Neighborhood gradient-based infrared weak and small target detection method under complex background

Abstract

The invention discloses a neighborhood gradient-based infrared weak and small target detection method under a complex background. The method comprises the following steps of: 1) generating an initialsearch main window template and an initial search sub-window template; 2) obtaining a foreground judgment window pixel matrix according to the window minimum value; 3) constructing a foreground judgment mapping table; 4) calculating neighborhood peak gradient characteristics and neighborhood step gradient characteristics; 5) performing SVM classification weight judgment on the window features; 6)performing neighborhood contrast judgment on the window; 7) adaptively adjusting the step length of the window, completing traversal of a single-frame image and outputting target information; and 8) carrying out continuous target detection on the sequence image, respectively carrying out motion characteristic judgment and static characteristic judgment, and calculating and obtaining target detection information data of the latest frame. The method can be used for remote photoelectric reconnaissance, unmanned aerial vehicle detection, coast defense, vehicle-mounted ground object target reconnaissance and other scenes, and the problems of low detection accuracy, high false alarm rate and low detection robustness in the existing weak and small target detection technology under the complex background are solved.

Description

technical field [0001] The invention relates to the technical field of digital image processing, in particular to a method for detecting infrared weak and small targets based on neighborhood gradients. Background technique [0002] As one of the research hotspots of photoelectric image processing technology, infrared faint target detection is widely used in the field of early warning and reconnaissance. Infrared weak and small targets have the characteristics of small imaging size, weak shape features, unobvious texture features, and are susceptible to noise interference, especially in complex backgrounds such as clouds, ground objects, and sea surfaces, which are likely to cause false and missed alarms. Therefore, in order to improve the performance of the photoelectric reconnaissance system, it is of great practical significance to study how to detect weak targets in complex backgrounds. [0003] Yang Hui et al. proposed a background difference detection algorithm that co...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies of the existing technology, the present invention proposes a detection method for infrared weak and small targets in complex backgrounds based on neighborhood gradients in order to solve the problems of detection effectiveness and robustness of small infrared targets in complex backgrounds. Low computational complexity and easy engineering implementation

Images