基于亚像素定位的图像边缘检测策略研究  

Image Edge Detection Strategy Based on Sub-pixel Location

作　　者：刘浩 任宏 赵丁选 孙海超[1] 姜金辰 姜瑞凯[1] LIU Hao;REN Hong;ZHAO Dingxuan;SUN Haichao;JIANG Jinchen;JIANG Ruikai(Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Science,Changchun 130033,China;College of Mechanical Engineering,Yanshan University,Qinhuangdao 066004,China)

机构地区：[1]中国科学院长春光学精密机械与物理研究所,长春130033 [2]燕山大学机械工程学院,秦皇岛066004

出　　处：《农业机械学报》2024年第2期242-248,294,共8页Transactions of the Chinese Society for Agricultural Machinery

基　　金：国家自然科学基金项目(U20A20332)。

摘　　要：针对图像处理与计算机视觉技术中低对比度、边缘模糊图像的边缘检测问题,参考局部极值与梯度方向两种因素,并结合图像边缘方向趋势,提出了一种单像素边缘跟踪策略。相较于应用广泛的Canny算法,该跟踪策略无需设置全局阈值,实现方式更为简洁、高效;提取的图像边缘连续、平滑、完整,并有效地减少了图像边缘的冗余像素,进而提升了图像后续处理的效率;边缘跟踪方向抗干扰性强,具有较强的鲁棒性。为了减小检测的图像边缘与真实图像边缘之间的偏差、提高图像边缘检测的精度,参考边缘像素点的相邻区域灰度,以边缘像素点的梯度分布为依据对该像素点进行亚像素定位。经实验验证,经过亚像素优化的图像边缘检测策略可用于检测边缘模糊、对比度低的图像,检测的图像边缘完整、连续且平滑。该策略有效地消除了程序运算中引入的截断误差,提升了图像边缘检测精度,且适用于亮度5~100000 lx的高动态成像场景中。Image edge detection is a technique that extracts mutation information from images and is widely used in the fields of image processing and computer vision.The effectiveness of image edge detection directly affects the accuracy of subsequent region information extraction,target recognition,and pose measurement.Taking into account two factors:local extremum and gradient direction,and combining with the trend of image edge direction,a single-pixel edge tracking strategy was proposed for the edge detection problem of low contrast and edge blurred images.Compared with the widely used Canny algorithm,this tracking strategy did not require setting a global threshold,and its implementation was more concise and efficient.The extracted image edges were continuous,smooth,and complete,effectively reducing redundant pixels at the image edges,thereby improving the efficiency of subsequent image processing.Edge tracking direction had strong anti-interference ability and robustness.In order to reduce the deviation between the detected image edge and the real image edge,and improve the accuracy of image edge detection,the adjacent gray values of edge pixels were referred to,and the gradient distribution of edge pixels was used as the basis for sub-pixel localization of that pixel.Through experimental verification,the sub-pixel optimized image edge detection strategy can be used to detect images with blurred edges and low contrast.The detected image edges were complete,continuous,and smooth.This strategy effectively eliminated truncation errors introduced in program operations,improved the accuracy of image edge detection,which was suitable for high dynamic imaging scenes with a brightness range of 5~100000 lx.

关 键 词：图像处理 边缘检测 亚像素定位 单像素跟踪 鲁棒性 高动态 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]