测绘通报 ›› 2017, Vol. 0 ›› Issue (4): 44-48.doi: 10.13474/j.cnki.11-2246.2017.0117

• 学术研究 • 上一篇    下一篇

POS辅助下的车载序列影像匹配

谢洪1,2, 吴博义3, 龚珣1, 王奕丹1   

  1. 1. 武汉大学测绘学院, 湖北 武汉 430079;
    2. 武汉市测绘研究院博士后创新实践基地, 湖北 武汉 430079;
    3. 山西省基础地理信息院, 山西 太原 030001
  • 收稿日期:2016-07-27 修回日期:2017-02-03 出版日期:2017-04-25 发布日期:2017-05-05
  • 作者简介:谢洪(1987—),男,博士,讲师,研究方向为三维激光测量.E-mail:hxie@sgg.whu.edu.cn
  • 基金资助:
    国家自然科学基金(41401527);测绘地理信息公益性行业科研专项(201512008);武汉市测绘研究院博士后创新实践基地科研项目(WGF2016001)

POS-aided Matching of Vehicle-borne Sequential Images

XIE Hong1,2, WU Boyi3, GONG Xun1, WANG Yidan1   

  1. 1. School of Geodesy and Geomatics of Wuhan University, Wuhan 430079, China;
    2. Postdoctors Innovation and Practice Base of Wuhan Geomatics Institute, Wuhan 430079, China;
    3. Shanxi Basic Geographic Information Institute, Taiyuan 030001, China
  • Received:2016-07-27 Revised:2017-02-03 Online:2017-04-25 Published:2017-05-05

摘要: 针对车载序列影像中所包含的具有大量重复纹理的建筑立面区域给现有匹配方法带来的误匹配率高、匹配点不足等不适应性问题,提出了一种联合POS辅助及KLT(Kanade-Lucas-Tomasi)角点特征跟踪的新匹配方法。通过充分利用POS信息所能够建立的局部近似建筑立面分层平面及DEM信息,获取KLT跟踪算法中所需的初始位移信息,并将建筑立面及路面区域进行分开追踪匹配,以保证匹配点的良好分布特性,最后利用RANSAC结合核线约束进行误差剔除得到最终匹配结果。试验证明本文方法能够有效解决车载序列影像中重复纹理区域的匹配问题,可高效获取分布均匀、数量充足的匹配特征点,为后期空中三角测量提供更稳健的同名约束条件。

关键词: 车载序列影像, POS辅助, KLT算法, RANSAC, 核线约束

Abstract: Aiming at the existing problem of high mismatching rate and insufficient corresponding points for vehicle-borne sequential images,as a result of the plentiful repetitive texture in the building façade area,a new method combining auxiliary POS and the KLT corner tracking algorithm is proposed in this paper. In the first place, through taking full advantage of POS information, the local approximate stratification façade plane and DEM are established to get the initial displacement required by the KLT algorithm.Then a new strategy tracking the façade and road area separately is employed to ensure a good distribution of matching points.After that,the final result is obtained by integrating the RANSAC and epipolar constraint to eliminate the matching error. The implemented experiments show that the presented method could solve the preceding mismatching problem,as well as obtaining adequate and uniformly distributed corresponding points for a more robust aerial triangulation process.

Key words: vehicle-borne sequential image, POS-aided, KLT algorithm, RANSAC, epipolar constraint

中图分类号: