A Feature Extraction Method of Marine Target Based on Companion Variance Modification Model

Abstract

The invention discloses a marine target feature extraction method based on a concomitant variance correction model, which belongs to the technical field of marine remote sensing, including constructing an OceanTD deep learning model, and performing preliminary detection of marine target features based on the OceanTD deep learning model; and then constructing a concomitant variance The model is revised, the variance of the logarithmic distribution function is corrected, the standard deviation and absolute value error indicators are considered, the variance correction item is added, and its formula is derived, which improves the goodness of fit for complex sea conditions and sea clutter; finally, based on the The variance correction model uses the CFAR algorithm to extract ocean target features, and visualizes the extracted ocean target features, which improves the recall rate of ocean target detection and the accuracy of ocean target parameter extraction; the method proposed in the present invention, sea clutter fitting The superiority is significantly improved, the amount of false alarms in target detection is significantly reduced, and the accuracy of feature extraction is effectively improved.

Description

technical field [0001] The invention discloses a marine target feature extraction method based on a concomitant variance correction model, which belongs to the technical field of marine remote sensing. Background technique [0002] CFAR algorithm is a relatively mature method in current marine target detection, and is the most commonly used and effective detection algorithm in the field of radar signal detection, including dual-parameter CFAR algorithm, adaptive dual-parameter CFAR detection method, and K-distribution-based CFAR algorithm. And the CFAR algorithm based on Weibull distribution, etc. Based on the assumption that the ocean background clutter conforms to the Gaussian distribution, Burl et al. proposed a two-parameter CFAR detection algorithm. Because the ocean background clutter is affected by many factors and does not strictly conform to the Gaussian distribution, the two-parameter detection algorithm has a high false alarm rate. At present, it is rare to perfo...

AI Technical Summary

Problems solved by technology

[0003] The invention discloses a marine target feature extraction method based on a concomitant variance correction model to solve the problem that in the prior art, the Gaussian distribution assumption of the traditional CFAR target detection method has certain limitations, resulting in insufficient accuracy of marine target feature extraction

Images