based on the Neyman-Pearson rule to form a flow field signal set, and to obtain the optimal flow field signal from the flow field signal set and from the preprocessed The final electric field distortion signal takes the optimal electric field signal and divides the data sample set according to the detection probability, and uses the data sample set for model training to obtain a multi-model probability output model;

[0146] The multi-m...