Infrared weak and small target detection method and device

Abstract

The invention discloses an infrared weak and small target detection method. The method at least comprises the following steps: S1, an image preprocessing step; s2, an image blocking step: dividing theto-be-processed image into four overlapped sub-images, and performing parallel processing; s3, carrying out partition target segmentation on the sub-images, carrying out target segmentation on a large area by utilizing a maximum between-cluster variance method, carrying out target segmentation on a cell by utilizing a local signal-to-clutter ratio threshold segmentation method, and carrying out target fusion processing on two segmentation results; s4, carrying out noise filtering on the sub-images, wherein the noise filtering comprises scatter filtering and shape filtering; s5, calculating target information, wherein the target information at least comprises a target centroid position, a size and a signal-to-noise ratio; and S6, performing target fusion processing on the processing results of the four sub-images, deleting targets repeatedly detected in the overlapping region, and outputting target information. According to the method, an improved method is designed for infrared imagenoise suppression and small and weak target detection, the small and weak target detection probability can be effectively improved, and the false alarm rate is reduced.

Description

technical field [0001] The invention belongs to the technical field of image processing and target detection, and in particular relates to a method and device for detecting small and weak infrared targets. Background technique [0002] Infrared weak and small target detection is one of the most important performance indicators of infrared detection system. Affected by detectors, weather, environment and other factors, infrared targets have low contrast and low signal-to-noise ratio, and there are few features that can be used for target detection; environment and background interference are constantly changing, and long-distance targets are small in size and are often submerged in background noise. The above factors make the detection of small and weak infrared targets very difficult, which affects the performance of the infrared detection system. [0003] Researchers have proposed many methods for infrared target detection, which are generally divided into two methods: det...

AI Technical Summary

Problems solved by technology

[0004] At present, most of the infrared target detection methods are still developed from the visible light image processing technology, which solve some target detection problems from different angles, but there are still relatively few detection methods for small infrared targets.

Images