Research On Small Target Detection Method In The Sea And Sk

Sea and sky weak target detection is a key technology to realize the modernization of China’s naval operations,and infrared thermal imaging technology has been widely used due to its advantages of stealth,full time operation and long range detection.When the detected ship target is far away,it will be presented as a weak target.Weak targets are easily submerged in the complex and variable sea clutter,bright bands,and island background,which leads to false detection and missed detection.In addition,the original image bit width of thermal imaging camera is usually 14 Bit,but the subsequent display and processing needs are often8 Bit data,so the original high Bit data need to be compressed,and how to effectively enhance the image details and adjust the contrast at the same time in the data compression is particularly important.In this paper,a detailed study of infrared weak target detection in sea and sky scenes is carried out from the following three aspects.For the special sea-sky background and noise suppression,this paper adopts a superimposed filtering algorithm,that is,first filtering out the pepper noise in the image with adaptive median filtering,such as blind elements in the image;then processing the image with bilateral filtering,taking into account noise suppression and edge preservation.Through multiple sets of comparison experiments,the applicability of the algorithm in this paper is verified under the sea and sky scenes.For dynamic range compression and detail enhancement of infrared images,in view of the shortcomings of conventional infrared image detail enhancement algorithms,this paper proposes a dynamic range compression and detail enhancement algorithm based on guided image filtering and APHE.The method divides the original high-Bit image into a base layer and a detail layer by guided image filtering;the base layer contains the background information of the image,and adaptive platform histogram equalization(APHE)is applied to it;the detail layer contains the edge information of the image and a large amount of noise,and adaptive noise suppression and detail enhancement are applied to the detail layer;then the two parts are linearly fused after processing separately to obtain the enhanced 8Bit image.The superiority of this paper’s algorithm is verified through several sets of comparison experiments,and the objective indexes and subjective feelings are integrated.For sea-sky weak target detection,this paper combines background suppression and local structure features on the basis of traditional local contrast algorithm(LCM)to obtain an infrared weak target detection method applicable to sea-sky scenes.Firstly,background and noise suppression is applied to the sea-sky IR image to reduce the interference of sea clutter,bright bands and islands to the detection algorithm,followed by detail enhancement to improve the saliency of weak targets,and finally,local structure features and local contrast features of the image are calculated,and the features in these two dimensions are integrated to complete the detection of sea-sky weak targets.The superiority and robustness of the algorithm in this paper are proved through multiple sets of comparison experiments.