基于角点特征的机载摄像系统电子稳像算法  

An Electronic Image Stabilizing Algorithm for Airborne Camera System

作　　者：鲜勇[1] 董力文 

机构地区：[1]海军装备部驻武汉地区军事代表局,湖北武汉430064 [2]华中光电技术研究所-武汉光电国家实验室,湖北武汉430223

出　　处：《光学与光电技术》2016年第2期54-59,共6页Optics & Optoelectronic Technology

摘　　要：为了消除载体姿态变化和振动造成的视频抖动,提出了一种机载摄像系统的电子稳像算法。将图像分为若干个块,每个块中取一个点作为特征点,采用块匹配算法在局部区域进行特征点匹配,然后利用改进的随机一致性检测算法剔除误匹配的特征点,最后采用卡尔曼滤波算法对图像的运动参数进行滤波,得到稳定后的视频图像。该算法时间复杂度和空间复杂度低,便于在硬件平台上实现,实验结果表明,该算法稳像精度高,精度达到1个像素,适应性好,能较好地实现图像序列稳定。In order to eliminate the video jitter caused by aircraft attitude change and vibration,an electronic image stabilizing algorithm for airborne camera system is presented in this paper.First,the reference image is divided into several blocks,select one point as the corner point in one block and use block matching algorithm for feature matching.Secondly,an improved RANSAC algorithm is proposed to eliminate the false matching points.Finally,Kalman filtering is applied in intentional motion parameter estimation.This method could be implemented on hardware platform because of low complexity.The experimental results show that this method could produce stabilized series of images with high accuracy and adaptability.

关 键 词：特征匹配 一致性检测 电子稳像 航拍图像 

分 类 号：TN911.73[电子电信—通信与信息系统]