基于轮廓提取的毛竹直径测量方法研究

Research on Diameter Measurement Method of Moso Bamboo Based on Contour Extraction

针对目前人工测量原竹壁厚及径级尺寸中存在的效率低、准确率低、自动化程度低等问题,提出一种利用脉冲式线阵激光相机并基于OpenCV图像处理库和编码器原理的原竹竹筒径级及壁厚尺寸测量方法。首先,采用中值滤波降低采集竹筒图像中的噪声;其次,采用全局阈值分割法分离背景和竹筒内壁纹理信息并通过Canny算子提取竹筒横截面轮廓;最后,基于提取轮廓的像素点坐标计算得到了竹筒直径及壁厚尺寸。试验结果表明,对于任意选取的12个不同尺寸的竹筒,该算法在径级和壁厚测量结果的准确度分别达到95.12%和93.25%,同时平均测量时间为810 ms,远优于人工测量。基于机器视觉的毛竹径级及壁厚的检测方法可以满足测量所需的准确度并提高测量效率,为利用机器视觉技术代替人工检测提供了理论依据。

Aiming at the problems of low efficiency,low accuracy and low automation in the manual measurement of wall thickness and diameter level dimensions of raw bamboo,a method for the measurement of diameter level and wall thickness dimensions of raw bamboo canes using pulsed line array laser camera and based on the OpenCV image processing library and encoder principle is proposed.Firstly,the median filter is used to reduce the noise in the collected bamboo tube images;then,the global threshold segmentation method is used to separate the background and the texture information of the inner wall of the bamboo tube,and the cross-section profile of the bamboo tube is extracted by the Canny operator;finally,the diameter of the bamboo tube and the wall thickness dimensions of the bamboo tube are obtained by calculating based on the coordinates of the pixel points of the extracted profile.The experimental results show that for 12 different sizes of bamboo tubes selected arbitrarily,the accuracy of this algorithm reaches 95.12%and 93.25%for the diameter and wall thickness measurement results,respectively,while the average measurement time is 81o ms,which is much better than manual measurement.The machine visionbased detection method for diameter grade and wall thickness of moso bamboo can meet the required accuracy and improve the measurement efficiency,which provides a theoretical basis for the use of machine vision technology instead of manual inspection.