一种自动检测靶板角点的方法

靶板是立靶调炮速度测量系统的重要组成部分,针对传统的角点检测算法不能自动检测靶板角点的问题,提出了一种基于图像处理技术的靶板角点的检测方法。对CCD采集的靶板图像进行自适应平滑滤波提高图像信噪比,达到去除噪声和细节增强的目的,采用迭代式阈值分割算法分割靶板,通过形态学运算对分割后的像素点进行填充,利用连通域分析和链码法提取目标区域轮廓,利用多边形逼近算法对靶板轮廓进行逼近,利用逼近结果检测靶板角点。在CCD分辨率1280×1024,像元尺寸14μm,焦距50mm,测量距离5m的情况下,检测精度小于1.4mm,在立靶调炮速度测量中具有重要应用价值。

A Method of Automatically Detecting the Corner of a Target

The target is important part of vertical target speed measurement system,the traditional corner detection al-gorithm does not automatically detect the corner of the target question. Based on image processing technology corner of the target method is proposed. Adaptive smoothing filter is applied to the image acquired by CCD to improve the tar-get image signal to noise ratio, to achieve the purpose of removing noise and detail enhancement. Using iterative threshold segmentation algorithms split target, the contour of the target is approximated by the polygon approximation algorithm,using approximation results detecting the corner of the target. In the case of CCD resolution is 1280 × 1024 , pixel size 14μm , focal length 50mm, measuring distance 5m, detection accuracy is less than 1.4mm, in the vertical target gun speed measurement field has important application value.