Infrared weak and small target detection method based on image inpainting technology

Abstract

The invention relates to an infrared weak and small target detection method and device based on an image inpainting technology. The method comprises the following steps: extracting a to-be-processed current frame infrared image from an infrared video image, respectively detecting weak and small targets through a spatial domain algorithm and a time domain algorithm, merging suspected weak and small target areas obtained by the two ways into a candidate weak and small target area, digging out the candidate target area from an original infrared image, and obtaining a weak and small target area; the method comprises the following steps of: recovering and estimating a pixel where a candidate target is located by using an image inpainting technology, reconstructing a current frame of infrared background image, subtracting the current frame of infrared background image from the current frame of infrared background image to obtain a target saliency map, and segmenting the target saliency map to obtain a weak target. According to the method, the detection rate of the infrared weak and small target is effectively improved, false alarms caused by noise, clutter, edges and other factors are reduced, the algorithm complexity is low, the calculation amount is small, and the real-time requirement in actual engineering application is easily met.

Description

technical field [0001] The present application relates to the field of infrared detection, in particular to a method and device for detecting small infrared targets based on image repair technology. Background technique [0002] The infrared search and tracking system adopts an important passive and passive detection technology, which has strong stealth and anti-jamming capabilities. Targets often appear in the form of weak targets in infrared images, including only a few pixels to dozens of pixels, lack of shape and texture information, the target energy is very weak, the signal-to-noise ratio is very low, and it may be submerged in strong clutter and complex backgrounds. All these factors increase the difficulty of infrared weak and small target detection, resulting in the Insufficient detection rate and high false alarm rate. [0003] According to the main technical approaches, the infrared weak and small target detection methods currently proposed can be divided into: m...

AI Technical Summary

Problems solved by technology

[0004] For the detection of weak and small targets in infrared video images, the main shortcomings of the existing technology are low reliability and detection rate, high false alarm rate, and low real-time performance. Further research is still needed to develop a better infrared weak and small target detection technology.

Images