红外导引头边缘模板匹配跟踪算法研究

A Tracking Algorithm Based on Edge Template Matching for an Infrared Imaging Seeker

实时目标跟踪是当前红外成像导引头图像处理中的关键技术,文章提出了基于特征点邻域的边缘模板匹配目标跟踪算法,该算法从红外图像中获取特征点,以特征点为中心选取参考模板,然后利用边缘检测算法获得边缘点集,最后使用改进的Hausdorff距离测度进行边缘点集的匹配,从而实现实时目标跟踪。文章深入分析和探讨了模板的选取原则和提高算法实时性的四项措施。仿真实验测试证明,该方法能够很好的解决跟踪点滑动和漂移的问题,并满足实时性要求,跟踪稳定。

A new real-time tracking algorithm is proposed for tracking airborne target in the terminal of infrared imaging tracking. In this algorithm, a small set of feature points are extracted from an IR （infrared） image using the Harris arithmetic operators of image processing. Therefore we can select the reference template according to these points, and then we can obtain the edge points by using the edge detection arithmetic operators. By measuring the improved Hausdorff distance between the feature points template and IR image, we can track the target in real-time. In this paper, the principle of selecting template and improving real-time performance of the tracking algorithm is explained in detail. The experimental and simulation results show that our tracking algorithm can well overcome the two shortcomings of the existing algorithm： （1） the sliding of tracking point, （2） the locked frame excursion. Consequently, our algorithm can satisfy the requirement of real-time tracking and tracking stability.