基于梯度直方图和SUSAN算子的红外目标检测  

Infrared Target Detection Based on Gradient Histogram and SUSAN Operator

作　　者：罗华锋[1] 王铎[1] LUO Hua-feng;WANG Duo(92941 Army Unit,Huludao 125001,China)

机构地区：[1]92941部队

出　　处：《光电技术应用》2020年第1期47-50,共4页Electro-Optic Technology Application

摘　　要：红外制导技术的核心任务是将视场中的目标提取出来,然而受多种因素的影响,红外成像呈现出信噪比低,对比度不强的特点。为有效检测出红外目标,首先分析红外图像梯度信息并进行直方图统计,发现其值只占据窄小的区间,借鉴直方图均衡化思想,对梯度直方图进行拉伸,并与原图进行加权融合,增强图像对比度的同时增大信噪比,然后采用改进的SUSAN算法对图像进行处理,可较好的提取出红外目标。仿真实验结果表明,与传统算法相比,文中算法计算量小、运行时间短,可有效检测出目标,有利于工程实现。The main task of infrared guidance technology is to get the target from background,however,influ⁃enced by many factors,infrared images have a lower signal-to-noise ratio(SNR)and contrast.For detecting the tar⁃get effectively,firstly,the gradient information of images is analyzed and histogram statistic is performed,it is found that gradient pixels only occupy a small section.Taking the thought of histogram equalization to broaden,and then,this image is fused to the original image to get a higher contrast and SNR.Finally,the improved SUSAN algorithm is used to process the image.Simulation experimental results show that the method has a smaller calculation and short⁃er calculate time,and can better detect target compared with traditional ones.

关 键 词：红外制导 梯度 SUSAN算子 信噪比 目标检测 

分 类 号：TN219[电子电信—物理电子学]