基于局部梯度的红外线列扫描图像小目标检测

Small target detection of infrared column scan images based on local gradient

线列探测器受外界环境中不同像素点特性的影响,导致红外线列扫描到的图像存在一定误差。为了提升红外线列扫描图像中小目标检测的准确性,提出基于局部梯度的红外线列扫描图像小目标检测方法。首先分析红外线列扫描小目标的成像原理,获取小目标及其周围环境的像素特点,校正线列探测器的误差,得到理想光强下的小目标图像。结合灰度值和梯度方向一致法抑制图像背景,突出小目标本身,再利用特征分解的方法减少边缘背景对小目标的影响,最后,利用阈值对小目标实施分离,实现小目标检测的目的。实验结果表明,所提方法的信噪比增益高、背景抑制效果好、虚警率低,小目标的检测精度高。

The line detector is affected by the characteristics of different pixel points in the external environment,resulting in a certain error in the image scanned by the infrared column.In order to improve the accuracy of small target detection in infrared column scanning images,a small target detection method based on local gradients in infrared column scanning images is proposed.Firstly,the imaging principle of the infrared array scanning small target is analyzed,the pixel characteristics of the small target and its surrounding environment are obtained,the error of the line detector is corrected,and the image of the small target under the ideal light intensity is obtained.Combine the gray value and gradient direction consistency method to suppress the image background,highlight the small target itself,and then use the feature decomposition method to reduce the influence of the edge background on the small target.Finally,use the threshold to separate the small target to achieve the purpose of small target detection.The experimental results show that the proposed method has high signal-to-noise ratio gain,good background suppression effect,low false alarm rate,and high detection accuracy of small targets.