基于机器视觉的汽车仪表盘指针检测

基于机器视觉构建汽车仪表自动检测系统已成为实现仪表生产测试的主要途径。基于图像空间到参数空间的收敛映射提出了改进CM-Hough变换检测算法对汽车仪表盘的指针位置实施检测。首先,介绍了基于机器视觉对汽车仪表的符号片及指针进行自动检测的系统组成。接着,针对经典Hough变换发散映射运算量大的缺点,提出了基于收敛映射CM-Hough变换进行指针检测的算法,给出了利用Hough变换的检测结果直接解算指针位置的方法。最后,将算法由软件编程实现,通过测试实验验证了算法的实时性和有效性,测试数据分析显示了指针位置误差小于1%。

Auto dashboard pointer detection Based on machine vision

The automatic test system of auto instrument based on machine vision has become the main way of doing instrument production and test . The improved CM-Hough transform detection algorithm based on convergence mapping from image space to parameter space is presented for dashboard pointer position. First of all, the automatic detection system is introduced. Then, in view of large computation for divergence mapping of classical Hough transform, the pointer detection algorithm based on the convergence mapping of CM-Hough transform is proposed and the method of calculating pointer position is given by using the test results of Hough transform. Finally, the real-time and effectiveness of the proposed algorithm is validated and the experimental results show that the pointer position error is less than 1%.