测绘学报 ›› 2017, Vol. 46 ›› Issue (5): 554-564.doi: 10.11947/j.AGCS.2017.20160571

• 摄影测量学与遥感 • 上一篇    下一篇

基于多视影像匹配模型的倾斜航空影像自动连接点提取及区域网平差方法

张力1, 艾海滨1, 许彪1, 孙钰珊1,2, 董友强1,3   

  1. 1. 中国测绘科学研究院, 北京 100830;
    2. 武汉大学测绘学院, 湖北 武汉 430079;
    3. 中国矿业大学(北京)地球科学与测绘工程学院, 北京 100083
  • 收稿日期:2016-11-11 修回日期:2017-02-07 出版日期:2017-05-20 发布日期:2017-06-05
  • 作者简介:张力(1970-),男,博士,研究员,博士生导师,研究方向为摄影测量与遥感。E-mail:zhangl@casm.ac.cn
  • 基金资助:
    国家自然科学基金(41271374)

Automatic Tie-point Extraction Based on Multiple-image Matching and Bundle Adjustment of Large Block of Oblique Aerial Images

ZHANG Li1, AI Haibin1, XU Biao1, SUN Yushan1,2, DONG Youqiang1,3   

  1. 1. Chinese Academy of Surveying & Mapping, Beijing 100830, China;
    2. School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China;
    3. College of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing 100083, China
  • Received:2016-11-11 Revised:2017-02-07 Online:2017-05-20 Published:2017-06-05
  • Supported by:
    The National Natural Science Foundation of China (No. 41271374)

摘要: 自动可靠地获取精确且均匀分布的连接点并进行区域网平差解算,是使用倾斜航空影像进行高精度测绘、三维信息提取和三维城市模型构建等应用的前提。本文提出了一种实用化的大重叠率倾斜航空影像的全自动连接点匹配和联合区域网平差方法。一方面,针对倾斜航空影像因遮挡严重、尺度变化大和几何变形严重而引起的同名点匹配困难问题,充分利用POS数据和平均飞行高度等初始数据,同时顾及这些数据的误差,通过有效组合一种改进的ASIFT算法和基于窗口的多角度多视影像匹配模型(WMVM),使用由粗到细的多分辨率分层匹配策略完成连接点的全自动提取;另一方面,在传统的最小二乘光束法平差的基础上,根据倾斜航空影像数据的特点,提出了基于稳健估值原理的粗差自动探测与剔除关键算法。最后,利用多组典型试验区域的倾斜航空影像数据试验结果验证了所提算法的可靠性、精度和实际性能。

关键词: 倾斜航空摄影, 光束法最小二乘平差, 仿射不变性特征提取算子, 特征提取, 多视影像匹配

Abstract: Due to advantages such as ease of interpretation, completeness through mitigation of occluding areas, as well as system accessibility, the aerial oblique images have found their place in numerous civil applications. However, for these applications high quality orientation data are essential. A fully automatic tie-point extraction procedure is developed to precisely orient the large block of oblique aerial images, in which a refined ASIFT algorithm and a window-based multiple-viewing image matching (WMVM) method are combined. In this approach, the WMVM method is based on the concept of multi-image matching guided from object space and allows reconstruction of 3D objects by matching all available images simultaneously, and a square correlation window in the reference image can be correlated with windows of different size, shape and orientation in the search images.Then another key algorithms, i.e. the combined bundle adjustment method with gross-error detection & removal algorithm, which can be used for simultaneously orient the oblique and nearly-vertical images will be presented. Finally, through the experiments by using real oblique images over several test areas, the performance and accuracy of the proposed method is studied and presented.

Key words: oblique aerial photos, bundle adjustment, affine invariant feature detector, feature extraction, multiple-image matching

中图分类号: