摘要
运动估计是图像超分辨率复原重要的步骤,直接影响最终的复原结果。针对运动估计中特征点匹配的问题,提出运用改进加速鲁棒特征(SURF)算法对图像的特征点进行匹配。再使用凸集投影(POCS)算法重建图像序列,最终得到复原的高分辨率图像。所提出的基于改进SURF算法的POCS算法对比其他图像复原算法,得到了峰值信噪比值较高、均方误差较低的复原图像,说明该算法的有效性。
Motion estimation is an important step of image restoration technique, which directly affects the result of the final restoration. To solve the problem of feature point matching in motion estimation, this paper used improved speeded up robust features(SURF) algorithm to match the feature points of the image. Using the projection onto convex set(POCS) reconstruction algorithm for image sequences, finally it got the high resolution image restoration. Compared with other image restored algorithm, the POCS algorithm based on improved SURF algorithm gets higher peak signal-to-noise ratio and lower mean square error restored image, and the experimental data has demonstrated the effectiveness of the proposed method.
引文
[1]STARK H,OSKOUI P.High-resolution image recovery from image-plane arrays,using convex projections[J].Journal of the Optical Society of America A Optics&Image Science,1989,6(11):1715-1726.
[2]肖杰雄.基于POCS算法的超分辨率重建[D].上海:上海交通大学,2009.
[3]徐鹏宇.超分辨率图像重建研究[D].上海:上海交通大学,2009.
[4]马伟林,朱国魂.改进SURF算法的图像拼接算法研究[J].微型机与应用,2014,33(24):45-47.
[5]张志强,王万玉,一种改进的双边滤波器算法[J].中国图像图形学报,2009,14(3):443-447.
[6]孙即祥.图像处理[M].北京:科学出版社,2009.
[7]BROWNFIGG D R K.The weighted median filter[J].Communication of the Association for Computing Machinery,1984,27(8):807-818.