Method for identifying sea ship of SAR (Synthetic Aperture Radar) image

Abstract

The invention provides a method for identifying a sea ship of an SAR (Synthetic Aperture Radar) image. By use of the method, detection and identification for a sea ship target of an SAR image under different sea clutter backgrounds can be implemented. The method is implemented by the following technical scheme: calculating a global segmentation threshold value of an input sea SAR image based on anaccumulative distribution histogram to obtain an index matrix of a target leakage pixel; for each pixel, self-adaptively selecting an optimal statistical model from a model dictionary through a KS (Kolmogorov-Smirnov) test for clutter modeling, and performing binary segmentation by use of a CFAR (Constant False Alarm Rate) method; removing isolated noise points by use of a local highlight densityon the basis of a binary segmentation result, extracting a connection region, removing the background and calculating corresponding characteristic parameters to obtain a candidate ship target; and constructing a ship target characteristic set by use of a training data set, and calculating the confidence degree of the ship target by a naive bayesian method.

Description

technical field [0001] The invention belongs to the technical field of radar image processing, in particular to a synthetic aperture radar (SAR) image sea surface ship target recognition method based on adaptive statistical modeling. Background technique [0002] Synthetic Aperture Radar (SAR) is a microwave remote sensing imaging system that uses microwave reflection signals to image. All-day and all-weather features. SAR images are also increasingly used in military and civilian fields, such as fishery monitoring, detection of smuggling ships, detection of sea ice, rescue of ships in distress, detection of dumped oil pollution, etc. With the increasing improvement of SAR equipment and the in-depth research of SAR image imaging algorithms, a large number of SAR images are used to detect targets such as ships on the ocean. In recent years, the use of SAR images to detect and identify maritime targets has received great attention in the field of marine remote sensing. [0...

AI Technical Summary

Problems solved by technology

These small number of ship target recognition methods only use grayscale statistics, peaks and other features for identification and screening, and the effect is not good.

[0007] Analyzing the existing SAR image ship target detection and recognition methods, there are mainly the following shortcomings: when performing statistical modeling of the sea clutter background, the sliding window method is usually used. When the target pixel appears in the background window, the statistical model Inaccurate estimation leads to failure of the method; for high-resolution SAR images, the statistical characteristics of sea clutter are complex, and different regions show heterogeneity and inhomogeneity. The traditional single model cannot meet the modeling requirements of different statistical characteristics of sea clutter. It is not conducive to accurate detection of ship targets; with the continuous improvement of the resolution of synthetic aperture radar SAR sensors, ship targets no longer appear in the form of point targets, but appear as surface targets, and the detection results of CFAR algorithm usually have loopholes and fractures, etc. Discontinuous phenomenon requires further processing to obtain better ship detection results; in addition, ship targets in high-resolution SAR images show obvious details such as texture and geometric structure, and using these detailed information can improve ship target recognition accuracy, but the existing methods do not fully utilize the detailed information

Images