Infrared images method for detecting targets at sea

Abstract

The invention provides an infrared images method for detecting targets at sea, which relates to a method for detecting the targets at sea. The invention aims to provide the method for detecting the targets at sea, which not only can well inhibit sea clutters to obtain reasonable image segmentations, but also can extract out the fractal characteristics at a high speed to remove false targets so as to achieve effective detections. The method comprises the following steps: performing preprocessing on the obtained infrared images; performing self-adapting iteration threshold segmentation; detecting whether the part of a sea-sky line has a region of interest (ROI); extracting the ROI at the background part of the sea-sky line; extracting the ROI at the background part of a non-sea-sky line; and combining the regions of interest to obtain an image of interest to be further processed, and extracting the fractal characteristics of each ROI to perform target detections. The method can quickly and effectively segment out the regions of interest in the infrared images, and not only reduces the amount of calculation to extract out the fractal characteristics at a higher speed because the extracted regions of interest is far smaller than the original images, but also can remove the false targets appearing in the threshold segmentation through the fractal characteristics.

Description

technical field [0001] The invention relates to a sea target detection method. Background technique [0002] Compared with visible light, infrared images have larger noise and lower resolution, but because of their passive advantages, especially the detection of infrared targets at sea has attracted close attention from all over the world. With the continuous development of high technology, higher requirements are put forward for the detection of infrared targets. It is necessary to ensure a high detection probability and a low false alarm probability, and to make judgments and even respond accordingly in a short period of time. Reaction. [0003] The current classic maritime infrared target detection algorithm is to firstly perform various preprocessing on the infrared image, such as denoising, edge extraction, etc., and then extract the grayscale and geometric features of the target to achieve the purpose of detecting the target. Many research institutions at home and ab...

AI Technical Summary

Problems solved by technology

[0006] However, if the fractal feature is directly used for image segmentation, target extraction and recognition, there are the following disadvantages: 1) the amount of calculation is large

Fractal calculations generally need to open windows, and calculate the change of window scale, which undoubtedly increases the amount of calculation and complexity, which is not conducive to real-time processing

2) Use fractal theory to segment images. If you use rectangular window sliding calculations, you can only extract the rectangular area of ​​interest, and you cannot obtain the actual shape of the target, let alone segment the target; if you perform window calculations for each point, in addition to increasing the amount of calculation , it is also easy to split a target into multiple targets, or form a so-called scattered target (even if it is the same target, its own texture may be different), which will not be conducive to subsequent target detection

Images