基于光斑轮廓特征的目标快速识别算法研究  

Research on fast target recognition algorithm based on spot contour feature

作　　者：谢忠旭 王志乾[1] 沈铖武[1] 刘旭[1,2] 孙浩洋 郑博文 成顺 XIE Zhong-xu;WANG Zhi-qian;SHEN Cheng-wu;LIU Xu;SUN Hao-yang;ZHENG Bo-wen;CHENG Shun(Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,Changchun 130033,China;University of Chinese Academy of Sciences,Beijing 100049,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,吉林长春130033 [2]中国科学院大学,北京100049

出　　处：《激光与红外》2024年第2期289-294,共6页Laser & Infrared

基　　金：吉林省科技发展计划项目(No.20230201039GX)资助

摘　　要：大视场的视觉着陆引导系统在引导无人机自主着陆过程中,需要快速检测出安装在无人机上的合作目标。该合作目标在图像上是以光斑形式存在,因此为了满足系统的实时性要求,本文提出了基于轮廓特征的快速检测光斑算法。该算法是根据光斑在图像中的特征,采用了目标裁剪方法,将原始图像中的光斑部分裁剪出来,从而降低算法运算量;再通过图像预处理,消除背景的无关信息与噪声干扰,增强光斑的清晰度;最后利用最小二乘算法进行椭圆拟合定位出光斑的中心位置。将本实验算法与其他光斑检测算法进行实验对比,从而验证系统的实时性。结果表明:利用本文算法可以在保证精度的同时将运行时间缩减到36 ms。The large-field visual landing guidance system needs to quickly detect the cooperative targets mounted on the UAV during the autonomous landing of the UAV.The cooperative target exists in the form of light spots on the image,so in order to meet the real-time requirements of the system,a fast spot detection algorithm based on contour features is proposed in this paper.Firstly,according to the characteristics of light spots in the image,the target clipping method is used to extract the light spots in the original image,so as to reduce the amount of computation.Then,through the image preprocessing,the irrelevant information and noise interference in the background are eliminated to enhance the clarity of the spot.Finally,the least square algorithm is used to locate the center of the light spot by ellipse fitting.The experimental algorithm is compared with other spot detection algorithms so as to verify the real-time performance of the system.The results show that the proposed algorithm can reduce the running time to 36ms while ensuring the accuracy.

关 键 词：视觉引导系统 大视场 目标快速识别 轮廓特征 中心定位 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TN247[自动化与计算机技术—计算机科学与技术]