基于图像深度信息的尺度不变特征变换算法误匹配点对剔除

被引:7
作者
刘政 [1 ]
刘本永 [2 ]
机构
[1] 贵州大学计算机科学与技术学院
[2] 贵州大学大数据与信息工程学院
关键词
图像配准; 深度估计; 特征点误匹配; 随机抽样一致性; 尺度不变特征变换特征点;
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
特征点匹配是基于特征点的图像配准技术中的一个重要环节。针对现有基于尺度不变特征变换(SIFT)图像配准技术特征点匹配不理想,也无法较客观、快速地筛选正确匹配点对的问题,提出结合图像深度信息进行特征点误匹配筛选剔除的方法。该算法首先根据模糊聚焦线索和机器学习算法估计出待配准图像的深度信息图,再提取SIFT特征点,并在特征点匹配环节利用随机抽样一致性(RANSAC)算法迭代循环,结合深度局部连续性的原理来进一步提高匹配精度。实验结果表明,该算法具有很好的误匹配点对剔除功能。
引用
收藏
页码:3554 / 3559
页数:6
相关论文
共 15 条
[1]  
SIFT flow: dense correspondence across scenes and its applications. Liu Ce,Yuen Jenny,Torralba Antonio. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2010
[2]  
2D-to-3Dimage conversion by learning depth from examples. Konrad J,Wang M,Ishwar P. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops . 2012
[3]  
Automatic 2D-to-3D image conversion using 3D examples from the internet. Konrad J,Brown G,Wang M,et al. Proceedings of SPIE the International Society for Optical Engineering . 2012
[4]  
"Histograms of Oriented Gradients for Human Detection,". Navneet Dalai,Bill Triggs. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005) . 2005
[5]  
"Super resolution based on scale invariant feature transform". Zhi Yuan,Peimin Yan,Sheng Li. International Conference on Audio, Language and Image Processing . 2008
[6]  
Automatic registration of satellite images. L.M.G. Fonseca,M.H.M. Costa. Proceedings of the Brazilian Symposium on Computer Graphic and Image Processing . 1997
[7]  
On the recovery of depth from a single defocused image. Zhuo S,Sim T. Computer Analysis of Images and Patterns . 2009
[8]  
图像处理、分析与机器视觉[M]. 人民邮电出版社 , ( ) 桑克 (Sonka, 2003
[9]  
MLESAC: A New Robust Estimator with Application to Estimating Image Geometry[J] . P.H.S. Torr,A. Zisserman. &nbspComputer Vision and Image Understanding . 2000 (1)
[10]   A SURVEY OF IMAGE REGISTRATION TECHNIQUES [J].
BROWN, LG .
COMPUTING SURVEYS, 1992, 24 (04) :325-376