一种特征线提取的自适应阈值选择方法  

An Adaptive Threshold Selection Method for Feature Line Extraction

作　　者：邵煜 王亚伟 胡建华[3] 王昊天 万子豪 Shao Yu;Wang Yawei;Hu Jianhua;Wang Haotian;Wan Zihao(College of Computer Sciences and Technology,Taiyuan University of Science and Technology,Taiyuan 030024,China;Foshan Science and Automation Intelligence Technology Corporations,Foshan,Guangdong 528010,China;Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China)

机构地区：[1]太原科技大学计算机科学与技术学院,太原030024 [2]佛山市科自智能系统技术有限公司,广东佛山528010 [3]中国科学院自动化研究所,北京100190

出　　处：《机电工程技术》2022年第11期68-72,共5页Mechanical & Electrical Engineering Technology

基　　金：佛山市科技创新项目(编号:2017IT100022)。

摘　　要：特征提取是计算机视觉中的重要研究领域之一,其结果可进一步应用于虚拟现实、三维重建、智能驾驶、古建筑数字化保护等方面。目前,特征提取主要包括特征点、直线及区域等信息,其中,由于直线包含丰富的局部描述信息及纹理特征,基于特征线的特征提取方法研究具有重要的理论意义和实际应用价值。Hough变换作为一种常用的特征线提取方法,存在参数选择困难的问题。针对上述问题,设计与实现了一个可变阈值特征线提取方法。首先采用高斯滤波方法进行图像预处理;其次采用Canny边缘检测算法提取图像边缘点,并分析了不同的阈值对图像边缘提取结果的影响;然后采用Hough变换方法进行特征线提取,并分析影响Hough变换特征线结果的因素;最后通过定量分析给出阈值选取的结果。Feature extraction is the one of the most important research fields in computer vision.The results can be further applied to virtualreality,three-dimensional reconstruction,intelligent driving,digital protection of ancient buildings etc.At present,feature extraction mainlyincludes feature points,lines,regions and other information,among them,because the line contains abundant local description information andtexture features,the research on feature extraction method based on feature line has important theoretical significance and practical applicationvalue.Hough variation,as a commonly used feature line extraction method,has difficulty in parameter selection.To solve the above-mentioned,a variable threshold feature line extraction method was designed and implemented.The method first used a Gaussian filter methodfor image preprocessing.Secondly,Canny edge detection algorithm was used to extract image edge points,and analyzed the influence ofdifferent thresholds on image edge extraction results.Afterwards,used the Hough transformation to extract the feature lines,and analyzed thefactors that affect the results of Hough transformation in the meantime.Finally,the result of threshold selection was gotten by quantitativeanalysis.

关 键 词：CANNY边缘检测 阈值 HOUGH变换 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]