一种改进图像拼接算法的仿真研究  被引量:12

Simulation Research on Improved Image Mosaic Algorithm

在线阅读下载全文

作  者:李军[1] 吴洁明[1] 

机构地区:[1]梧州学院计算机科学系,广西梧州543002

出  处:《计算机仿真》2012年第2期273-276,313,共5页Computer Simulation

基  金:广西教育厅科研项目(桂教科研[2007]34号文件200708MS057)

摘  要:研究图像拼接优化问题,在图像拼接中有精度要求,但由于受到光照、目标移动、视角等影响,图像含有噪声,且容易发生变形,传统Harris特征提取算子不能适应图像变形特性,容易获得很多错误的特征点,导致后继的图像拼接精度低。为了提高图像拼接精度,提出一种改进Harris算子的图像拼接方法。首先对待拼接图像进行平滑和几何校正处理,然后采用改进Harris算子提取图像特征点,最后采用傅立叶变换实现图像配准,平均值法进行图像融合,得到一幅全景图像。仿真结果表明,改进算法不仅减少了图像拼接耗费的时间,同时提高了图像精度和拼接的效率,达到了图像无缝拼接的效果。Study image mosaicking algorithm. Due to the effects of illumination, target mobile, angle of view, and image noise, the traditional Harris feature extraction operator can not adapt to the the image distortions, and is inclinable to get wrong feature points, result inlow accuracy of image mosaicking. In order to improve the accuracy of image mosaicking, the paper put forward a kind of improved Harris operator image mosaicking method. First, the mosaicked image was smoothed and geometricly corrected, and then the improved Harris operator was used to extract image feature points. Finally, Fourier - transform was used for image registration and average value method was used for image fusion to get a panoramic image. Simulation results show that the improved algorithm not only reduces the image mosaicking time -consuming, but also improves the accuracy and efficiency of image mosaicking and achieves the seamless effect of image mosaicking.

关 键 词:图像拼接 图像融合 图像特征点 

分 类 号:TP391[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象