面向无人机水域影像的自动拼接方法  

Automatic Mosaic Method for UAV Water-Area Images

作　　者：王雅萍[1] 陈宜金[1] 谢东海[2] 吴俣[3] 

机构地区：[1]中国矿业大学(北京)地球科学与测绘工程学院,北京100083 [2]首都师范大学资源环境与旅游学院,北京100048 [3]中国科学院遥感与数字地球研究所,北京100094

出　　处：《长江科学院院报》2014年第5期92-96,共5页Journal of Changjiang River Scientific Research Institute

基　　金：中央高校基本科研业务费专项资金资助项目(2010YD06)

摘　　要：基于无人机航拍的水域影像,研究了该类影像的自动拼接方法。针对水域与陆地共存的影像(水域面积占比例较大,影像灰度值较小),利用SIFT和Harris算子共同提取特征点,再用RANSAC算法对错误匹配进行筛选,从而完成图像拼接。针对影像内容完全是水域的情况,利用无人机携带的POS定向数据辅助图像拼接。最后,以近海面油污监测的实例,阐述了本研究在无人机水资源监测和应急救灾中的实际应用价值。The automatic mosaic method for unmanned aerial vehicle （UAV） water-area images was researched. When there was not only water-area but also one small land in images （the monitoring water area was relatively larger and the image gradation changed small） , SIFT and Harris algorithms were used to extract the feature points, and RANSAC algorithm was used to filter the mismatched. When there was only water-area, POS directional data was used to help image mosaic. Oil spill monitoring for offshore surface was taken as an example to illustrate the practical application value of UAV in water resources monitoring and emergency relief.

关 键 词：UAV水域影像 SIFT HARRIS RANSAC POS 自动拼接 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]