计算机科学 ›› 2018, Vol. 45 ›› Issue (1): 313-319.doi: 10.11896/j.issn.1002-137X.2018.01.054
• 图形图像与模式识别 • 上一篇
厉丹,肖理庆,田隽,孙金萍
LI Dan, XIAO Li-qing, TIAN Jun and SUN Jin-ping
摘要: 针对拼接过程易受图像采集时曝光、尺度变化、旋转、环境噪声、光照等因素的影响,以及多图手动排序出错率高、耗时长等问题,提出了一种基于改进相位相关与特征点配准的多图拼接算法。首先,基于对数极坐标变换的改进相位相关算法来计算缩放、旋转和平移参数,根据冲激函数峰值实现多图自动排序;接着,在重叠位置提取Harris角点,改进的Ransac算法精确提纯匹配点对,优化变换矩阵以完成拼接;最后,通过利用NSCT变换算法多尺度分解低频、高频子带来制定融合策略,从而解决接缝明显的问题。实验结果表明,新算法 建立的模型参数准确且高效,拼接融合效果过渡自然,能较好地解决复杂环境及乱序图像的拼接问题。
[1] FANG S P,XIA X H,XIAO Y,et al.Lens Distortion Calibration Method for Linear Array Cameras[J].Journal of Xi’an Jiaotong University,2013,7(1):11-14.(in Chinese) 方素平,夏晓华,肖燕,等.一种线阵相机镜头畸变的标定方法[J].西安交通大学学报,2013,7(1):11-14. [2] VIALA C R,SALMERON A J S.Robust metric calibration of non-linear camera lens distortion[J].Pattern Recognition,2009,3(4):1688-1699. [3] SONG B S,FU Y Q,SONG H L.New Efficient Image Fusion Algorithm for Image Mosaic [J].Computer Science,2011,8(2):260-263,2.(in Chinese) 宋宝森,付永庆,宋海亮.一种消除图像拼接痕迹的新方法 [J].计算机科学,2011,8(2):260-263,2. [4] XU H,JIANG T B.Multi-source remote sensing image fusionalgorithm based on combined wavelet transform and HIS transform[J].Journal of Convergence Information Technology,2012,7(18):392-400. [5] HUANG L Q,CHEN C G.Study on Image Fusion Algorithm of Panoramic Image Stitching [J].Journal of Electronics & Information Technology,2014,6(6):1292-1298.(in Chinese) 黄立勤,陈财淦.全景图拼接中图像融合算法的研究[J].电子与信息学报,2014,36(6):1292-1298. [6] WU Z P,GUO L L,ZHU M C,et al.Improved image registration using feature points combined with image entropy [J].Infrared and Laser Engineering,2013,42(10):2846-2852.(in Chinese) 吴泽鹏,郭玲玲,朱明超,等.结合图像信息熵和特征点的图像配准方法[J].红外与激光工程,2013,2(10):2846-2852. [7] CHHETRI R P,ELRAHMANl A A.Filtering high-resolutionhyperspectral imagery in a maximum noise fraction transform domain using wavelet-based destriping [J].International Journal of Remote Sensing,2013,34(6):2216-2235. [8] ALFONSO A,EDGAR A S,RTUH M,et al(1)Phase-correlation guided area matching for realtime vision and video encoding[J].Journal of Real-Time Image Processing,2014,9(4):621-633. [9] REN Y,CHUA C S,HO Y K.Motion detection with nonstationary background[J].Machine Vision and Applications,2003,3(5):332-343 [10] HARRIS C,STEPHENS M.A combined corner and edge detec-tor[C]∥Proc.of International Joint Conference on Artificial Intelligence.1988:189-192. [11] LIU Y C,ZHU F.A new algorithm for X-corner detection[J].Journal of Image and Graphics,2006,11(5):656-660.(in Chinese) 刘阳成,朱枫.一种新的棋盘格图像角点检测算法[J].中国图象图形学报,2006,1(5):656-660. [12] SMITH S M,BRADY J M.SUSAN-A New Approach to Low Level Image Processing[J].International Journal of Computer Vision,1997,3 (1):45-78. [13] SCHMID C,MOHR R,BAUCKHAGE C.Evaluation of Interest Point Detectors[J].International Journal of Computer Vision,2000,37(2):151-172. [14] HUANG S.Research on image matching algorithm based onharris scale invariant reature[D].Hefei:Hefei University of Technology,2010.(in Chinese) 黄帅.基于 Harris尺度不变特征的图像匹配算法研究[D].合肥:合肥工业大学,2010. [15] YOO J C,CHOI B D,CHOI H K.1-D fast normalized cross-correlation using additions[J].Digital Signal Processing,2010,0(5):1482-1493. [16] SATTLER T,LEIBE B,KOBBELT L.Improving RANSAC’s efficiency with a spatial consistency filter[C]∥International Conference on Computer Vision.USA:IEEE Computer Society,2009:2090-2097. [17] ZHANG K J,DOU J J.Texture image retrieval based on Wavelet-directionlet transform and GLCM[J].Journal of Xuzhou Institute of Technology(Natural Science Edition),2016,1(4):65-69.(in Chinese) 张克军,窦建君.基于小波方向波变换和灰度共生矩阵的纹理图像检索[J].徐州工程学院学报(自然科学版),2016,1(4):65-69. [18] ZHANG B,LUO H Y,LIU J W,et al.RANSAC based robust localization algorithm for visual sensor network[J].Journal on Communications,2013,4(8):62-69.(in Chinese) 张波,罗海勇,刘冀伟,等.视觉传感器网络中基于RANSAC的顽健定位算法[J].通信学报,2013,4(8):62-69. |
No related articles found! |
|