Infrared weak and small target detection algorithm based on multi-channel improved dog filter

Abstract

The present invention proposes a kind of infrared faint target detection algorithm based on multi-channel improved DoG filter, first carries out normalization processing to infrared image; secondly carries out multi-channel improved DoG (IDoG) filter to infrared image, obtains 8-channel filter result map; Then Take the maximum value of the 8-channel filtering result image and process it to obtain the multi-channel IDoG result image; then perform Gaussian enhancement on the processing result image to obtain the final processing result image; finally find the position of the maximum gray value point in the result image, which is The location of the small infrared target. The invention can be used to detect weak and small targets in infrared images, and can effectively improve the detection accuracy of small targets in infrared images to improve detection performance and robustness.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to an infrared weak and small target detection algorithm based on multi-channel improved DoG filtering in the field of infrared image processing under complex backgrounds. Background technique [0002] With the rapid development of infrared technology, the detection of small and weak infrared targets has been extensively and deeply studied, and has applications in many fields such as precise guidance and long-range early warning. In recent years, with the development of anti-radiation and stealth technology, as well as the interference of natural weather phenomena such as fog, clouds, and rain, the background of infrared images has become more and more complex, and small infrared targets can easily be submerged. Therefore, the detection of small infrared targets has always been a hot and difficult point in the field of infrared image processing. [0003] There are th...

AI Technical Summary

Problems solved by technology

In recent years, with the development of machine learning, algorithms based on neural networks have also begun to be applied to the detection of small infrared targets. However, this type of feature learning and model training methods have high complexity, poor real-time performance, and limited application.

In summary, although there are a large number of infrared small target detection methods, these methods still have the problems of requiring more prior knowledge, poor robustness, high algorithm complexity, and insufficient real-time performance.

Therefore, there are still challenges in the detection of small infrared targets in complex backgrounds.

Images