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
机构地区:[1]周口师范学院计算机科学与技术学院,河南周口466001
出 处:《微电子学与计算机》2015年第7期133-137,共5页Microelectronics & Computer
基 金:河南省软科学研究项目(132400411253)
摘 要:在震动环境下,对目标视频采集中,常受到干扰因素作用导致图像采集稳定性差,需要对图像进行电子稳像处理,传统的电子稳像技术采用块匹配方法,受到阴影和障碍物遮挡等因素的干扰,块匹配电子稳像效果不好.由此提出一种基于高斯差分灰度补偿的角点匹配稳像技术.进行图像全局运动估计,将空间邻域信息融入到运动图像的幅度检测中,提取运动图像的幅度特征,把图像结构纹理信息类比为一个全局运动RGB三维位平面随机场,进行差分灰度补偿,在不同的尺度下选用合适的差分组合函数来描述图像的特征点,进行目标像素视差分析和像素图像配准,实现角点配准和电子稳像.仿真结果表明,采用该算法对失稳图像进行稳像处理,能有效提高电子稳像效果,峰值信噪比提高,稳像性能较传统方法优越.算法在远程探测和目标识别等领域具有重要的应用价值.In the vibration environment, the target video acquisition often be disturbed by the out factors, leading to image acquisition and poor stability, need to use image electronic image stabilization, traditional electronic image stabilization technology uses block matching method, by the shadow and obstacles occlusion interference, block matching electronic image stabilization effect is not good. An angle points gray compensation of image stabilization technique is proposed based on gauss gray compensation difference. For global motion estimation, the spatial neighborhood information to detecting motion of image in the magnitude of the amplitude characteristics, extraction of moving images, the image structure and texture information of analogy as a global movement of 3D RGB bit plane with the airport, the difference of gray level compensation, appropriate selection of the difference in different scales combined function to describe feature points of the image, pixel disparity target analysis and pixel image registration, achieve the corner point registration and electronic image stabilization. The simulation results show that, using the algorithm of image stabilization on instability of image, it can effectively improve the electronic image stabilization effect, the peak signal to noise ratio is improved, image stabilization performance is superior compared with the traditional method. The algorithm has important application value in the field of remote detection and target recognition.
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:216.73.216.222