An Infrared Dim Target Detection Algorithm Based On Density Peak Search

The infrared search and tracking system(IRST)has the advantages of good concealment and strong anti-interference ability,which is widely used in many aspects such as military early warning,precision guidance and remote sensing.The infrared small target detection is one of the key technologies.The infrared small target usually contains only dozens of pixels in each frame.Because the dim targets miss texture and shape information and are often submerged in complex backgrounds(such as cloud edges,ocean waves,and high-brightness noise),so the signal to clutter ratio of each frame is very low,for the above reasons,subsequent target detection processing and detection of the trajectory are hard to do well.Under complex background conditions,traditional detection methods are not ideal in robustness and accuracy.This paper focuses on practical problems such as the presence of bright clutter in the background,too dense targets,low contrast,and weak robustness,based on the density peak search algorithm,research work is carried out in combination with regional consistency and local contrast,and is dedicated to solving the defects of existing algorithms in processing complex background images.The main work is summarized as follows:1.In order to solve the "expansion effect" of the human visual system method,an infrared small target detection algorithm based on dual-neighborhood contrast is proposed,which is mainly divided into four parts: the peak search algorithm extracts the candidate target and constructs a three-layer dual-neighborhood window for the candidate target,Dual-neighborhood contrast mechanism enhances the target and suppresses clutter,threshold segmentation extracts the real target.First,the peak search algorithm is used to screen out the candidate targets;then the candidate targets are traversed through a single-scale three-layer double neighborhood window,and finally the dual-neighbor contrast model is used to calculate the minimum gray contrast of the candidate target area,and the diagonal gradient factor enhances the contrast and suppresses clutter.Finally,the target is obtained by adaptive threshold algorithm.2.In order to suppress background clutter and improve detection accuracy,this paper proposes a dim target detection algorithm based on density peak search and region consistency.Firstly the density peak search algorithm is used to extract the candidate targets.And then the candidate targets are classified and marked according to the local mosaic probability factor,which is important to suppress the background clutter and accurately strip the candidate target region from the background.Considering the regional stability of the dim targets,local mosaic gradient factors are used to screen real targets from the candidate targets,and then facet kernel filter is used to extract irregular contours of the dim targets,and as a result,the target can be enhanced.The method in this paper effectively solves the "expansion effect" and at the same time strengthens the targets.Compared with the comparison method,the experimental results show that the research effectively suppresses the clutter,has better detection accuracy and robustness,can accurately detect multiple targets close to each other,and improves the detection precision of multiple targets in complex backgrounds.