摘要
针对传统影像拼接方法需要地面控制点支持或不能较好地适应无人机影像变形特性的问题，提出一种基于飞行姿态校正的无人机影像快速拼接方法。该方法通过构建无人机姿态角几何校正模型纠正原始影像，选择计算复杂度较低的改进Harris算法提取角点特征完成影像匹配和拼接。实验表明，新的方法能够较好地抵抗无人机飞行姿态变化较大带来的影响，性能稳定，拼接速度快、效果好。
In order to solve the problems in traditional image mosaic methods which need ground control point or cannot a- void the effects of Unmanned Aerial Vehicle （UAV） image distortion, the authors propose an improved UAV image mosaic meth- od in this paper. It corrects the original image by setting up UAV geometric correction model and choses the improved Harris algo- rithm with lower computational complexity to extract features and realize image matching and mosaic. The experimental results show that the improved method can resist against the effects of significant change of flight attitudes. Besides the performance is stable and the mosaic is fast and with high quality.
出处
《测绘科学与工程》
2015年第1期47-54,共8页
Geomatics Science and Engineering
