不变量约束和参数自适应的点状编码标志稳定识别方法  

Stable recognition of point-distributed coded targets with invariant constraints and parameter adaptation

作　　者：范生宏 蒋家庆 范文杰 任杰 李潘 刘阳 FAN Shenghong;JIANG Jiaqing;FAN Wenjie;REN Jie;LI Pan;LIU Yang(Beijing Prodetec Technology Co.Ltd.,Beijing 100083,China)

机构地区：[1]北京普达迪泰科技有限公司,北京100083

出　　处：《测绘科学》2024年第8期143-152,共10页Science of Surveying and Mapping

基　　金：科技创新2030—“新一代人工智能”重大项目(2021ZD0109800)。

摘　　要：针对GSI编码标志识别方法在参数自适应、高精度中心定位和稳定性方面存在一定局限性的问题,该文提出了一种改进的点状编码标志稳定高精度识别方法。首先,采用自适应局部均值二值化代替手动全局二值化。然后,通过融合灰度加权质心和椭圆拟合进行高精度中心定位。最后,在模板点确定过程中,基于二维交比不变量并融入点-线距离比值不变量,而在解码点确定过程中,将点-线距离比值不变量融入到仿射变换中,拟通过不变量约束实现几何参数的自适应并增强识别的稳定性。通过室内外实验与公开的方法以及商用软件V-STARS进行了比较。结果表明,该方法可以实现参数的自适应且识别更稳定更准确,性能与V-STARS相当。In response to the limitations of GSI coding flag recognition methods in parameter adaptation,high-precision center positioning,and stability,this paper proposes an improved point coding flag stable high-precision recognition method.Firstly,adaptive local mean binarization is adopted instead of manual global binarization.Then,high-precision center localization is achieved by integrating grayscale weighted centroid and ellipse fitting.Finally,in the process of template point determination,based on the two-dimensional intersection ratio invariant and incorporating the point line distance ratio invariant,and in the decoding point determination process,the point line distance ratio invariant is incorporated into the affine transformation,aiming to achieve adaptive geometric parameters and enhance recognition stability through invariant constraints.A comparison was made between indoor and outdoor experiments and publicly available methods,as well as commercial software V-STARS.The results show that this method can achieve parameter adaptation and more stable and accurate identification,with performance comparable to V-STARS..

关 键 词：编码标志 V-STARS 几何不变量 摄影测量 

分 类 号：P208.2[天文地球—地图制图学与地理信息工程]