改进Steger 算法流程的线激光中心线提取方法  

Line Laser Centerline Extraction with Improved Flow of Steger Algorithm

作　　者：王宇 丁召 赵麒 周骅 WANG Yu;DING Zhao;ZHAO Qi;ZHOU Hua(College of Big Data and Information Engineering,Guizhou University,Guiyang 550025,CHN;College of Mechanical Electronic and Engineering,Guizhou Minzu University,Guiyang 550025,CHN)

机构地区：[1]贵州大学大数据与信息工程学院,贵阳550025 [2]贵州民族大学机械电子工程学院,贵阳550025

出　　处：《光电子技术》2025年第1期57-63,共7页Optoelectronic Technology

摘　　要：提出一种基于海森矩阵的改进了Steger算法流程的线激光中心线提取方法。首先,采用高斯滤波、图像锐化等方法对图像进行预处理,去除噪声,加强灰度差别。其次,采用迭代式的全局阈值分割方法,将图像中的图像分割,得到图像中的感兴趣区域。最后,改进海森矩阵的计算原理,对Steger算法进行了优化,以求出亚像素点的位置,并采用非极大值抑制去除噪声点。计算结果表明,相较于传统的Steger算法,这一改进型算法能将中心线的提取速度提高4倍以上,而且能去除传统Steger算法上提取中心线会出现的冗余点,提取精度相比传统的灰度重心法和Steger算法分别提高了28%和19%。A line laser centerline extraction method based on Hessian matrix with improved process of Steger's algorithm was proposed.Firstly,the image was preprocessed using Gaussian filtering and image sharpening to remove the noise and enhance the gray level difference.Secondly,an iterative global threshold segmentation method was used to segment the image to get the region of interest in the image.Finally,the calculation principle of Hessian matrix was improved,and Steger's algorithm was optimized to find out the location of sub-pixel points,and non-extremely large value suppression was used to remove noise points.The computational results showed that compared with the traditional Steger algorithm,this improved algorithm could increase the extraction speed of the centerline by more than 4 times,and could remove the redundant points that would appear in the extraction of the centerline on the traditional Steger algorithm,and the extraction accuracy was improved by 28%and 19%compared with the traditional grayscale center of gravity method and the Steger algorithm,respectively.

关 键 词：线激光 图像处理 中心线提取 海森矩阵 感兴趣区域 

分 类 号：TN249[电子电信—物理电子学] TP301.6[自动化与计算机技术—计算机系统结构]