Wavelet domain multi- sensor Correction Weighted optimal information integration method

Abstract

The invention relates to a wavelet field multisensor correction weighing optimal information fusion method in the target location technical field, comprising the following steps that: firstly, the method for wavelet domain wavelet transformation is applied to observation state components of a multisensor, and the state components are discomposed; secondly, the correction weighting fusion method is provided for the state components after decomposition in the first step in a wavelet domain, so as to obtain fusion information in the wavelet domain by correction weighing information fusion of various state components; the correction weighing fusion method refers to adoption of matrix weighing fusion on state components corresponding to cross covariance matrixes of strictly positive definite estimation errors and adoption of scalar weighing fusion on state components with strange cross covariance matrixes of the estimation errors; thirdly, the state components in the wavelet domain after correction weighting fusion are converted into a time domain by adoption of wavelet inverse transformation method, and then state fusion information is obtained. The invention can effectively improve the precision of target states in the multisensor information fusion state field.

Description

technical field [0001] The invention relates to an information processing method in the technical field of sensors, in particular to a subwave domain multi-sensor correction weighted optimal information fusion method. Background technique [0002] The concept of multi-sensor information fusion (Multi-sensor Information Fusion) was proposed in the 1970s, but it did not attract enough attention at that time. In recent years, with the rapid development of science and technology, the complexity of continuous warfare in the field of military industry has made military commanders or industrial control environments face the problems of frequent data and information overload, which requires new technical approaches to process excessive information. Digestion, interpretation and evaluation, so the information fusion of multi-sensors has received close attention from military and non-military fields. Information fusion is a multi-level automatic intelligent information processing pro...

AI Technical Summary

Problems solved by technology

[0004] After searching the literature of the prior art, it was found that in the field of linear weighted information fusion, Sun Shuli et al. published "Multi-sensor Linear Minimum Variance Optimal Information Fusion Criteria", in which the optimal information fusion method of matrix weighting in the sense of minimum variance is proposed. This method uses Lagrange (Lagrange) multiplier method and matrix differential operation to carry out matrix weighting on each component. The disadvantages are: This method assumes the correlation of all errors. For the case of singular cross-covariance matrix, the method of local statistics is adopted. The fusion error is large and the calculation amount is large, so it needs to be improved.

In summary, the current research on information fusion in the wavelet domain and the improvement of linear weighted fusion methods is still relatively weak.

Images