基于图像处理技术的机场跑道胶痕检测系统  

Airport Runway Glue Mark Detection System Based on Image Processing Technology

作　　者：刘晓琳 孙晓璐 吴佳敏 LIU Xiao-lin;SUN Xiao-lu;WU Jia-min(College of Electronic Information and Automation,Civil Aviation University of China,Tianjin 300300,China)

机构地区：[1]中国民航大学电子信息与自动化学院,天津300300

出　　处：《计算机仿真》2024年第6期39-45,382,共8页Computer Simulation

基　　金：天津市研究生科研创新项目(人工智能专项)(2020YJSZX15);第十一期波音基金(20210715113)。

摘　　要：针对目前机场跑道胶痕检测方法效率低下和精度不足等问题,设计一套基于图像处理技术的机场跑道胶痕自动检测系统。首先,利用自适应阈值和滑动窗口,采用一种基于噪声判断规则的胶痕图像滤波算法,提高去噪能力;然后,引入小孔成像和Metropolis准则提高麻雀搜索算法的搜索能力和收敛速度,并利用改进的麻雀搜索算法优化K-Means进行胶痕分割,提高分割精度;最后,搭建实物平台,验证系统的可行性和有效性。实验结果表明,在处理多维函数时,改进麻雀搜索算法收敛精度和速度分别提高0.6和5量级;去噪胶痕图像的SSIM可达到0.7;改进图像分割算法可精准识别跑道胶痕。该系统具有良好的适应性和抗干扰性。Aiming at the problems of low efficiency and insufficient precision of the current airport runway glue mark detection method,an automatic detection system for airport runway glue marks based on computer vision is de⁃signed.Firstly,a glue mark image filtering algorithm based on noise judgment rules is adopted by using an adaptive threshold and sliding window to improve the denoising ability;then,pinhole imaging and Metropolis criterion are in⁃troduced to improve the searchability and convergence speed of the sparrow search algorithm,and the improved spar⁃row search algorithm was used to optimize K-Means for glue mark segmentation to improve the segmentation accuracy.Finally,a physical platform was built to verify the feasibility and effectiveness of the system.The experimental results show that when dealing with multi-dimensional functions,the convergence accuracy and speed of the improved sparrow search algorithm are improved by 0.6 and 5 orders of magnitude respectively;the SSIM of the denoised glue mark image can reach 0.7;the improved image segmentation algorithm can accurately segment the runway glue marks.The system has good adaptability and anti-interference.

关 键 词：系统设计 机场跑道胶痕 图像去噪 麻雀搜索算法 图像分割 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]