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:丁丁 张小国[1] DING Ding;ZHANG Xiao-guo(School of Instrumental Science and Engineering,Southeast Univers ity,Nanjing 210096,China)
机构地区:[1]东南大学仪器科学与工程学院,江苏南京210096
出 处:《测控技术》2020年第8期76-81,90,共7页Measurement & Control Technology
基 金:安顺市违章建筑监控系统开发(8522000157)。
摘 要:大范围定点监控存在摄像头预置位不足以覆盖全部监控区域的问题,而依靠摄像头本身的三维定位功能抓取监控点图像速度太慢,且可能存在定位误差。针对上述问题,提出了一种用于土地违法与违章建筑大范围定点监控的虚拟预置位图像提取及配准方法。对前后两帧图像进行灰度转化和中值滤波去除噪声点,使用基于金字塔的Lucas-Kanade光流算法计算前一帧图像强角点的光流,通过计算仿射变换得到帧间运动矢量;对相邻帧间运动矢量进行积分,得到每一帧图像总的运动矢量;通过提取出运动矢量与虚拟预置位运动矢量最接近的那一帧,得到所需的新时相虚拟预置位图像。实验结果表明,本文算法可以更快速地提取出同一监控点不同时相的监控对比图像,图像重叠率优于95%,不论是重叠率还是图像质量都可以很好地满足日常监控的需求。In the scene of large-scale fixed-point monitoring,the camera preset position is not enough to cover all the entire monitoring area,and the capturing speed of the image of the monitoring area by the three-dimensional positioning function of the camera itself is too slow,and there may be positioning errors.To solve these problems,a virtual preset position image extraction method is proposed for large-scale fixed-point monitoring of land illegality and illegal buildings.Gray-scale conversion and median filter are performed on the two frames before and after to remove noise points,the pyramid-based Lucas-Kanade optical flow algorithm is used to calculate the optical flow of the strong corner points of the previous frame and inter-frame motion vectors are obtained by computing the affine transformation.The motion vectors between adjacent frames are integrated to obtain the total motion vectors of each frame.The frame whose motion vector is closest to the motion vector of the virtual preset position is extracted,which is the required virtual preset position image.The experimental results show that the proposed virtual preset position image extraction algorithm can extract the monitoring point images more quickly,and the overlap rate of the new and old images is better than 95%,which can meet the needs of daily monitoring very well.
分 类 号:TP391.4[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:216.73.216.4