基于离线标定的快速图像拼接算法  

Fast image mosaic algorithm based on offline calibration

作　　者：于国栋 王春阳 兰孝野 徐鹏宇 张月[1] 刘晓辰 李忠琦 YU Guo-dong;WANG Chun-yang;LAN Xiao-ye;XU Peng-yu;ZHANG Yue;LIU Xiao-chen;LI Zhong-qi(63850 Troops of PLA, Baicheng 137001, China)

机构地区：[1]中国人民解放军63869部队,吉林白城137001

出　　处：《液晶与显示》2021年第10期1430-1436,共7页Chinese Journal of Liquid Crystals and Displays

基　　金：军队试验技术研究项目。

摘　　要：针对大场景、大视场图像应用和一般图像拼接算法速度慢的问题,采用了基于离线标定的快速图像拼接算法。在实际应用中多台相机位置固定,采用离线标定计算出图像拼接的单应性矩阵,实时拼接中直接加载该矩阵进行计算,从而省去了大量的特征提取和配准时间。在快速图像对齐的基础上,提出了一种基于YUV色彩空间的拉普拉斯金字塔的快速图像融合算法,相对传统拉普拉斯金字塔融合算法有更好的融合效果和更快的速度。实验结果表明,本文算法的图像融合速度是传统传统拉普拉斯图像融合的3倍,满足应用场景中实时图像拼接速度需求,具有良好的图像拼接效果。Aiming at the problem of large scene,large field of view image applications and the slow speed of traditional image stitching algorithms,a fast image stitching algorithm based on offline calibration is adopted.In practical applications,the positions of multiple cameras are fixed,and offline calibration is used to calculate the homography matrix of image-stitching,which saves a lot of feature extraction and registration time.On the basis of fast image alignment,a fast image fusion algorithm based on the Laplacian pyramid of YUV color space is proposed in this paper,and it has better fusion effect and faster speed than the traditional Laplacian pyramid fusion algorithm.Experimental results show that the image fusion speed of the article algorithm is three times that of traditional Laplacian image fusion.The alorithm of this paper can meet the real-time image stitching speed requirements in application scenarios,with good image stitching effects.

关 键 词：图像拼接 全景监控 特征提取 图像融合 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]