摘要
实时电子稳像的目的是除去视频图像序列中因摄像机无意抖动而造成的图像扰动,从而保证修正后输出的视频图像序列是平滑、稳定的.灰度投影算法将初始的二维图像信息映射成两个独立的一维信息后,只对图像行列的投影曲线做一次相关运算便可较准确地检测出图像序列的帧间运动矢量,具有图像信息利用充分、算法稳定性好等优点.同时由于该算法对灰度图像进行直接处理,能够反映出图像的整体特征并有效地抑制了噪声,具有较高的稳像精度.实验结果表明,该算法具有较好的稳像效果.
Real-time electronic image stabilization is a method to timely stabilize image sequences in image stabilization algorithm,which remove the unwanted movements of image.So as to ensure that the output of the video image sequence is smooth and stable.A fast digital image stabilization algorithm based on gray pr-ojction is proposed in this paper：firstly,the image is projected into one-dimensional curves;then calculating movement vector by one-dimensional correlation.And adopting the gradation projection algorithm to detect the inter-frames motion vector of image sequence has many advantages,such as richly using the image information and good algorithm stability.Because the algorithm processes gray information directly and could restrain the noises,it can acquire high accurate image stabilization.And the simulation experiments validate the performance of the algorithm.
出处
《微电子学与计算机》
CSCD
北大核心
2010年第10期53-56,共4页
Microelectronics & Computer
基金
山西省青年科技研究基金(2009021019-2)
关键词
灰度投影
电子稳像
投影曲线
图像运动矢量
gray projection
image stabilization
projection curves
movement vector
