SIFT算法优化及其用于遥感影像自动配准

¹武汉大学遥感信息工程学院,武汉市珞喻路129号430079;²湖北工业大学土木工程与建筑学院,武汉市李家墩1村430068;³中共湖南省委互联网新闻宣传办公室,长沙市韶山路1号410011

基金项目: 湖北省自然科学基金资助项目(2008CDB388)；湖北省教育厅自然科学基础研究资助项目(G200514001)；国家863计划资助项目(2007AA120203)

详细信息

Improved SIFT Algorithm and Its Application in Automatic Registration of Remotely-sensed Imagery

¹School of Remote Sensing and Information Engineering,Wuhan University,129 Luoyu Road,Wuhan 430079,China;²Civil Engineering & Architecture School,Hubei University of Technology,1 Lijiadun,Wuhan 430068,China;³Internet News Management Office of Publicity Department of Hunan Provincial CCPCommittees,1 Shaoshan Road,Changsha 410011,China

Funds: 湖北省自然科学基金资助项目(2008CDB388)；湖北省教育厅自然科学基础研究资助项目(G200514001)；国家863计划资助项目(2007AA120203)

摘要: 对传统SIFT算法从特征点提取时间和匹配精度上进行了优化,基于优化算法提取的特征点对构建三角网进行小面元微分纠正配准。试验结果表明,该方法是一种有效的遥感影像自动配准方法。
- SIFT算法 /
- 小面元微分纠正 /
- 影像配准
Abstract: Optimized traditional SIFT algorithm from feature point extracting time and matching accuracy.Registration control points extracted from this algorithm are used to construct TIN for tiny facet primitive rectifying.Experiment results show that the method is an effective automatic registration method for remotely-sensed imagery.
- SIFT /
- tiny facet primitive /
- image registration