JOURNAL OF YANGTZE RIVER SCIENTIFIC RESEARCH INSTI ›› 2014, Vol. 31 ›› Issue (5): 92-96.DOI: 10.3969/j.issn.1001-5485.2014.05.019

• INFORMATION TECHNOLOGY APPLICATION • Previous Articles     Next Articles

Automatic Mosaic Method for UAV Water-Area Images

WANG Ya-ping1, CHEN Yi-jin1, XIE Dong-hai2, WU Yu3   

  1. 1.College of Geoscience and Surveying Engineering, China University of Mining & Technology,Beijing 100083, China;
    2.College of Resource Environment and Tourism, Capital Normal University,Beijing 100048, China;
    3. Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences,Beijing 100094, China
  • Received:2013-06-04 Revised:2014-05-12 Online:2014-05-12 Published:2014-05-12

Abstract: 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.

Key words: UAV water-area images, SIFT, Harris, RANSAC, POS, automatic mosaic

CLC Number: