检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:程钢[1,2] 李玮琳 李丽[1] CHENG Gang;Li Wei-lin;LI li(College of Humanities and Information,Changchun University of Technology,Changchun Jilin 130122,China;College of Mechanical and Electrical Engineering,Changchun University of Technology,Changchun Jilin 130012,China)
机构地区:[1]长春工业大学人文信息学院,吉林长春130122 [2]长春工业大学机电工程学院,吉林长春130012
出 处:《计算机仿真》2019年第1期197-200,共4页Computer Simulation
基 金:吉林省教育厅"十三五"科学技术项目(JJKH20171025KJ)
摘 要:多路传感器传输图像自动配准,能够获取高精度传感器图像。对传输图像配准时,需要在配准前对图像进行增强,计算图像配准参数,完成传输图像的自动配准。传统方法采用球面成像模型获取图像,将深度图与完成信息提取之后的图像进行配准,但忽略了计算图像配准参数,导致配准系数低、耗时长。提出基于区域选择的多路传感器传输图像自动配准方法,利用软阈值法对小波系数缩减去噪,于不同尺度实现分解系数增强。针对高频子带和低频子带图像实行非线性处理,提高图像对比度,完成多路传感器传输图像增强。重复提取图像特征,得到图像配准点对。使用结构相似度最大的配准点来计算图像配准参数,实现图像自动配准。仿真结果表明,上述方法平均配准耗时短,图像配准系数较高。与当前相关方法比较,所提方法可提高图像配准效率与精度,可行性和可靠性强。In the traditional method,the spherical imaging model was used to obtain the image,but the image registration parameters were not calculated,which results in low registration coefficient and high time consumption.Therefore,an automatic registration method for transmission image of multichannel sensor based on region selection was proposed. Firstly,the soft threshold method was used to reduce the noise of wavelet coefficient,and the decomposition coefficient was enhanced at different scales. Meanwhile,the nonlinear processing for high-frequency sub-band image and low-frequency sub-band image could improve image contrast and enhance image transmitted through multi-channel sensor. The image feature was extracted repeatedly to obtain the registration point pair. Moreover,the registration point with the largest structural similarity was used to calculate image registration parameters. Thus,the automatic registration of image was realized. Simulation results verify that the proposed method has short average registration time and high image registration coefficient. Compared with the current methods,the proposed method can improve the efficiency and accuracy of image registration,which has strong feasibility and reliability.
分 类 号:TP391[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:3.128.247.220