摘要
为了克服无人机在空中执行遥感监测任务时受摄像头硬件性能的限制,以获得高分辨率的大面积区域图像,给出一种基于小波包变换的多分辨率图像拼接方法。先将小波包变换多分辨率的性质应用于Canny算法边缘检测,消除噪声干扰,提取更加完整的边缘,再通过基于像素灰度值的双匹配方法进行图像匹配和融合。仿真实验结果表明,所给方法拼接图像效果良好,速度较快,可以达到30幅的连续拼接标准,满足实际应用的要求。
Unmanned aerial vehicles （UAVs） cannot obtain the high resolution large area image due to the limitation of imaging equipment performance. A multi-resolution image mosaic method based on wavelet packet transform is therefore proposed. In this method the multi-scale analysis of wavelet packet transform and the edge detection of the traditional Canny algorithm is combined to eliminate the noise and extract more complete edge. Then the image matching and fusion are carried out by using the double matching method based on the pixel gray value. Experimental results show that this method has a good image stitching effect and a faster speed, and that the maximum number of continuous splicing images is 30, which can meet the requirement of practical application.
出处
《西安邮电大学学报》
2017年第2期53-59,共7页
Journal of Xi’an University of Posts and Telecommunications
基金
山东省自然科学基金资助项目(ZR2014FM030
ZR2013FM032
ZR2014FM010)
关键词
图像拼接
图像融合
图像匹配
边缘检测
小波包变换
image mosaic, image blending, image registration, edge detection, wavelet packet transform
