摘要
针对红外点目标检测问题,采用图像灰度同本行均值相减方法抑制温度场的非线性影响;利用Top-Hat算子形态滤波,抑制背景和增强目标;通过比较预处理后的不同背景下红外图像直方图特点,确定分割阈值;最后进行目标二值化分割,得到包含较少虚警点的点目标分割图像。实验证明,该方法较好地解决了不同红外背景下低信噪比红外点目标的分割检测问题。
Aiming at the detection of IR point target, correction of IR image fuzziness are carried out by inhibiting nonlinear influence in temperature field with the same row average subtracting. Inhibiting background and enhancement of point target are implemented by using Top-Hat operator morphological;segmenting threshold is obtained by comparing characteristics of filtered IR images histograms under different background. In the end, a point target segmentation image contained few false alarm points is obtained after binary segmentation. The experiments show the method can detect IR point target under different background with low signal-to-noise ratio.
出处
《激光与红外》
CAS
CSCD
北大核心
2008年第11期1144-1148,共5页
Laser & Infrared
基金
预研项目(No.4010605020402)资助
关键词
红外点目标
目标检测
图像分割
数学形态学
灰度直方图
IR point-target
target detection
image segmentation
mathematical morphology
gray histogram
