低空无人机交叉口悬停影像抖动纠正

汪炯骅; 许涛; 李响

doi:10.13203/j.whugis20130834

低空无人机交叉口悬停影像抖动纠正

Geometric Correction for Images of Intersection Taken by Hovering UAV

摘要

摘要: 低空无人机影像在交通规划、城市管理、应急监控等领域正逐渐体现出其独到的优势,而将影像快速、准确地纠正与配准则是其发挥功用的必要前提。以拍摄于道路交叉口上方的无人机悬停视频为研究对象,探讨对其实现影像抖动纠正配准的方法。视频中的连续影像包含大量的近似地物及移动地物,难以直接采用传统的空间域或频率域方法进行配准。由此,提出了一种基于横道线识别的影像配准方法,经由图斑提取、筛选分类、轴线拟合及影像配准等步骤,实现了影像任意帧间的配准。利用无人机悬停拍摄的交叉口视频进行了验证,结果表明,该方法稳健、有效。

Abstract: Low altitudeunmannedaerialvehicle(UAV)imagesshaveincreasinglydemonstrateduniquead vantagesinthefieldsoftransportplanning,urbanmanagement,emergencymonitoring.TounderstandtheadvantagesofUAVimages,rapidandaccuratecorrectionandregistrationoftheimageareanecessaryprem ise.ThispapertakesaimageofintersectiontakenbyhoveringUAVasitsresearchtarget,anddiscussesthemethodofgeometriccorrectionandregistrationforsuchimages.Theimagecontainsalargenumberofsimilarfeaturesandmovingobjects,whichmakesitdifficulttobecorrectedintraditionalway,basedonspatialdo mainorfrequencydomain.Thus,thispaperproposesanimageregisteringmethodbasedonsemanticinforma tionextractedfromzebralines.Torealizeimagesregistrationbetweenarbitraryframes,thefollowingstepsarenecessary:patternsextraction,zebralinepatternspreparationandclassification,axisfittingandimageregistration.Finally,atestisperformedwithavideotakenbyUAV.Theresultsdemonstratethatthemeth odisrobustandeffective.

HTML全文

参考文献(0)

施引文献

资源附件(0)