超声相控阵无损检测图像多目标跟踪算法

Multi-target Tracking Algorithm for Ultrasonic Phased Array NDT Images

提出一种超声相控阵无损检测图像的多目标跟踪算法。该算法能自动检测和跟踪多个弱小目标,无需任何学习过程和前景目标大小、形状等先验知识。通过Phasor-XS超声相控阵检测仪对试验模板采集的图像序列进行多次跟踪试验验证,结果表明:该方法能有效地对缺陷区域进行跟踪。

In this paper, a multi-target auto-tracking algorithm for ultrasonic phased array NDT images was proposed. The method can automatically detect and track several weak targets and doesn’t ask for any learning process and the prior knowledge of the size and shape of the foreground object. Employing the Phasor-XS ultrasonic phased array detector to verify the multiple tracking test of the image sequence of the experimental template detection shows that, this method can track the defect area effectively.