基于Hausdorff距离的自动目标识别算法的研究

红外自动目标识别是智能化图像处理及应用开发的方法.由于传统的图像匹配方法受到诸如景物的遮挡、背景和噪声的影响比较大,并且需要建立模板与图像间的对应关系,因而使实际图像的匹配变得困难.为了克服上述缺陷,以便快速地进行图像匹配,提出了一种基于Hausdorff距离的自动目标识别算法.该算法不仅加快了匹配过程,提高了抗噪性能,而且能准确匹配遮挡图像.实验结果证明,该方法是正确有效的.

An Automatic Target Recognition Algorithm Based on Hausdorff Distance

Infrared automatic target recognition methodology is a key technology in intelligent image processing and application development, and image matching is an important method to recognize targets. The conventional matching methods are easily affected by scene occlusions, background and noise. On the other hand, the relationship of correspondence between model and image need to be built, which makes the matching process become more complicated. To overcome the problems of conventional Hausdorff distance and achieve image matching quickly, an automatic target recognition algorithm based on Hausdorff distance is introduced, which speeds up the matching process greatly. In addition, this method improves the resistance to noise and matches the image occlusions correctly. The experimental results demonstrate that the proposed method is feasible and effective.