测绘学报 ›› 2015, Vol. 44 ›› Issue (10): 1125-1131.doi: 10.11947/j.AGCS.2015.20140467

• 摄影测量学与遥感 • 上一篇    下一篇

采用最优生成树的正射影像镶嵌线快速智能检测

陈继溢1, 许彪1, 张力1, 艾海滨1, 杜全叶1   

  1. 1. 中国测绘科学研究院, 北京100830;
    2. 国家测绘地理信息局卫星测绘应用中心, 北京 100830
  • 收稿日期:2014-09-07 修回日期:2015-02-06 出版日期:2015-10-20 发布日期:2015-10-23
  • 作者简介:陈继溢(1990—),男,硕士,研究方向为数字摄影测量,特别是影像无缝镶嵌.E-mail:whulife@gmail.com
  • 基金资助:
    国家自然科学基金(41271374);国家科技合作专项(2012DFA20930)

Fast and Intelligent Seamline Detection for Orthoimage Mosaicking Based on Minimum Spanning Tree

CHEN Jiyi1, XU Biao1, ZHANG Li1, AI Haibin1, DU Quanye1   

  1. 1. Chinese Academy of Surveying and Mapping, Beijing 100830, China;
    2. Satellite Surveying and Mapping Application Center, NASG, Beijing 100830, China
  • Received:2014-09-07 Revised:2015-02-06 Online:2015-10-20 Published:2015-10-23
  • Supported by:
    The National Natural Science Foundation of China (No.41271374),International Science & Technology Cooperation Program of China(No.2012DFA20930)

摘要: 针对高分辨率遥感影像提出了一种基于最优生成树的镶嵌线快速智能检测方法.该方法利用影像亮度差异和梯度构建重叠区域差分影像并视其为带权无向图,以Bottleneck模型为基础,采用最优生成树生成方法智能检测最佳镶嵌线.该方法回避了迭代搜索过程,具有速度快、效率高的优点.试验结果表明,所提出的方法能够在保证镶嵌线质量的同时具有较高的效率,可有效解决正射影像镶嵌过程中镶嵌线的自动选择问题.

关键词: 最优生成树, Bottleneck模型, 正射影像镶嵌, 镶嵌线智能检测

Abstract: A method of fast and intelligent seamline detection is presented that based on minimum spanning tree for high resolution orthoimage mosaicking. The image gradient and difference of homonymy pixels in the overlap area are calculated to build the differential image, which is deemed as a weighted undirected graph. According to the Bottleneck model, the optimal seamline is detected on the differential image by finding the minimum spanning tree of the weighted undirected graph. This method discards the conventional iterative process, thus achieves high speed. Experiment results illustrate the value of the proposed method which achieves great efficiency and guarantees the quality of the seamlines at the same time.

Key words: minimum spanning tree(MST), Bottleneck model, orthoimage mosaicking, intelligent seamline detection

中图分类号: