CAJ | 학술논문

针对天空背景下红外弱小目标检测困难的情况，首先通过改进的形态学滤波目标增强方法对图像进行背景抑制与噪声去除，而后采用恒虚警检测方法（CFAR）对滤波后图像进行分割，获得候选点目标，然后采用行程目标标记的方法得到候选目标的位置信息、面积信息等，单帧图像检测之后，复杂的天空背景仍然会存在虚警。为了提高检测概率、降低虚警率，结合目标运动特性（包括运动轨迹、速度、加速度等）、灰度变化、面积变化等帧间相关性采用移动式管道滤波方法对序列图像候选目标做进一步判断。实验结果表明，该方法能有效地从复杂背景中检测出真实目标。
침대천공배경하홍외약소목표검측곤난적정황，수선통과개진적형태학려파목표증강방법대도상진행배경억제여조성거제，이후채용항허경검측방법（CFAR）대려파후도상진행분할，획득후선점목표，연후채용행정목표표기적방법득도후선목표적위치신식、면적신식등，단정도상검측지후，복잡적천공배경잉연회존재허경。위료제고검측개솔、강저허경솔，결합목표운동특성（포괄운동궤적、속도、가속도등）、회도변화、면적변화등정간상관성채용이동식관도려파방법대서렬도상후선목표주진일보판단。실험결과표명，해방법능유효지종복잡배경중검측출진실목표。
Against the difficult detection of dim small infrared targets in the sky background,in this paper,the improved morphological filtering target enhancement method is adopted for background suppression and noise removing,and then constant false alarm rate(CFAR)method is used to segment the filtered image to obtain candidate point targets,and get the position and area information of candidate point targets by adopting run?length target labeling method. After the single frame image detection, there are still false alarms in the complicated sky background. In order to improve the detection probability and reduce false alarm rate,the mobile pipeline filtering method is adopted to make further judgment for the candidate targets in sequential imag?es in combination with the correlation between image frames of the target motion characteristics(including trajectory,velocity, acceleration,etc),grey change,area change and so on. The experimental results show that the method proposed in this paper can accurately and quickly detect the true targets in the complex background.