摘要
针对航拍图像的特点和难点,提出了一种基于局部特征的航拍图像拼接方法,以提高拼接的质量和速度。该方法利用多分辨率技术和局部特征对航拍图像序列进行配准。通过仿射变换模型将拼接问题转化为像素点空间坐标变换的过程。采用渐入渐出的图像融合算法,消除拼接痕迹,实现了色彩和亮度的平滑过渡。实验结果表明,该方法对航拍图像序列和视频图像拼接效果良好,具有较高的实用价值。
This paper presents an algorithm of image mosaic based on local features to improve the effect and speed of aerial image mosaic. The method registers images according to multi-resolution analysis and local features The problem of image mosaic is turned into the problem of the coordinate transformation between the pixels by using aft＇me transformation. The weighted average algorithm is used to achieve smooth stitching results and eliminate intensity seam globally. Experimental results show that the proposed method is effective for the mosaic of real aerial sequences and video images.
出处
《电子科技大学学报》
EI
CAS
CSCD
北大核心
2013年第1期125-129,共5页
Journal of University of Electronic Science and Technology of China
基金
北京市自然科学基金(4112016
4123095)
北京市属高等学校人才强教深化计划专项(PHR201108075)
北京市属高等学校科学技术与研究生教育创新工程建设项目(PXM2012_014213_000079)
关键词
仿射变换
局部特征
图像拼接
图像配准
多分辨率分析
affine transformation
local features
image mosaic
image registration
multiresolution analysis
