自然地面背景红外目标检测方法研究

Study on Algorithm of Detecting IR Target in Natural Background

文章结合分形特征的特点,提出了一种基于分形技术的图像预处理算法。该方法利用自然背景和人造目标的不同分形持征检测目标,并利用领域连通性进行目标边界的合并,进一步地提取目标,大大提高了单帧检测的概率。仿真结果表明,该方法可以有效地在单帧图像中检测出目标。

A pre-processing algorithms based on the character of fractal is proposed for detecting IR target in natural background. In this algorithm the intrinsic difference in fractal characters between man-made objects and natural background is used to identify man-made object, and the method of combination the boundary is employed to get the target and improve the detection ratio of single image. The simulation results show that it can detect the small targets in single frame effectively.