Infrared detection false alarm detection method based on scene space-time saliency and application thereof

Abstract

The invention discloses an infrared detection false alarm detection method based on scene space-time saliency and application thereof. The detection method comprises the following steps: obtaining an inter-frame time domain mean value image of an infrared detection image sequence, obtaining a gradient magnitude image of an intra-frame space domain gradient image of the inter-frame time domain mean value image, carrying out gray threshold segmentation processing on the gradient magnitude image, carrying out four-neighborhood discrimination on a candidate detection result image obtained after segmentation processing, and carrying out four-neighborhood discrimination on the candidate detection result image obtained after segmentation process, and distinguishing blind pixels and normal pixels. The detection method can effectively detect various types of infrared detection system blind pixels such as dead pixels and overheated pixels, has high detection precision and low false detection rate, and can be effectively applied to false alarm detection of infrared detection system point target detection.

Description

technical field [0001] The invention relates to the technical field of infrared detection signal processing. Background technique [0002] Modern airborne photoelectric detection systems are widely used in the detection and tracking of air targets such as flight obstacle avoidance and missile air attack warning, as well as the search and positioning of ground targets such as battlefield situation awareness and aircraft takeoff and landing. Infrared detection system is an important part of modern airborne photoelectric detection system. Infrared detection technology is a passive detection method, which has high concealment and can effectively detect the thermal radiation signal of the target. With the continuous development of infrared detection technology, infrared point target detection has gradually become a hot research problem. However, the false alarm problem of infrared point targets caused by blind pixels (such as dead pixels, overheated pixels, etc.) caused by the ...

AI Technical Summary

Problems solved by technology

[0005] Although there have been many researches on blind element detection methods in the prior art, there are problems such as insufficient threshold segmentation automation and high false alarm rate in these methods, which limit the improvement of target detection accuracy.

Images