摘要
由于受到强光束的干扰,低轨高清遥感图像拼接处的拼接边界容易出现突变。当前图像拼接方法因不能避免外界因素的干扰,无法实现图像的无缝拼接。为此,提出一种新的强光束干扰下低轨高清遥感图像无缝拼接方法。通过Retinex理论对强光束干扰下低轨高清遥感图像进行预处理,利用原始低轨高清遥感图像的照射光得到物体的反射性质,以获取物体自身的面貌。介绍了尺度不变特征变换(SIFT)算法的基本思想,通过SIFT特征匹配法对遥感图像进行配准处理;针对SIFT法效率低的弊端,利用区域分块法对其进行改进。通过幂比值拉伸方法对拼接缝进行消除。实验结果表明,采用所提方法得到的拼接图像拼接处无重叠,较为平滑,在保证拼接图像信息量、清晰度和整体质量的同时,效率较高。
Due to the strong interference of the light beam, Leo high-resolution remote sensing image mosaicing splicing boundary prone to mutation, the current image splicing method can？t avoid the interference of external fac-tors ,unable to realize the seamless Mosaic. To do this, then a new strong beam interference was put forward under the high-resolution remote sensing images seamless splicing method, then through Retinex theory under the strong light interference of high-resolution remote sensing image preprocessing, then the original high-resolution remote sensing images were used the illuminate of light reflection properties of the object, in order to get the appearance of the object itself. Scale invariant feature transform （SIFT） algorithm is introduced, the basic idea of using SIFT fea-ture matching method for remote sensing image registration process, in view of the shortcomings of low efficiency of SIFT method, using the method of region partition to be improved. Through drawing power ratio method to eliminate spelling a seam, the experimental results show that the proposed method for splicing image mosaicing without over-lapping, relatively smooth, the guarantee joining together information, clarity, and overall quality of the image at the same time, the efficiency is higher.
出处
《科学技术与工程》
北大核心
2017年第15期273-277,共5页
Science Technology and Engineering
基金
河南省教育厅科学技术研究重点项目(12B520047)资助
关键词
强光束干扰
低轨高清遥感图像
无缝拼接
strong beam interference leo high-resolution remote sensing images seamless splicing
作者简介
第一作者简介：潘亚（1980-）,女,汉族,河南商丘人,硕士,讲师.研究方向：图形图像处理、软件工程等.E-mail：panyaaaa@163.com.
通信作者简介：贾延明（1983-）男,汉族,河南洛阳人,硕士,讲师.研究方向：图形图像、计算机辅助设计、计算机仿真、人工智能等.
