摘要
水下自动化操作处理使用机器视觉进行测量时,由于水面的折射、波动等会导致扰动出现,严重影响图像检测的质量。提出了一种基于图像复原的在线视觉测量算法。该方法基于一种图像质量评价时域高通滤波与空间解卷积滤波的水下图像复原算法。首先将获取的原始序列图像,通过基于图像质量评价的高通滤波器;然后进行时域均值滤波,接着通过高斯维纳空间解卷积滤波;最后通过标定的水下摄像机参数模型,求解零件孔距。实验结果表面,水下图像复原方法可有效去除水下扰动对图像的干扰,检测方法具有较高的检测精度,求解出的零件孔距平均误差小于0.1 mm。
When automatic operation processing using machine vision for measuring under water,disturbance effect caused by refraction and fluctuation of water surface sensitively degrades the video quality,and affecting the detection results. A new online visual measurement method is presented in this paper. The method is based on an image restoration algorithm. First,a temporal high pass filter is used to get a stabilized but blurry video,which using image quality assessment function. Second,a spatial Gauss-Wiener deconvolution filter is then used to estimate the video which would have been observed without turbulence. Finally,the feature holes’ distance of the part is solved by the calibrated underwater camera model. The experimental results show that the underwater image restoration method can effectively remove the disturbance effect. The average error of feature holes’ distance is less than 0.1 mm.
出处
《机电一体化》
2018年第8期29-33,共5页
Mechatronics
关键词
图像复原
维纳滤波
高斯分布
孔距
image restoration
Wiener filter
Gaussian distribution
holes’distance
