Ship target detection method based on adaptive layered high-resolution SAR image

Abstract

The invention discloses a ship target detection method based on anadaptive layered high-resolution SAR image. The method comprises the steps that firstly a visual attention mechanism combining an image domain and a frequency domain is constructed, not only can better maintain the details of a saliency map, but also has an obvious speed advantage compared with other attention mechanisms; secondly,a candidate target region segmentation threshold value is obtained by adopting a mean dichotomy, so that instability caused by hard threshold value selection is eliminated; and finally, ship target fine detection is carried out by using a frequency domain accelerated block kernel density estimation method. Calculation burden caused by super-pixel segmentation is avoided due to the idea of region partitioning. The mismatch risk of a clutter model is eliminated through kernel density estimation. In addition, the execution efficiency of the detection method is further improved through a frequencydomain acceleration method of the detection method. In addition, compared with an existing high-resolution SAR image ship target detection method, the method has the advantages that the constant false alarm characteristic can be kept while the target is detected.

Description

Technical field [0001] The invention belongs to the technical field of radar signal processing, and particularly relates to a ship target detection method based on an adaptive layered high-resolution SAR image. Background technique [0002] In terms of earth observation, synthetic aperture radar (SAR) has irreplaceable performance advantages. The basic principle of SAR image ship target detection is based on the difference between the microwave scattering characteristics of the metal structure of the ship and the sea surface. The radar cross-sectional area of ​​the ship is usually higher than the sea surface. According to the intensity difference between the target and the clutter pixels, the ship can be detected by selecting an appropriate threshold. Limited by the resolution, early ship detection was mainly for point targets, and the clutter characteristics of the sea surface conformed to a relatively simple Gaussian distribution. As the resolution increases, the pixel unit o...

AI Technical Summary

Problems solved by technology

First of all, it needs to know the size of the detected hull to determine the size of the protection window, which is only applicable to the case of a single target in local uniform clutter

When there are ship targets of different sizes in the SAR image, that is, multi-scale situations, a single window size has the risk of target pixels leaking into the background window and affecting the detection threshold

Increased probability of missing target pixels, holes and breaks in detected targets

In addition, the ship target often only occupies a small part of the pixels in the image, and the sliding window technology traverses the entire image, which undoubtedly causes too many redundant calculations

In addition, traditional methods often use Gaussian distribution as the sea clutter model, which has a great risk of mismatch in high-resolution images

Images