Infrared image aerial moving target detecting method

Abstract

The invention relates to the technical field of image processing, and specifically discloses an infrared image aerial moving target detecting method. According to the method, a frame difference methodis used as a basic algorithm to establish a frame difference ROI binary image model by buffering a frame difference ROI binary image; the value of the similarity of the current frame difference ROI binary image and the frame difference ROI binary image model is calculated; if the similarity value is greater than or equal to a preset similarity threshold, a screening method is used in the currentframe difference ROI binary image to detect a target; and if the similarity value is less than the preset similarity threshold, the screening method is used in the current ROI binary image to detect the target. The method solves the problem that the target is lost, which is caused by the fact that the existing target detecting method is not suitable for target detection in a moving background andthe target passes through the moving background. Moving target detecting in the moving background is real-time and accurate.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a detection method of an infrared image moving target in the air. Background technique [0002] With the development of science and technology, the progress of society, and the improvement of living standards, the security awareness of groups and individuals is constantly increasing, and video surveillance systems have been more and more widely used. At present, it has been widely used in security monitoring, automatic monitoring and remote monitoring of systems and fields such as banks, museums, traffic roads, commerce, military, public security, electric power, factories and mines, and intelligent communities. The function of the monitoring system has also developed from simple manual monitoring of video signals, system multi-screen display and hard disk video recording to the use of computers to realize intelligent target detection and target tracking. [0003] Movin...

AI Technical Summary

Problems solved by technology

[0004] At present, the main target detection algorithms include frame difference method, background difference method, optical flow method, TLD, etc. These methods have their own advantages and disadvantages. The disadvantage of the traditional frame difference method is that it is sensitive to environmental noise and is not suitable for the detection of moving targets. , the disadvantage of the background difference method is that it is particularly sensitive to changes in dynamic scenes, such as lighting and interference from external irrelevant events, and other algorithms are complex to use, and it is difficult to guarantee real-time performance

Images