基于无人机航拍图像快速拼接方法的研究  

Research on Fast Mosaic Method of Uav Aerial Image

作　　者：赵丽颖 付强[1] 黄丹飞[1] 钟艾琦 张玉爽 ZHAO Liying;FU Qiang;HUANG Danfei;ZHONG Aiqi;ZHANG Yushuang(School of Optoelectronic Engineering,Changchun University of Science and Technology,Changchun 130022)

机构地区：[1]长春理工大学光电工程学院,长春130022

出　　处：《长春理工大学学报（自然科学版）》2021年第6期39-46,共8页Journal of Changchun University of Science and Technology(Natural Science Edition)

基　　金：国家自然科学基金(61890953)。

摘　　要：无人机航拍图像拼接已经针对无人机航拍图像特征不明显、拼接速度较慢等问题,提出了一种基于无人机POS系统数据的快速拼接方法。针对无人机POS系统会受到地理环境、风速等影响以及无人机POS数据的精度较低等问题,引入光束区域网平差方法建立优化参数方程,对优化后的数据进行一系列的坐标变换计算出影像的四个角点的地理坐标,以第一张影像地理坐标为基准,进行航拍图像的快速拼接。拼接结果与基于SURF图像拼接算法进行对比,算法在拼接的速率比基于SURF算法更高。Due to the harsh geographic environment,complex climatic conditions,unobvious image features,and the small field of view of the drone in the marine area,it can only cover part of the area,etc.Therefore,in order to accurately grasp the ocean target information,it is of great significance to develop Uav aerial image Mosaic technology for Marine disaster and Marine emergency response.Aiming at the slow stitching speed of Uav aerial image without obvious features,in this paper,a fast stitching method based on Uav POS system data is proposed.Uav POS system will be affected by geographical environment,wind speed and other issues,and Uav POS data accuracy is low.An aerial photography parameter optimization model is established to improve the measurement parameter accuracy.A series of coordinate transformations are performed on the optimized data.Using the data of Uav POS system to calculate the geographic coordinates of the four corners of the image,based on the geographic coordinates of the first image,the orderly aerial image can be quickly assembled.

关 键 词：图像处理 图像拼接 航拍图像 无人机 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]